{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:5X5CL27FVKXUOB2LVKKNNDSA4J","short_pith_number":"pith:5X5CL27F","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"},"canonical_sha256":"edfa25ebe5aaaf47074baa94d68e40e26e3b4a1b82191396055bbaa0e6c9837d","source":{"kind":"arxiv","id":"1403.2004","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1403.2004","created_at":"2026-05-18T02:56:51Z"},{"alias_kind":"arxiv_version","alias_value":"1403.2004v1","created_at":"2026-05-18T02:56:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1403.2004","created_at":"2026-05-18T02:56:51Z"},{"alias_kind":"pith_short_12","alias_value":"5X5CL27FVKXU","created_at":"2026-05-18T12:28:16Z"},{"alias_kind":"pith_short_16","alias_value":"5X5CL27FVKXUOB2L","created_at":"2026-05-18T12:28:16Z"},{"alias_kind":"pith_short_8","alias_value":"5X5CL27F","created_at":"2026-05-18T12:28:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:5X5CL27FVKXUOB2LVKKNNDSA4J","target":"record","payload":{"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"},"canonical_sha256":"edfa25ebe5aaaf47074baa94d68e40e26e3b4a1b82191396055bbaa0e6c9837d","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"},"source_kind":"arxiv","source_id":"1403.2004","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:56:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"whBynhcgBuWADLlY2vj+6Kf8U60EcU/HzgB0+7JZ99nGQVaX3BtEBS8wT49+kaosIndnXx+4LU2hMWz8T/VnCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T18:13:53.290033Z"},"content_sha256":"d3f227e486d57a8fa936ab7022ad0744b5c0edcb60276460904f8cb6bcf838a5","schema_version":"1.0","event_id":"sha256:d3f227e486d57a8fa936ab7022ad0744b5c0edcb60276460904f8cb6bcf838a5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:5X5CL27FVKXUOB2LVKKNNDSA4J","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:56:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zpsJLleenQS5vTML1Fqe9tEj3KlrWgcTajnycNW58V93Pi6BAVszc338kdf7PFH5YUhzL+NSvlHD6rHT12DADw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T18:13:53.290781Z"},"content_sha256":"36f7ad5dadf1850a6e378674cbef7a695df0e17277f217f8973e0b94ae25e099","schema_version":"1.0","event_id":"sha256:36f7ad5dadf1850a6e378674cbef7a695df0e17277f217f8973e0b94ae25e099"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5X5CL27FVKXUOB2LVKKNNDSA4J/bundle.json","state_url":"https://pith.science/pith/5X5CL27FVKXUOB2LVKKNNDSA4J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5X5CL27FVKXUOB2LVKKNNDSA4J/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-09T18:13:53Z","links":{"resolver":"https://pith.science/pith/5X5CL27FVKXUOB2LVKKNNDSA4J","bundle":"https://pith.science/pith/5X5CL27FVKXUOB2LVKKNNDSA4J/bundle.json","state":"https://pith.science/pith/5X5CL27FVKXUOB2LVKKNNDSA4J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5X5CL27FVKXUOB2LVKKNNDSA4J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:5X5CL27FVKXUOB2LVKKNNDSA4J","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":"6793d230227a03fa609a3cd07ef779ccccf3ecfa55916c245e98d9d706942001","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-03-08T20:10:37Z","title_canon_sha256":"0bd29d3138ec2c69f32ca3751f78f7860d048366b7edd3bc79a3e84677a44276"},"schema_version":"1.0","source":{"id":"1403.2004","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1403.2004","created_at":"2026-05-18T02:56:51Z"},{"alias_kind":"arxiv_version","alias_value":"1403.2004v1","created_at":"2026-05-18T02:56:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1403.2004","created_at":"2026-05-18T02:56:51Z"},{"alias_kind":"pith_short_12","alias_value":"5X5CL27FVKXU","created_at":"2026-05-18T12:28:16Z"},{"alias_kind":"pith_short_16","alias_value":"5X5CL27FVKXUOB2L","created_at":"2026-05-18T12:28:16Z"},{"alias_kind":"pith_short_8","alias_value":"5X5CL27F","created_at":"2026-05-18T12:28:16Z"}],"graph_snapshots":[{"event_id":"sha256:36f7ad5dadf1850a6e378674cbef7a695df0e17277f217f8973e0b94ae25e099","target":"graph","created_at":"2026-05-18T02:56:51Z","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"},"paper":{"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","authors_text":"Michael Stewart","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-03-08T20:10:37Z","title":"Natural Language Feature Selection via Cooccurrence"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1403.2004","kind":"arxiv","version":1},"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:d3f227e486d57a8fa936ab7022ad0744b5c0edcb60276460904f8cb6bcf838a5","target":"record","created_at":"2026-05-18T02:56:51Z","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":"6793d230227a03fa609a3cd07ef779ccccf3ecfa55916c245e98d9d706942001","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-03-08T20:10:37Z","title_canon_sha256":"0bd29d3138ec2c69f32ca3751f78f7860d048366b7edd3bc79a3e84677a44276"},"schema_version":"1.0","source":{"id":"1403.2004","kind":"arxiv","version":1}},"canonical_sha256":"edfa25ebe5aaaf47074baa94d68e40e26e3b4a1b82191396055bbaa0e6c9837d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"edfa25ebe5aaaf47074baa94d68e40e26e3b4a1b82191396055bbaa0e6c9837d","first_computed_at":"2026-05-18T02:56:51.071204Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:56:51.071204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oXiddudgrC417mdL3PeojQ5DFfzFVq/MiFbNUPyBse1UluadX7tTETYjsZG9mhN69P/1Ah1U3MroQeZT0YisBw==","signature_status":"signed_v1","signed_at":"2026-05-18T02:56:51.071665Z","signed_message":"canonical_sha256_bytes"},"source_id":"1403.2004","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d3f227e486d57a8fa936ab7022ad0744b5c0edcb60276460904f8cb6bcf838a5","sha256:36f7ad5dadf1850a6e378674cbef7a695df0e17277f217f8973e0b94ae25e099"],"state_sha256":"06438cb5ac9dbb38b13f9cb34a550c8f46186952ee0ef885ca791c966956a924"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iWLYhalwPaNlrPe3yBuPsUoIZOPRzRlNlhP4lKQbEEKfKSHgV5cze0wAQSM2XA1t6gw1IIFV27OIg5YLlzQJDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T18:13:53.294815Z","bundle_sha256":"3b659beee592be49c83e92ab596092c38a14103c402b5d1f8b62ad1c8531c34f"}}