{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LKPQUCMIF62RPYZ3AE7UYIPDOH","short_pith_number":"pith:LKPQUCMI","schema_version":"1.0","canonical_sha256":"5a9f0a09882fb517e33b013f4c21e371d23ef864c4f86913f8d69d3ac1ad3593","source":{"kind":"arxiv","id":"2410.01166","version":2},"attestation_state":"computed","paper":{"title":"Document Classification using File Names","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kevin Leach, Stefan Larson, Zhijian Li","submitted_at":"2024-10-02T01:42:19Z","abstract_excerpt":"Rapid document classification is critical in several time-sensitive applications like digital forensics and large-scale media classification. Traditional approaches that rely on heavy-duty deep learning models fall short due to high inference times over vast input datasets and computational resources associated with analyzing whole documents. In this paper, we present a method using lightweight supervised learning models, combined with a TF-IDF feature extraction-based tokenization method, to accurately and efficiently classify documents based solely on file names, that substantially reduces i"},"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":"2410.01166","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-02T01:42:19Z","cross_cats_sorted":[],"title_canon_sha256":"23d453b7f70b724dd9f62ba173f1a5bcd99da963650c216e4dba95cd4fd93b67","abstract_canon_sha256":"22493e7b2b28ee916f36b4f6453abec08d18ad9888efac16c5e6fa2f17cfee88"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:25:10.844435Z","signature_b64":"f8VtwMh9QGtvlWA3FPp5BQqwhCpIB2SdEEuGEhbtEIX/X6xC4v9hXYY6bbXmjri7/xLTumZk0Ylm10IgT03LCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a9f0a09882fb517e33b013f4c21e371d23ef864c4f86913f8d69d3ac1ad3593","last_reissued_at":"2026-07-05T10:25:10.843854Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:25:10.843854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Document Classification using File Names","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kevin Leach, Stefan Larson, Zhijian Li","submitted_at":"2024-10-02T01:42:19Z","abstract_excerpt":"Rapid document classification is critical in several time-sensitive applications like digital forensics and large-scale media classification. Traditional approaches that rely on heavy-duty deep learning models fall short due to high inference times over vast input datasets and computational resources associated with analyzing whole documents. In this paper, we present a method using lightweight supervised learning models, combined with a TF-IDF feature extraction-based tokenization method, to accurately and efficiently classify documents based solely on file names, that substantially reduces i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01166","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/2410.01166/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":"2410.01166","created_at":"2026-07-05T10:25:10.843924+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.01166v2","created_at":"2026-07-05T10:25:10.843924+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01166","created_at":"2026-07-05T10:25:10.843924+00:00"},{"alias_kind":"pith_short_12","alias_value":"LKPQUCMIF62R","created_at":"2026-07-05T10:25:10.843924+00:00"},{"alias_kind":"pith_short_16","alias_value":"LKPQUCMIF62RPYZ3","created_at":"2026-07-05T10:25:10.843924+00:00"},{"alias_kind":"pith_short_8","alias_value":"LKPQUCMI","created_at":"2026-07-05T10:25:10.843924+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/LKPQUCMIF62RPYZ3AE7UYIPDOH","json":"https://pith.science/pith/LKPQUCMIF62RPYZ3AE7UYIPDOH.json","graph_json":"https://pith.science/api/pith-number/LKPQUCMIF62RPYZ3AE7UYIPDOH/graph.json","events_json":"https://pith.science/api/pith-number/LKPQUCMIF62RPYZ3AE7UYIPDOH/events.json","paper":"https://pith.science/paper/LKPQUCMI"},"agent_actions":{"view_html":"https://pith.science/pith/LKPQUCMIF62RPYZ3AE7UYIPDOH","download_json":"https://pith.science/pith/LKPQUCMIF62RPYZ3AE7UYIPDOH.json","view_paper":"https://pith.science/paper/LKPQUCMI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.01166&json=true","fetch_graph":"https://pith.science/api/pith-number/LKPQUCMIF62RPYZ3AE7UYIPDOH/graph.json","fetch_events":"https://pith.science/api/pith-number/LKPQUCMIF62RPYZ3AE7UYIPDOH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LKPQUCMIF62RPYZ3AE7UYIPDOH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LKPQUCMIF62RPYZ3AE7UYIPDOH/action/storage_attestation","attest_author":"https://pith.science/pith/LKPQUCMIF62RPYZ3AE7UYIPDOH/action/author_attestation","sign_citation":"https://pith.science/pith/LKPQUCMIF62RPYZ3AE7UYIPDOH/action/citation_signature","submit_replication":"https://pith.science/pith/LKPQUCMIF62RPYZ3AE7UYIPDOH/action/replication_record"}},"created_at":"2026-07-05T10:25:10.843924+00:00","updated_at":"2026-07-05T10:25:10.843924+00:00"}