{ "documents": 6, "tokens": 14052, "document_frequency": { "0": 2, "0-9": 2, "0-9]+\\\\.[0-9": 1, "0-9a-f]{64": 1, "1": 2, "1,424": 1, "1.0": 4, "10": 1, "1000": 1, "11": 1, "12": 2, "12-gram": 1, "12-token": 1, "128": 1, "13": 1, "16": 1, "18": 1, "18446744073709551615": 1, "192": 1, "2": 2, "2020-12": 1, "2026-09-10t22:14:03z": 1, "2119": 1, "24": 1, "256-word": 1, "3": 1, "3-token": 1, "32": 1, "394": 1, "4": 1, "4.0": 1, "400,000-page": 1, "41": 1, "42": 1, "48211904": 1, "5": 2, "512": 3, "512-token": 1, "5g": 1, "6": 1, "64": 2, "64-bit": 1, "64-character": 1, "64.7": 1, "7": 2, "7.3": 1, "754": 1, "79200000": 1, "7e6732e23d92fd8b496d04c40a6b7ac005dafa8c622167c82bb6bffcb1b786df": 2, "8": 1, "8174": 1, "8601": 1, "89": 1, "8a7de7d08415184f00d76c06ccc1072fde13905ac24087d8a54cd51544653ae7": 1, "9": 1, "900": 1, "96": 1, "a": 6, "a-z": 2, "a-z0-9._-]+/[a-z0-9": 1, "a-z0-9._-]{1,64}/[a-z0-9._-]{1,64": 1, "ab": 1, "aber": 1, "able": 1, "about": 4, "above": 3, "absence": 1, "absent": 2, "absolute": 1, "absorbs": 1, "acceptable": 1, "accepted": 1, "accident": 2, "accounted": 1, "across": 2, "act": 1, "acts": 1, "actually": 1, "adapter": 4, "adapter's": 2, "adapter.addressspace": 1, "adapter.indexing": 1, "adapter.indexing.terms": 1, "adapter.name": 1, "adapters": 1, "adapters/{owner}/{name}/tags/{tag": 1, "adapters/{owner}/{name}/versions/{hash}/manifest.json": 1, "adapters/{owner}/{name}/versions/{hash}/{target}/{file": 1, "add": 2, "added": 2, "adding": 2, "additionalproperties": 1, "address": 3, "address\",\"title\",\"url\",\"language\",\"published\",\"keywords": 1, "address_space": 1, "address_space\":\"per-corpus\",\"indexing\":{\"mode\":\"full_text\"},\"catalog_version\":\"v1": 1, "addressable": 1, "addressed": 1, "addresses": 2, "addressing": 3, "addressspace": 1, "adds": 1, "after": 3, "afterwards": 3, "again": 2, "against": 4, "agree": 2, "agreeing": 1, "agreement": 1, "ai": 1, "alias": 2, "all": 4, "alle": 1, "allem": 1, "allen": 1, "aller": 1, "alles": 1, "allocated": 1, "allocates": 1, "almost": 2, "alone": 1, "already": 2, "already-scoped": 1, "als": 1, "also": 3, "altering": 1, "am": 1, "among": 1, "an": 6, "and": 6, "another": 2, "another's": 1, "answer": 2, "answers": 3, "any": 4, "anybody": 1, "anyone": 1, "anything": 6, "anyway": 1, "anywhere": 1, "apart": 2, "appear": 1, "appears": 1, "appendix": 1, "applied": 1, "applies": 2, "apply": 2, "applying": 1, "approval": 1, "approximate-nearest-neighbour": 1, "arbitrary": 1, "architecture": 2, "architectures": 1, "are": 6, "arguments": 1, "array": 1, "arrives": 1, "artifact": 4, "artifacts": 1, "as": 4, "ascending": 1, "asked": 1, "asking": 2, "asks": 2, "asserts": 1, "assume": 1, "assumed": 2, "assumption": 1, "at": 5, "attach": 1, "attaches": 1, "attribution": 1, "auch": 1, "auf": 1, "aus": 1, "author": 1, "authoritative": 1, "authority": 1, "automatic": 1, "average": 1, "avoid": 2, "away": 1, "aws": 1, "b": 1, "back": 2, "band": 1, "bands": 1, "bare": 1, "barely": 1, "base": 1, "basis": 1, "batches": 1, "bc": 1, "be": 6, "because": 4, "become": 1, "becomes": 2, "been": 2, "before": 3, "begin": 2, "beginning": 1, "begins": 1, "behave": 1, "behind": 1, "bei": 1, "being": 3, "belief": 1, "belong": 2, "belongs": 1, "below": 2, "beside": 2, "best": 1, "better": 1, "between": 4, "bin": 1, "binary32": 1, "bio": 1, "bis": 1, "bist": 1, "bit": 1, "bits": 1, "bits\",\"shingle_tokens": 1, "blanked": 1, "bm25": 1, "body": 2, "body's": 1, "boilerplate": 1, "boolean": 1, "both": 3, "bound": 2, "boundary": 3, "break": 1, "breaking": 1, "broken": 1, "bucket": 2, "build": 1, "builder": 1, "building": 4, "builds": 1, "built": 5, "built-in": 1, "built_at": 1, "builtat": 1, "business": 1, "but": 1, "buys": 2, "by": 6, "byte": 1, "bytes": 3, "c": 1, "cached": 1, "cadence": 1, "call": 1, "called": 3, "caller": 1, "calls": 1, "came": 3, "can": 5, "candidate": 1, "candidates": 1, "cannot": 4, "canonical": 1, "canonicalisation": 1, "canonicalised": 1, "canonicalising": 1, "canonicalize": 1, "cap": 2, "capability": 1, "capitals": 1, "captured": 1, "car": 1, "carried": 2, "carries": 6, "carry": 3, "carrying": 2, "case": 3, "cases": 2, "casts": 1, "catalog": 1, "catalog_version": 1, "catalog_version\",\"embed\",\"simhash\",\"bands\",\"entities\",\"stopwords": 1, "catalogversion": 2, "catches": 1, "caveat": 1, "cc": 1, "ceiling": 1, "certify": 1, "chain": 1, "change": 2, "changed": 2, "changes": 3, "changing": 1, "character": 1, "characters": 1, "cheap": 2, "check": 2, "checkable": 2, "checked": 2, "checks": 2, "choice": 1, "chosen": 1, "chunked-256w-mean-v1": 1, "chunks": 1, "ci": 1, "citations": 1, "cites": 1, "cites/outlink": 1, "citesdomain": 1, "citesdomain/rollup": 1, "claim": 1, "claimed": 1, "claiming": 1, "claims": 1, "class": 1, "classifier": 1, "clean": 1, "client": 1, "clock": 1, "close": 1, "closed": 1, "cluster": 1, "cluster's": 1, "clusters": 1, "collation": 1, "collide": 1, "collision": 1, "column": 2, "combination": 1, "combined": 1, "combines": 1, "combining": 1, "come": 2, "comes": 3, "command": 2, "commands": 1, "commercially": 1, "common": 1, "companies": 1, "company's": 1, "comparability": 1, "comparable": 1, "compare": 1, "compared": 1, "compares": 2, "comparing": 1, "comparison": 1, "complete": 1, "completeness": 1, "composer": 1, "composer's": 1, "composition": 1, "compressed": 1, "compression": 1, "compromised": 1, "compute": 1, "computed": 1, "computing": 1, "concatenated": 1, "concatenation": 1, "concerned": 1, "conditions": 1, "config": 1, "configuration": 1, "configured": 1, "conform": 1, "conformance": 2, "conforming": 4, "conforms": 1, "connection": 1, "consequence": 1, "consistently": 1, "consists": 2, "const": 1, "constant": 1, "constants": 1, "constraint": 1, "construction": 1, "consulted": 1, "consumer": 1, "contact": 1, "contain": 2, "contains": 2, "content": 4, "content-addressed": 1, "content_sha256": 1, "contents": 1, "contentsha256": 1, "contract": 4, "contradicts": 1, "contributes": 1, "convenience": 2, "convention": 1, "conventions": 1, "coordinate": 1, "coordinated": 1, "copied": 1, "copies": 1, "copy": 3, "corpora": 6, "corpora/{owner}/{name}/index.json": 1, "corpora/{owner}/{name}/tags/{tag": 1, "corpora/{owner}/{name}/versions/{hash}/manifest.json": 1, "corpora/{owner}/{name}/versions/{hash}/manifest.sig": 1, "corpora/{owner}/{name}/versions/{hash}/{payload": 1, "corpus": 6, "corpus's": 2, "corpus-local": 2, "corpus-relative": 1, "correction": 1, "correctly": 1, "correspondence": 1, "cost": 1, "costs": 2, "could": 3, "count": 3, "countable": 1, "countables": 1, "countables.bands.hash": 1, "countables.bands.keep": 1, "countables.bands.shingle_tokens": 1, "countables.catalog_version": 1, "countables.catalogversion": 1, "countables.embed.dimension": 1, "countables.embed.method": 1, "countables.embed.model": 1, "countables.embed.normalized": 1, "countables.entities": 1, "countables.simhash.bits": 1, "countables.simhash.shingle_tokens": 1, "countables.stopwords.languages": 1, "countables.stopwords.name": 1, "countables.stopwords.sha256": 1, "counted": 1, "counting": 1, "counts": 2, "court": 1, "cover": 1, "covered": 2, "covering": 1, "covers": 2, "cpus": 1, "crashing": 1, "crawl": 2, "crawler": 1, "create": 1, "criterion": 1, "cross": 2, "cross-corpus": 1, "crosses": 2, "curates": 1, "current": 1, "cursor": 1, "cursorcolumn": 1, "customers": 1, "cut": 1, "da": 1, "damit": 1, "dann": 1, "darwin-aarch64/adapter-folder\":{\"bytes\":2370704,\"sha256": 1, "das": 1, "dass": 1, "data": 1, "database": 2, "day": 1, "dazu": 1, "debug": 1, "decide": 1, "decided": 1, "decides": 1, "decimal": 1, "decision": 1, "decisions": 2, "declaration": 1, "declarations": 1, "declare": 2, "declared": 2, "declares": 4, "declaring": 2, "declined": 1, "decoration": 1, "deduplicated": 1, "deep": 1, "default": 2, "default\",\"rules_version": 1, "defaults": 1, "defect": 1, "defence": 1, "defend": 1, "defends": 1, "defines": 2, "dein": 1, "deine": 1, "delete": 2, "deletes": 1, "deletion": 2, "deliberate": 1, "deliberately": 3, "delta": 1, "deltas": 1, "dem": 1, "den": 1, "denn": 1, "depending": 1, "depends": 3, "deployment": 2, "der": 1, "dereferenced": 1, "derivation": 1, "derivation-over-membership": 1, "derive": 3, "derived": 3, "deriving": 1, "des": 1, "described": 1, "description": 1, "descriptions": 1, "dessen": 1, "detached": 1, "detected": 1, "determine": 1, "determinism": 1, "deterministic": 1, "deu": 1, "dich": 1, "did": 2, "die": 1, "dies": 2, "diese": 1, "diesem": 1, "diesen": 1, "dieser": 1, "dieses": 1, "differ": 1, "difference": 1, "different": 6, "differently": 2, "diffing": 1, "digest": 1, "digit": 1, "dimension": 1, "dir": 1, "directions": 1, "directive": 1, "directory": 4, "disagree": 2, "disagreed": 1, "disagrees": 1, "discovered": 1, "disk": 1, "display": 1, "distance": 1, "distinct": 2, "distinctive": 1, "distinctiveness": 1, "distributed": 1, "distribution": 2, "divide": 1, "divided": 1, "divisible": 1, "do": 4, "doc": 1, "doch": 1, "docs/readme.md": 1, "document": 4, "document's": 2, "document_id": 1, "document_id\",\"content_sha256\",\"hashed\",\"embed_method": 1, "documentation": 2, "documented": 1, "documentid": 1, "documents": 4, "documents.jsonl": 1, "documents.jsonl.zst": 1, "does": 5, "doing": 1, "domain": 1, "domains": 1, "dominated": 1, "done": 2, "dort": 1, "dot": 2, "double": 1, "down": 1, "downloads": 1, "draft": 1, "drawn": 1, "drift": 1, "drop": 1, "dropped": 1, "drops": 1, "du": 1, "duplicate": 1, "duplicateof": 1, "duplicateof/texthash": 1, "duplicates": 1, "durch": 1, "during": 1, "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855": 1, "each": 5, "earlier": 1, "earns": 1, "easy": 1, "ed25519": 1, "edge": 1, "edges": 1, "edit": 1, "ein": 1, "eine": 1, "einem": 1, "einen": 1, "einer": 1, "eines": 1, "either": 2, "eleven": 1, "else": 5, "else's": 1, "embed": 1, "embed.method": 1, "embed_method": 1, "embed_model": 1, "embedded": 1, "embedding": 2, "embedmethod": 1, "embedmodel": 1, "embeds": 1, "emit": 1, "emitted": 2, "empty": 2, "end": 2, "endorses": 1, "endpoints": 1, "ends": 1, "eng": 1, "engine": 2, "english": 1, "enough": 1, "entities": 2, "entities.jsonl": 1, "entity": 4, "entity\":\"cve-2026-1188\",\"documents\":3": 1, "entity\":\"cve-2026-1188\",\"documents\":[3,41,900": 1, "entity-mediated": 2, "entries": 1, "entry": 2, "enum": 1, "er": 1, "error": 2, "es": 1, "establish": 1, "estimating": 1, "etld+1": 1, "etwas": 1, "eu": 1, "euch": 1, "euer": 1, "ever": 2, "every": 5, "everyone": 3, "everything": 2, "everywhere": 2, "evicted": 1, "evicts": 2, "evidence": 1, "exact": 1, "exactly": 3, "example": 1, "exception": 1, "exist": 2, "existed": 2, "existing": 1, "exists": 1, "exit": 1, "exiting": 1, "exits": 1, "expect": 1, "expensive": 1, "explaining": 1, "explanation": 1, "express": 1, "extends": 1, "external_links": 1, "extra": 2, "extra\":{\"external_links\":42,\"https\":true": 1, "extract": 1, "extractable": 1, "extracted": 2, "extraction": 2, "fact": 1, "fact-about-a-document": 1, "facts": 1, "fail": 2, "failed": 1, "failing": 1, "fails": 3, "failure": 3, "falls": 1, "false": 2, "far": 1, "faster": 1, "feature": 1, "features": 1, "feed": 2, "feeds": 1, "fetch": 1, "fetchable": 1, "fetched": 4, "fetches": 2, "fetching": 2, "few": 1, "fewer": 2, "field": 2, "fields": 2, "fifteen": 1, "file": 6, "file's": 1, "files": 2, "files\":{\"linux-x86_64/adapter-folder\":{\"bytes\":2841064,\"sha256": 1, "fill": 2, "filled": 1, "filter": 1, "find": 2, "findable": 1, "finding": 1, "fingerprint": 1, "fingerprints": 1, "finish": 1, "finished": 1, "fire": 1, "fired": 1, "fires": 1, "first": 6, "fitted": 1, "fix": 1, "fixed": 2, "fixes": 2, "fixture": 2, "fixtures": 1, "flips": 1, "floating": 1, "floating-point": 1, "floor": 1, "fnv-1a": 1, "fnv1a-64": 1, "folder": 1, "follow": 1, "follows": 4, "for": 6, "force": 1, "forever": 1, "form": 1, "formality": 1, "format": 2, "forming": 1, "four": 1, "fragment": 1, "fragments": 1, "free": 2, "french": 1, "frequencies": 1, "frequencies.jsonl": 1, "frequency": 1, "frequent": 1, "from": 5, "from\":3,\"to\":41,\"rule\":\"quotes/minhash_shingle\",\"version\":1,\"support\":{\"shared_bands\":4,\"of\":64": 1, "frontier": 1, "full": 1, "full_text": 1, "fulltext": 1, "function": 1, "further": 1, "fuses": 1, "fusion": 1, "für": 1, "gained": 1, "gate": 2, "gegen": 1, "generate": 1, "generative": 1, "genre": 1, "genuine": 1, "get": 1, "gets": 1, "gewesen": 1, "give": 1, "given": 1, "gives": 1, "global": 2, "global\",\"per-corpus": 1, "go": 1, "goes": 1, "gone": 1, "good": 2, "governed": 1, "governs": 1, "gpu": 1, "graph": 1, "grow": 1, "growing": 1, "guarantee": 1, "h": 1, "h(entries": 1, "hab": 1, "habe": 1, "haben": 1, "had": 2, "haircut": 1, "half": 2, "halfway": 1, "hamming": 1, "hand": 2, "handbook": 1, "handed": 1, "handing": 1, "happened": 1, "happens": 1, "hardware": 1, "has": 6, "hash": 5, "hashed": 1, "hasher": 1, "hashes": 3, "hashing": 1, "hat": 1, "hatte": 1, "hatten": 1, "have": 3, "having": 1, "he": 1, "head": 1, "header": 1, "headline": 1, "held": 2, "hello": 1, "her": 1, "here": 6, "hers": 1, "herself": 1, "hex": 1, "hidden": 1, "hier": 1, "high-water": 1, "highest": 2, "him": 1, "himself": 1, "hin": 1, "hinter": 1, "his": 1, "hold": 3, "holding": 1, "holds": 2, "honour": 1, "host": 3, "host's": 1, "host/]owner/name[@tag": 1, "how": 6, "however": 1, "http": 1, "https": 2, "https://download.zetlyn.com/zetlyn-entities-1.json": 2, "https://example.org/a": 1, "https://example.org/a#top": 1, "https://example.org:443/a": 1, "https://json-schema.org/draft/2020-12/schema": 1, "hub": 3, "hub.example.com/suspero/handbook@v3": 1, "hub.zetlyn.com": 1, "hubs": 1, "i": 2, "i-th": 1, "ich": 1, "id": 1, "idea": 2, "identical": 1, "identified": 1, "identifier": 1, "identifies": 1, "identify": 1, "identity": 2, "ids": 1, "ieee": 1, "if": 5, "ignore": 1, "ignores": 2, "ihm": 1, "ihn": 1, "ihnen": 1, "ihr": 1, "ihre": 1, "ihrem": 1, "ihren": 1, "ihrer": 1, "ihres": 1, "im": 1, "image_count": 1, "imagecount": 1, "images": 2, "implement": 1, "implementation": 3, "implementations": 2, "impose": 1, "improvement": 1, "improves": 1, "in": 5, "including": 2, "incompatibility": 1, "incremental": 1, "indem": 1, "independent": 1, "index": 1, "index's": 1, "index.json": 1, "indexed": 1, "indexes": 2, "indexing": 2, "indistinguishable": 1, "individually": 1, "inference": 1, "inferred": 1, "initial": 1, "input": 1, "ins": 1, "inside": 4, "insignificant": 1, "instance": 1, "instead": 1, "instruction": 1, "integer": 1, "integrity": 1, "intended": 1, "interface": 1, "internal": 1, "internet": 1, "interoperability": 1, "intersect": 1, "into": 4, "intra-publisher": 1, "invalid": 1, "invalidating": 1, "invent": 1, "inventing": 1, "inverse": 1, "involved": 1, "irrelevant": 1, "is": 6, "iso": 1, "ist": 1, "it": 6, "items": 1, "iterates": 1, "iteration": 1, "its": 4, "itself": 2, "jede": 1, "jedem": 1, "jeden": 1, "jeder": 1, "jedes": 1, "jene": 1, "jenem": 1, "jenen": 1, "jener": 1, "jenes": 1, "jetzt": 1, "job": 1, "join": 1, "joined": 1, "joining": 1, "json": 2, "just": 1, "kann": 1, "keep": 3, "keeping": 2, "keeps": 3, "kein": 1, "keine": 1, "keinem": 1, "keinen": 1, "keiner": 1, "keines": 1, "kept": 2, "key": 2, "keyed": 1, "keys": 2, "keyword-indexed": 1, "keywords": 1, "keywords\",\"full_text": 1, "kind": 1, "kinds": 1, "know": 3, "known": 1, "knows": 1, "können": 1, "l1": 1, "l2": 1, "l3": 1, "label": 1, "labelled": 1, "language": 2, "language's": 1, "languages": 1, "large": 1, "last": 2, "later": 2, "latest": 1, "law": 1, "layout": 3, "leave": 2, "leaves": 1, "left": 2, "legal": 2, "legible": 1, "length": 1, "less": 1, "lets": 2, "letter": 1, "letting": 1, "level": 2, "levels": 1, "lexical": 2, "lexically": 1, "lf": 1, "licence": 2, "licences": 1, "lifetime": 1, "like": 3, "likes": 1, "limit": 1, "limits": 1, "line": 4, "lines": 1, "link": 1, "links": 2, "list": 1, "list's": 1, "listed": 1, "listing": 1, "lists": 2, "little": 1, "little-endian": 1, "live": 1, "lives": 1, "locale's": 1, "locally": 1, "log": 2, "logistic": 1, "long": 1, "longer": 1, "look": 1, "looked": 1, "looking": 3, "looks": 3, "loses": 1, "lost": 2, "lower": 1, "lowercase": 1, "lowercased": 3, "ltd\",\"processing\":false": 1, "lying": 1, "machen": 1, "machine": 2, "machines": 1, "made": 1, "magnitude": 1, "mail": 1, "main": 1, "maintained": 1, "maintains": 1, "major": 2, "major.minor": 2, "make": 2, "makes": 5, "making": 1, "man": 1, "manche": 1, "manifest": 4, "manifest's": 1, "manifest.json": 1, "manifest.sig": 1, "manifests": 1, "map": 1, "mapped": 2, "mark": 1, "marking": 1, "marks": 2, "match": 1, "matched": 1, "matches": 1, "material": 1, "matter": 2, "matters": 1, "maturity": 1, "maximum": 1, "maxitems": 1, "may": 4, "me": 1, "mean": 1, "meaning": 2, "means": 3, "meant": 1, "measured": 1, "measurement": 1, "measuring": 1, "mechanism": 1, "median": 1, "medical": 1, "mein": 1, "meine": 1, "member": 1, "members": 1, "membership": 1, "memory": 1, "mention": 3, "mentions": 1, "mentions/nercanonical": 1, "merge": 1, "merging": 1, "message": 1, "method": 2, "mich": 1, "middle": 1, "millions": 1, "min(⌈√n": 1, "minimum": 1, "minlength": 1, "minor": 2, "minproperties": 1, "minus": 2, "mir": 1, "mirror": 1, "mis-synced": 1, "missing": 1, "mit": 1, "mode": 1, "mode\":\"fulltext": 1, "mode\":\"keywords\",\"terms\":15": 1, "model": 2, "model\",\"dimension\",\"normalized": 1, "moderation": 1, "modified": 1, "months": 1, "more": 5, "most": 4, "move": 1, "moved": 2, "moves": 3, "moving": 2, "multilingual-e5-small": 1, "muss": 1, "musste": 1, "must": 1, "mutable": 1, "my": 1, "myself": 1, "müssen": 1, "n": 1, "nach": 1, "name": 6, "name\",\"address_space\",\"indexing": 1, "name\",\"contact": 1, "name\",\"sha256\",\"languages": 1, "named": 1, "named-list": 2, "names": 4, "namespace": 1, "namespaced": 2, "namespaces": 1, "naming": 1, "native": 1, "natural": 1, "navigation": 1, "near": 1, "near-duplicate": 1, "near-duplicates": 1, "nearduplicate": 1, "nearduplicate/simhash": 1, "nearly": 1, "need": 1, "needed": 1, "needs": 3, "negotiates": 1, "neither": 4, "nested": 1, "never": 4, "new": 2, "newer": 1, "news": 1, "next": 1, "nicht": 1, "nichts": 1, "nine": 1, "no": 5, "nobody": 3, "noch": 1, "noise": 1, "non-empty": 1, "non-zero": 1, "none": 3, "nor": 2, "normal": 1, "normalised": 1, "normalized": 1, "normative": 1, "not": 6, "nothing": 4, "notices": 1, "nouns": 1, "now": 1, "nowhere": 1, "null": 1, "number": 2, "numbered": 1, "numbers": 1, "nun": 1, "nur": 1, "ob": 1, "object": 3, "obligation": 2, "obligations": 1, "obsoletes": 1, "obsoletes/rfc-index": 1, "obtain": 1, "obtained": 1, "occur": 1, "oder": 1, "of": 6, "off": 1, "offer": 1, "offered": 1, "offering": 1, "often": 1, "ohne": 1, "old": 1, "older": 1, "omits": 1, "on": 6, "once": 3, "one": 6, "ones": 3, "only": 5, "onto": 2, "open": 3, "open\",\"closed": 1, "operator": 2, "operator's": 3, "opinions": 1, "opposite": 1, "optional": 3, "options": 1, "or": 6, "order": 4, "ordering": 1, "orderings": 1, "orders": 2, "ordinary": 3, "organisation": 1, "original": 2, "other": 2, "other's": 1, "others": 1, "otherwise": 3, "our": 1, "ours": 1, "ourselves": 1, "out": 2, "outbound": 2, "outlink": 1, "output": 2, "outside": 2, "over": 5, "overlap": 1, "overwrite": 1, "overwritten": 1, "owes": 1, "own": 4, "owner": 3, "owner/name": 1, "owns": 1, "paced": 1, "packaging": 1, "page": 2, "page's": 1, "pages": 1, "pair": 1, "pairing": 1, "pairs": 1, "parameter": 2, "parameters": 1, "parses": 1, "parsing": 1, "part": 3, "partial": 1, "particular": 1, "parties": 3, "parts": 2, "partway": 1, "party": 2, "pass": 2, "passes": 3, "passing": 1, "path": 3, "pattern": 1, "pay": 1, "payload": 1, "payload's": 1, "payloads": 2, "paywall": 2, "paywalled": 1, "people": 2, "people's": 1, "per": 5, "per-corpus": 2, "per-document": 1, "per-file": 1, "per-token": 1, "performs": 1, "permission": 2, "permissions": 1, "permit": 1, "person": 1, "picked": 1, "pin": 2, "pinned": 4, "pinning": 3, "pins": 3, "place": 2, "plain": 1, "plainly": 1, "planned": 1, "plans": 1, "platform": 1, "plus": 2, "point": 2, "pointer": 1, "pointers": 1, "policy": 1, "population": 1, "port": 1, "position": 1, "positions": 1, "positive": 1, "possible": 1, "posting": 1, "postings": 1, "posture": 1, "precisely": 1, "precision": 1, "precondition": 1, "predicate": 1, "predicates": 1, "prefix": 1, "prepared": 1, "pretend": 2, "price": 1, "printed": 1, "prints": 1, "private": 1, "privilege": 1, "privileged": 1, "problem": 1, "process": 1, "processes": 1, "processing": 1, "produce": 4, "produced": 2, "producer": 1, "producers": 1, "produces": 4, "producing": 1, "product": 2, "program": 3, "program's": 1, "programming": 1, "programs": 1, "promise": 1, "properties": 2, "property": 1, "proprietary": 1, "prose": 1, "protocol": 3, "provenance": 1, "proves": 1, "provides": 1, "public": 1, "publish": 1, "publishable": 1, "published": 5, "published\":\"2026-03-04\",\"language\":\"en\",\"url\":\"https": 1, "publisher": 2, "publisher's": 2, "publishers": 2, "publishers.jsonl": 1, "publishes": 2, "publishing": 2, "purpose": 1, "put": 2, "puts": 2, "putting": 2, "quality": 1, "quantity": 1, "queries": 1, "query": 1, "question": 3, "questions": 1, "quietly": 1, "quotation": 1, "quote": 1, "quotes": 1, "quotes/minhashshingle": 1, "raises": 1, "random": 1, "range": 1, "rank": 1, "ranked": 1, "ranking": 1, "ranks": 1, "rare": 1, "rather": 6, "raw": 1, "re-fetching": 1, "re-index": 1, "re-indexing": 1, "re-running": 1, "reach": 2, "reached": 1, "reaches": 1, "read": 4, "read_gate": 1, "reader": 4, "reader's": 1, "readgate.default": 1, "readgate.rulesversion": 1, "reading": 3, "reads": 2, "real": 1, "reason": 4, "reasoned": 1, "reasons": 2, "rebuild": 2, "rebuilt": 1, "recall": 1, "recipe": 1, "recipient": 1, "recognise": 1, "recognizer": 3, "recognizer's": 2, "recognizer.md": 1, "recomputation": 1, "recompute": 1, "recomputed": 1, "recomputes": 1, "reconfiguration": 1, "reconstructed": 1, "record": 2, "record's": 1, "recorded": 1, "records": 2, "recovered": 1, "redistributing": 1, "redistribution": 1, "reduction": 1, "ref": 1, "reference": 2, "references": 1, "refers": 1, "refusal": 1, "refuse": 1, "refused": 2, "refuses": 3, "refusing": 1, "regardless": 1, "register": 1, "registered": 1, "registration": 1, "registry": 1, "regulator's": 1, "reintroduces": 1, "reject": 1, "rejected": 1, "related": 1, "relates": 1, "relation": 2, "relation's": 1, "relations": 3, "relations.jsonl": 1, "release": 3, "releases": 2, "relevance": 1, "relevant": 1, "remains": 1, "remove": 1, "removed": 2, "removes": 1, "renames": 1, "renders": 1, "repeated": 1, "replaced": 2, "replacement": 1, "replaces": 2, "replacing": 1, "replay": 1, "report": 1, "reported": 1, "reporting": 2, "reports": 2, "repository": 3, "reproducible": 2, "republishing": 1, "request": 1, "require": 1, "required": 2, "requirement": 1, "requires": 2, "reserved": 2, "resolve": 2, "resolved": 1, "resolves": 2, "rest": 2, "restated": 1, "rested": 1, "rests": 1, "results": 1, "resume": 1, "resumes": 1, "retains_for": 1, "retention": 2, "retention.evicts": 1, "retracted": 1, "retrain": 1, "retrieval": 1, "return": 1, "returns": 2, "reuse": 1, "rfc": 1, "right": 2, "rights": 1, "rights.jsonl": 1, "rolled": 1, "rounding": 1, "route": 2, "route's": 2, "routes": 1, "routing": 1, "row": 2, "rows": 2, "rule": 2, "rule's": 1, "rule_set_id": 1, "rule_set_id\",\"adapter\",\"countables\",\"retention\",\"read_gate\",\"payloads": 1, "rules": 1, "rules_version": 1, "rulesetid": 1, "run": 4, "run's": 1, "running": 1, "runs": 5, "runtime": 1, "s3": 1, "safe": 1, "same": 6, "sample": 1, "saw": 1, "say": 1, "saying": 2, "says": 4, "scale": 1, "scales": 1, "schema": 1, "schemas": 1, "scheme": 2, "scheme's": 1, "schon": 1, "scope": 2, "scoped": 1, "scoping": 1, "score": 1, "scores": 1, "scp": 1, "search": 3, "searchable": 1, "searched": 3, "searching": 1, "second": 3, "second-class": 1, "seconds": 1, "section": 3, "see": 3, "seen": 1, "sees": 2, "segment": 1, "segments": 1, "sehr": 1, "sein": 1, "seine": 1, "seinem": 1, "seinen": 1, "seiner": 1, "seines": 1, "selbst": 1, "send": 1, "sends": 1, "sense": 1, "sent": 2, "sentence": 1, "separate": 3, "separated": 1, "separately": 1, "separates": 1, "separator": 1, "sequence": 1, "serialization": 1, "serialized": 1, "serializing": 1, "serve": 2, "served": 3, "server": 2, "serves": 2, "serving": 2, "set": 2, "set's": 1, "sets": 2, "setting": 1, "settings": 1, "settled": 1, "seven": 1, "several": 2, "sha-256": 2, "sha-256(address": 1, "sha256": 1, "share": 3, "shared": 3, "shares": 2, "sharesentity": 1, "sharesentity/distinctive": 1, "she": 1, "shifted": 1, "shingle": 1, "shingle_tokens": 1, "shingle_tokens\",\"hash\",\"keep": 1, "ship": 1, "shipped": 1, "shipping": 1, "ships": 1, "short": 1, "should": 3, "show": 1, "showing": 1, "shown": 2, "sich": 1, "side": 1, "sides": 1, "sie": 1, "signature": 1, "signatures": 1, "signing": 1, "signs": 1, "silence": 1, "silently": 2, "simhash": 1, "similarity": 1, "simply": 4, "since": 1, "sind": 1, "single": 3, "sit": 1, "site": 1, "sitting": 1, "six": 1, "size": 1, "skip": 1, "skipped": 1, "slash": 2, "slashes": 1, "slot": 1, "slow": 1, "small": 1, "smaller": 1, "smallest": 1, "so": 4, "software": 2, "solche": 1, "soll": 1, "sollte": 1, "some": 1, "somebody": 2, "something": 2, "somewhere": 2, "son": 1, "sondern": 1, "sonst": 1, "sort": 1, "sorted": 2, "source": 2, "source\":\"example.com\",\"title\":true,\"summary\":false,\"attribution": 1, "source's": 1, "source-available": 1, "sources": 1, "space": 2, "spaces": 1, "span": 3, "spanning": 1, "spans": 2, "speaking": 1, "speaks": 2, "spec_version": 1, "spec_version\",\"corpus\",\"version\",\"built_at\",\"documents\",\"relations": 1, "spec_version\":\"1.0\",\"adapter\":\"zetlyn/folder\",\"version\":\"…\",\"interface\":1": 1, "specific": 2, "specification": 6, "specification's": 1, "specifications": 1, "specified": 2, "specifies": 2, "specversion": 1, "spell": 1, "spends": 1, "split": 1, "splits": 1, "srv/handbook": 1, "stable": 1, "stale": 1, "stamped": 1, "stand": 1, "standard": 2, "standards": 1, "stands": 1, "start": 1, "started\",\"text": 1, "starting": 1, "state": 2, "stated": 4, "statement": 1, "states": 4, "static": 1, "statistics": 1, "statistics.json": 1, "status": 2, "stay": 2, "stays": 1, "step": 3, "steps": 1, "still": 2, "stop": 1, "stops": 2, "stopwords": 1, "storage": 1, "store": 2, "stored": 2, "stores": 2, "stream": 1, "string": 1, "string\",\"null": 1, "strip": 1, "strongest": 1, "structure": 2, "structured-data": 1, "structures": 1, "subject": 1, "subscriber": 2, "subscribers": 2, "subset": 1, "substance": 1, "substitute": 1, "substitutes": 1, "succeeded": 1, "successfully": 1, "such": 2, "suite": 1, "suites": 1, "sum": 1, "summary": 1, "summed": 1, "summing": 1, "supplied": 1, "supplies": 1, "support": 2, "supports": 1, "survive": 1, "surviving": 1, "sus.pero/handbook": 1, "suspero/handbook": 2, "suspero/handbook.v2": 1, "suspero/handbook@v3": 1, "suspero/wiki": 1, "symmetric": 1, "sync": 1, "syndication": 1, "system": 1, "t\":\"delete\",\"address\":\"docs/old.md": 1, "t\":\"doc\",\"address\":\"docs/readme.md\",\"title\":\"getting": 1, "t\":\"done\",\"complete\":false": 1, "t\":\"done\",\"complete\":true": 1, "t\":\"hello\",\"interface\":1,\"adapter\":\"suspero/jira\",\"ends\":true,\"divisible\":false": 1, "t\":\"mark\",\"cursor\":\"2026-09-11t08:00:00z": 1, "t\":\"skip\",\"address\":\"handbook/scan.pdf\",\"reason\":\"no": 1, "table": 3, "tables": 1, "tag": 1, "tags": 1, "tags/{tag": 1, "take": 1, "takedown": 1, "taken": 1, "takes": 2, "taking": 3, "target": 1, "taste": 1, "teaser": 1, "technical": 1, "technology": 1, "tell": 2, "tempting": 1, "tens": 1, "tenth": 1, "term": 1, "term's": 1, "terminates": 1, "terms": 1, "testable": 1, "text": 4, "text_chars": 1, "text_chars\",\"word_count\",\"text_hash\",\"catalog_version\",\"embed_model\",\"extra": 1, "text_hash": 1, "texthash": 1, "tf-idf": 1, "than": 6, "that": 6, "the": 6, "their": 3, "theirs": 1, "them": 6, "themselves": 1, "then": 3, "there": 3, "therefore": 3, "these": 3, "they": 5, "thing": 3, "things": 1, "third": 1, "this": 6, "those": 2, "though": 1, "thousands": 1, "thread": 1, "threading": 1, "threads": 1, "three": 3, "threshold": 1, "through": 2, "tied": 1, "ties": 1, "time": 1, "timestamp": 1, "title": 2, "titles": 1, "to": 6, "together": 4, "token": 2, "tokens": 1, "toml": 1, "too": 1, "tools": 1, "top": 1, "top-level": 1, "topics": 1, "total": 1, "tracking": 1, "trademark": 1, "trailing": 1, "trained": 1, "transitive": 1, "translate": 1, "transport": 1, "travel": 1, "travels": 1, "treated": 1, "treats": 1, "tree": 1, "trees": 1, "tree}/{owner}/{name}/tags/{tag": 1, "tried": 1, "trigrams": 1, "trim": 1, "true": 2, "truncated": 1, "trust": 1, "trusted": 1, "trusts": 2, "trustworthy": 1, "tuning": 1, "twelfth": 1, "twelve": 2, "twice": 4, "two": 6, "type": 2, "type\":\"string": 1, "types": 2, "um": 1, "unable": 1, "unaffected": 1, "unambiguous": 1, "unbounded": 1, "unchanged": 1, "unchecked": 1, "uncompressed": 1, "und": 1, "under": 5, "unigram": 1, "unique": 2, "unit": 1, "unix": 1, "unless": 2, "unpacking": 1, "unqualified": 1, "unrelated": 2, "uns": 1, "unser": 1, "unsere": 1, "unstable": 1, "untagged": 1, "unter": 1, "until": 2, "up": 2, "update": 1, "updates": 2, "updates/rfc-index": 1, "uppercase": 1, "url": 2, "usable": 1, "use": 2, "used": 1, "usefully": 1, "userinfo": 1, "uses": 5, "using": 1, "usual": 1, "usually": 1, "utf-8": 1, "utmsource": 1, "valid": 1, "validate": 1, "validating": 1, "value": 3, "values": 2, "vector": 1, "vectors": 1, "vectors.f32": 1, "verbatim": 1, "verified": 1, "verify": 2, "version": 4, "versioned": 2, "versioning": 3, "versions": 4, "versions/{hash}/manifest.json": 1, "versus": 1, "very": 1, "viel": 1, "violates": 1, "visible": 1, "vocabulary": 4, "vocabulary/zetlyn-entities-1": 1, "voice": 1, "vom": 1, "von": 1, "vor": 1, "vote": 1, "voting": 1, "walks": 1, "want": 1, "wants": 2, "war": 1, "waren": 1, "warning": 1, "warst": 1, "was": 5, "way": 4, "ways": 1, "we": 1, "weaker": 1, "web": 3, "web's": 1, "web-shaped": 1, "weg": 1, "weighting": 1, "weil": 1, "weiter": 1, "welche": 1, "well": 1, "well-formed": 1, "wenn": 1, "went": 1, "werde": 1, "werden": 1, "were": 1, "what": 6, "whatever": 4, "when": 3, "whenever": 2, "where": 4, "wherever": 1, "whether": 3, "which": 5, "whichever": 1, "while": 1, "whitespace": 1, "who": 3, "whoever": 1, "whole": 2, "whole-page": 1, "whom": 1, "whose": 3, "why": 3, "wie": 1, "wieder": 1, "wiki": 1, "will": 1, "window": 1, "wir": 1, "wird": 1, "wirst": 1, "with": 6, "withdrawal": 1, "withheld": 1, "within": 2, "without": 5, "wo": 1, "wollen": 1, "wollte": 1, "word": 1, "word_count": 1, "words": 1, "worker": 1, "working": 2, "world": 1, "worse": 1, "worth": 2, "would": 5, "write": 4, "writes": 2, "writing": 3, "written": 3, "wrong": 3, "wrote": 1, "während": 1, "würde": 1, "würden": 1, "x": 1, "yet": 1, "yield": 1, "you": 4, "your": 2, "yours": 2, "yourself": 1, "yourselves": 1, "zero": 2, "zetlyn": 4, "zetlyn-entities-1": 4, "zetlyn-entities-2": 2, "zetlyn-entities-[0-9": 1, "zetlyn-interface": 1, "zetlyn-stopwords-1": 1, "zetlyn-stopwords-[0-9": 1, "zetlyn.document": 1, "zetlyn.document.hashed": 1, "zetlyn.manifest": 1, "zetlyn/folder": 1, "zetlyn/news": 1, "zetlyn/web": 1, "zetlyn:////