{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KPY4AZWEI6TJOR7W5UC42NFXUL","short_pith_number":"pith:KPY4AZWE","schema_version":"1.0","canonical_sha256":"53f1c066c447a69747f6ed05cd34b7a2d9c64f2b749068937139a3475594a9f1","source":{"kind":"arxiv","id":"2507.15742","version":2},"attestation_state":"computed","paper":{"title":"A Fisher's exact test justification of the TF-IDF term-weighting scheme","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","math.ST","stat.TH"],"primary_cat":"cs.CL","authors_text":"Aitazaz A. Farooque, Paul Sheridan, Zeyad Ahmed","submitted_at":"2025-07-21T15:54:23Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2507.15742","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-21T15:54:23Z","cross_cats_sorted":["cs.IR","math.ST","stat.TH"],"title_canon_sha256":"feebebe88bd229c6cde983afe8a35bb6f838ea714f1c0c4234062120c070889a","abstract_canon_sha256":"b5ba2b214f8d44744f93037a85d6e3763d0cf585b263738fefbdd64cf2072234"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:37.889287Z","signature_b64":"H9/NZO3fn4ySeZLBijlZivKUvpFdJbhxEaJj5HVGDQ/3XuPIVX73zxsL/SnzPnBU4Ltp541Mwo9WZLKu6v5LDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53f1c066c447a69747f6ed05cd34b7a2d9c64f2b749068937139a3475594a9f1","last_reissued_at":"2026-07-05T11:45:37.888812Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:37.888812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Fisher's exact test justification of the TF-IDF term-weighting scheme","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","math.ST","stat.TH"],"primary_cat":"cs.CL","authors_text":"Aitazaz A. Farooque, Paul Sheridan, Zeyad Ahmed","submitted_at":"2025-07-21T15:54:23Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.15742","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2507.15742/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2507.15742","created_at":"2026-07-05T11:45:37.888872+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.15742v2","created_at":"2026-07-05T11:45:37.888872+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.15742","created_at":"2026-07-05T11:45:37.888872+00:00"},{"alias_kind":"pith_short_12","alias_value":"KPY4AZWEI6TJ","created_at":"2026-07-05T11:45:37.888872+00:00"},{"alias_kind":"pith_short_16","alias_value":"KPY4AZWEI6TJOR7W","created_at":"2026-07-05T11:45:37.888872+00:00"},{"alias_kind":"pith_short_8","alias_value":"KPY4AZWE","created_at":"2026-07-05T11:45:37.888872+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KPY4AZWEI6TJOR7W5UC42NFXUL","json":"https://pith.science/pith/KPY4AZWEI6TJOR7W5UC42NFXUL.json","graph_json":"https://pith.science/api/pith-number/KPY4AZWEI6TJOR7W5UC42NFXUL/graph.json","events_json":"https://pith.science/api/pith-number/KPY4AZWEI6TJOR7W5UC42NFXUL/events.json","paper":"https://pith.science/paper/KPY4AZWE"},"agent_actions":{"view_html":"https://pith.science/pith/KPY4AZWEI6TJOR7W5UC42NFXUL","download_json":"https://pith.science/pith/KPY4AZWEI6TJOR7W5UC42NFXUL.json","view_paper":"https://pith.science/paper/KPY4AZWE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.15742&json=true","fetch_graph":"https://pith.science/api/pith-number/KPY4AZWEI6TJOR7W5UC42NFXUL/graph.json","fetch_events":"https://pith.science/api/pith-number/KPY4AZWEI6TJOR7W5UC42NFXUL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KPY4AZWEI6TJOR7W5UC42NFXUL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KPY4AZWEI6TJOR7W5UC42NFXUL/action/storage_attestation","attest_author":"https://pith.science/pith/KPY4AZWEI6TJOR7W5UC42NFXUL/action/author_attestation","sign_citation":"https://pith.science/pith/KPY4AZWEI6TJOR7W5UC42NFXUL/action/citation_signature","submit_replication":"https://pith.science/pith/KPY4AZWEI6TJOR7W5UC42NFXUL/action/replication_record"}},"created_at":"2026-07-05T11:45:37.888872+00:00","updated_at":"2026-07-05T11:45:37.888872+00:00"}