{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:5X5CL27FVKXUOB2LVKKNNDSA4J","short_pith_number":"pith:5X5CL27F","schema_version":"1.0","canonical_sha256":"edfa25ebe5aaaf47074baa94d68e40e26e3b4a1b82191396055bbaa0e6c9837d","source":{"kind":"arxiv","id":"1403.2004","version":1},"attestation_state":"computed","paper":{"title":"Natural Language Feature Selection via Cooccurrence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Michael Stewart","submitted_at":"2014-03-08T20:10:37Z","abstract_excerpt":"Specificity is important for extracting collocations, keyphrases, multi-word and index terms [Newman et al. 2012]. It is also useful for tagging, ontology construction [Ryu and Choi 2006], and automatic summarization of documents [Louis and Nenkova 2011, Chali and Hassan 2012]. Term frequency and inverse-document frequency (TF-IDF) are typically used to do this, but fail to take advantage of the semantic relationships between terms [Church and Gale 1995]. The result is that general idiomatic terms are mistaken for specific terms. We demonstrate use of relational data for estimation of term spe"},"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":"1403.2004","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-03-08T20:10:37Z","cross_cats_sorted":[],"title_canon_sha256":"0bd29d3138ec2c69f32ca3751f78f7860d048366b7edd3bc79a3e84677a44276","abstract_canon_sha256":"6793d230227a03fa609a3cd07ef779ccccf3ecfa55916c245e98d9d706942001"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:56:51.071665Z","signature_b64":"oXiddudgrC417mdL3PeojQ5DFfzFVq/MiFbNUPyBse1UluadX7tTETYjsZG9mhN69P/1Ah1U3MroQeZT0YisBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"edfa25ebe5aaaf47074baa94d68e40e26e3b4a1b82191396055bbaa0e6c9837d","last_reissued_at":"2026-05-18T02:56:51.071204Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:56:51.071204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Natural Language Feature Selection via Cooccurrence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Michael Stewart","submitted_at":"2014-03-08T20:10:37Z","abstract_excerpt":"Specificity is important for extracting collocations, keyphrases, multi-word and index terms [Newman et al. 2012]. It is also useful for tagging, ontology construction [Ryu and Choi 2006], and automatic summarization of documents [Louis and Nenkova 2011, Chali and Hassan 2012]. Term frequency and inverse-document frequency (TF-IDF) are typically used to do this, but fail to take advantage of the semantic relationships between terms [Church and Gale 1995]. The result is that general idiomatic terms are mistaken for specific terms. We demonstrate use of relational data for estimation of term spe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1403.2004","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1403.2004","created_at":"2026-05-18T02:56:51.071283+00:00"},{"alias_kind":"arxiv_version","alias_value":"1403.2004v1","created_at":"2026-05-18T02:56:51.071283+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1403.2004","created_at":"2026-05-18T02:56:51.071283+00:00"},{"alias_kind":"pith_short_12","alias_value":"5X5CL27FVKXU","created_at":"2026-05-18T12:28:16.859392+00:00"},{"alias_kind":"pith_short_16","alias_value":"5X5CL27FVKXUOB2L","created_at":"2026-05-18T12:28:16.859392+00:00"},{"alias_kind":"pith_short_8","alias_value":"5X5CL27F","created_at":"2026-05-18T12:28:16.859392+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/5X5CL27FVKXUOB2LVKKNNDSA4J","json":"https://pith.science/pith/5X5CL27FVKXUOB2LVKKNNDSA4J.json","graph_json":"https://pith.science/api/pith-number/5X5CL27FVKXUOB2LVKKNNDSA4J/graph.json","events_json":"https://pith.science/api/pith-number/5X5CL27FVKXUOB2LVKKNNDSA4J/events.json","paper":"https://pith.science/paper/5X5CL27F"},"agent_actions":{"view_html":"https://pith.science/pith/5X5CL27FVKXUOB2LVKKNNDSA4J","download_json":"https://pith.science/pith/5X5CL27FVKXUOB2LVKKNNDSA4J.json","view_paper":"https://pith.science/paper/5X5CL27F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1403.2004&json=true","fetch_graph":"https://pith.science/api/pith-number/5X5CL27FVKXUOB2LVKKNNDSA4J/graph.json","fetch_events":"https://pith.science/api/pith-number/5X5CL27FVKXUOB2LVKKNNDSA4J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5X5CL27FVKXUOB2LVKKNNDSA4J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5X5CL27FVKXUOB2LVKKNNDSA4J/action/storage_attestation","attest_author":"https://pith.science/pith/5X5CL27FVKXUOB2LVKKNNDSA4J/action/author_attestation","sign_citation":"https://pith.science/pith/5X5CL27FVKXUOB2LVKKNNDSA4J/action/citation_signature","submit_replication":"https://pith.science/pith/5X5CL27FVKXUOB2LVKKNNDSA4J/action/replication_record"}},"created_at":"2026-05-18T02:56:51.071283+00:00","updated_at":"2026-05-18T02:56:51.071283+00:00"}