{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:1997:J22HF6X4MCZO7EY6ELEIUHGT7P","short_pith_number":"pith:J22HF6X4","schema_version":"1.0","canonical_sha256":"4eb472fafc60b2ef931e22c88a1cd3fbe7ce78500e3a13f0588fa52ecfbc90ce","source":{"kind":"arxiv","id":"cmp-lg/9708010","version":1},"attestation_state":"computed","paper":{"title":"Similarity-Based Methods For Word Sense Disambiguation","license":"","headline":"","cross_cats":["cs.CL"],"primary_cat":"cmp-lg","authors_text":"Fernando Pereira (AT&T Labs -- Research), Ido Dagan (Bar-Ilan University), Lillian Lee (Cornell University)","submitted_at":"1997-08-18T23:20:40Z","abstract_excerpt":"We compare four similarity-based estimation methods against back-off and maximum-likelihood estimation methods on a pseudo-word sense disambiguation task in which we controlled for both unigram and bigram frequency. The similarity-based methods perform up to 40% better on this particular task. We also conclude that events that occur only once in the training set have major impact on similarity-based estimates."},"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":"cmp-lg/9708010","kind":"arxiv","version":1},"metadata":{"license":"","primary_cat":"cmp-lg","submitted_at":"1997-08-18T23:20:40Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"f61508565df15854808159ec4b04ae1779c866713fd42842e6d07267232f1fa2","abstract_canon_sha256":"139e17fce02d67cb0f76588b3401bb6ee63dc3374441501c516b85f2d8f669da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T15:08:32.077294Z","signature_b64":"osXRob1eSRyZU+rHe4GxoxI4OdJC9TBNiuyVmB23PAFANzyGzCRZiIiGLM86zGxrWTrHu9YGuqbOf+extTpEBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4eb472fafc60b2ef931e22c88a1cd3fbe7ce78500e3a13f0588fa52ecfbc90ce","last_reissued_at":"2026-07-04T15:08:32.076917Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T15:08:32.076917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Similarity-Based Methods For Word Sense Disambiguation","license":"","headline":"","cross_cats":["cs.CL"],"primary_cat":"cmp-lg","authors_text":"Fernando Pereira (AT&T Labs -- Research), Ido Dagan (Bar-Ilan University), Lillian Lee (Cornell University)","submitted_at":"1997-08-18T23:20:40Z","abstract_excerpt":"We compare four similarity-based estimation methods against back-off and maximum-likelihood estimation methods on a pseudo-word sense disambiguation task in which we controlled for both unigram and bigram frequency. The similarity-based methods perform up to 40% better on this particular task. We also conclude that events that occur only once in the training set have major impact on similarity-based estimates."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"cmp-lg/9708010","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/cmp-lg/9708010/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":"cmp-lg/9708010","created_at":"2026-07-04T15:08:32.076974+00:00"},{"alias_kind":"arxiv_version","alias_value":"cmp-lg/9708010v1","created_at":"2026-07-04T15:08:32.076974+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.cmp-lg/9708010","created_at":"2026-07-04T15:08:32.076974+00:00"},{"alias_kind":"pith_short_12","alias_value":"J22HF6X4MCZO","created_at":"2026-07-04T15:08:32.076974+00:00"},{"alias_kind":"pith_short_16","alias_value":"J22HF6X4MCZO7EY6","created_at":"2026-07-04T15:08:32.076974+00:00"},{"alias_kind":"pith_short_8","alias_value":"J22HF6X4","created_at":"2026-07-04T15:08:32.076974+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.07096","citing_title":"Query-efficient model evaluation using cached responses","ref_index":92,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J22HF6X4MCZO7EY6ELEIUHGT7P","json":"https://pith.science/pith/J22HF6X4MCZO7EY6ELEIUHGT7P.json","graph_json":"https://pith.science/api/pith-number/J22HF6X4MCZO7EY6ELEIUHGT7P/graph.json","events_json":"https://pith.science/api/pith-number/J22HF6X4MCZO7EY6ELEIUHGT7P/events.json","paper":"https://pith.science/paper/J22HF6X4"},"agent_actions":{"view_html":"https://pith.science/pith/J22HF6X4MCZO7EY6ELEIUHGT7P","download_json":"https://pith.science/pith/J22HF6X4MCZO7EY6ELEIUHGT7P.json","view_paper":"https://pith.science/paper/J22HF6X4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=cmp-lg/9708010&json=true","fetch_graph":"https://pith.science/api/pith-number/J22HF6X4MCZO7EY6ELEIUHGT7P/graph.json","fetch_events":"https://pith.science/api/pith-number/J22HF6X4MCZO7EY6ELEIUHGT7P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J22HF6X4MCZO7EY6ELEIUHGT7P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J22HF6X4MCZO7EY6ELEIUHGT7P/action/storage_attestation","attest_author":"https://pith.science/pith/J22HF6X4MCZO7EY6ELEIUHGT7P/action/author_attestation","sign_citation":"https://pith.science/pith/J22HF6X4MCZO7EY6ELEIUHGT7P/action/citation_signature","submit_replication":"https://pith.science/pith/J22HF6X4MCZO7EY6ELEIUHGT7P/action/replication_record"}},"created_at":"2026-07-04T15:08:32.076974+00:00","updated_at":"2026-07-04T15:08:32.076974+00:00"}