{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LKPQUCMIF62RPYZ3AE7UYIPDOH","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":"22493e7b2b28ee916f36b4f6453abec08d18ad9888efac16c5e6fa2f17cfee88","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-02T01:42:19Z","title_canon_sha256":"23d453b7f70b724dd9f62ba173f1a5bcd99da963650c216e4dba95cd4fd93b67"},"schema_version":"1.0","source":{"id":"2410.01166","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.01166","created_at":"2026-07-05T10:25:10Z"},{"alias_kind":"arxiv_version","alias_value":"2410.01166v2","created_at":"2026-07-05T10:25:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01166","created_at":"2026-07-05T10:25:10Z"},{"alias_kind":"pith_short_12","alias_value":"LKPQUCMIF62R","created_at":"2026-07-05T10:25:10Z"},{"alias_kind":"pith_short_16","alias_value":"LKPQUCMIF62RPYZ3","created_at":"2026-07-05T10:25:10Z"},{"alias_kind":"pith_short_8","alias_value":"LKPQUCMI","created_at":"2026-07-05T10:25:10Z"}],"graph_snapshots":[{"event_id":"sha256:10720b4495bdff3bcf67b2913e68d4d7d34ad80fc416e66f937dc3e63b81c81d","target":"graph","created_at":"2026-07-05T10:25:10Z","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/2410.01166/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Kevin Leach, Stefan Larson, Zhijian Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-02T01:42:19Z","title":"Document Classification using File Names"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01166","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":"sha256:64cfab8f40ef3265eeb89713a5d9e6bd4391cffea294d8df09aa0f3964531a23","target":"record","created_at":"2026-07-05T10:25:10Z","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":"22493e7b2b28ee916f36b4f6453abec08d18ad9888efac16c5e6fa2f17cfee88","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-02T01:42:19Z","title_canon_sha256":"23d453b7f70b724dd9f62ba173f1a5bcd99da963650c216e4dba95cd4fd93b67"},"schema_version":"1.0","source":{"id":"2410.01166","kind":"arxiv","version":2}},"canonical_sha256":"5a9f0a09882fb517e33b013f4c21e371d23ef864c4f86913f8d69d3ac1ad3593","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a9f0a09882fb517e33b013f4c21e371d23ef864c4f86913f8d69d3ac1ad3593","first_computed_at":"2026-07-05T10:25:10.843854Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:25:10.843854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f8VtwMh9QGtvlWA3FPp5BQqwhCpIB2SdEEuGEhbtEIX/X6xC4v9hXYY6bbXmjri7/xLTumZk0Ylm10IgT03LCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:25:10.844435Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.01166","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:64cfab8f40ef3265eeb89713a5d9e6bd4391cffea294d8df09aa0f3964531a23","sha256:10720b4495bdff3bcf67b2913e68d4d7d34ad80fc416e66f937dc3e63b81c81d"],"state_sha256":"eacae6ac34c07f4bd03006aa429239359fdeb59a8d1431893674b936fc47fd7a"}