{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KPY4AZWEI6TJOR7W5UC42NFXUL","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b5ba2b214f8d44744f93037a85d6e3763d0cf585b263738fefbdd64cf2072234","cross_cats_sorted":["cs.IR","math.ST","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-21T15:54:23Z","title_canon_sha256":"feebebe88bd229c6cde983afe8a35bb6f838ea714f1c0c4234062120c070889a"},"schema_version":"1.0","source":{"id":"2507.15742","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.15742","created_at":"2026-07-05T11:45:37Z"},{"alias_kind":"arxiv_version","alias_value":"2507.15742v2","created_at":"2026-07-05T11:45:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.15742","created_at":"2026-07-05T11:45:37Z"},{"alias_kind":"pith_short_12","alias_value":"KPY4AZWEI6TJ","created_at":"2026-07-05T11:45:37Z"},{"alias_kind":"pith_short_16","alias_value":"KPY4AZWEI6TJOR7W","created_at":"2026-07-05T11:45:37Z"},{"alias_kind":"pith_short_8","alias_value":"KPY4AZWE","created_at":"2026-07-05T11:45:37Z"}],"graph_snapshots":[{"event_id":"sha256:3cbcca5a3acce329e6e67f33b6d397b06b268401f10788a6972c6603dc81d10c","target":"graph","created_at":"2026-07-05T11:45:37Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2507.15742/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Term frequency-inverse document frequency, or TF-IDF for short, is arguably the most celebrated mathematical expression in the history of information retrieval. Conceived as a simple heuristic quantifying the extent to which a given term's occurrences are concentrated in any one given document out of many, TF-IDF and its many variants are routinely used as term-weighting schemes in diverse text analysis applications. There is a growing body of scholarship dedicated to placing TF-IDF on a sound theoretical foundation. Building on that tradition, this paper justifies the use of TF-IDF to the sta","authors_text":"Aitazaz A. Farooque, Paul Sheridan, Zeyad Ahmed","cross_cats":["cs.IR","math.ST","stat.TH"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-21T15:54:23Z","title":"A Fisher's exact test justification of the TF-IDF term-weighting scheme"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.15742","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6ca0187751725318fbb17d7e65f7d2318cce3a83a2c51194f262a9b4ea8214e3","target":"record","created_at":"2026-07-05T11:45:37Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b5ba2b214f8d44744f93037a85d6e3763d0cf585b263738fefbdd64cf2072234","cross_cats_sorted":["cs.IR","math.ST","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-21T15:54:23Z","title_canon_sha256":"feebebe88bd229c6cde983afe8a35bb6f838ea714f1c0c4234062120c070889a"},"schema_version":"1.0","source":{"id":"2507.15742","kind":"arxiv","version":2}},"canonical_sha256":"53f1c066c447a69747f6ed05cd34b7a2d9c64f2b749068937139a3475594a9f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53f1c066c447a69747f6ed05cd34b7a2d9c64f2b749068937139a3475594a9f1","first_computed_at":"2026-07-05T11:45:37.888812Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:45:37.888812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H9/NZO3fn4ySeZLBijlZivKUvpFdJbhxEaJj5HVGDQ/3XuPIVX73zxsL/SnzPnBU4Ltp541Mwo9WZLKu6v5LDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:45:37.889287Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.15742","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6ca0187751725318fbb17d7e65f7d2318cce3a83a2c51194f262a9b4ea8214e3","sha256:3cbcca5a3acce329e6e67f33b6d397b06b268401f10788a6972c6603dc81d10c"],"state_sha256":"ae492fb8f6145d63598dce56e71628fd2da6a0ae9431afdfbaf8566a08f2981d"}