{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:1997:J22HF6X4MCZO7EY6ELEIUHGT7P","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":"139e17fce02d67cb0f76588b3401bb6ee63dc3374441501c516b85f2d8f669da","cross_cats_sorted":["cs.CL"],"license":"","primary_cat":"cmp-lg","submitted_at":"1997-08-18T23:20:40Z","title_canon_sha256":"f61508565df15854808159ec4b04ae1779c866713fd42842e6d07267232f1fa2"},"schema_version":"1.0","source":{"id":"cmp-lg/9708010","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"cmp-lg/9708010","created_at":"2026-07-04T15:08:32Z"},{"alias_kind":"arxiv_version","alias_value":"cmp-lg/9708010v1","created_at":"2026-07-04T15:08:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.cmp-lg/9708010","created_at":"2026-07-04T15:08:32Z"},{"alias_kind":"pith_short_12","alias_value":"J22HF6X4MCZO","created_at":"2026-07-04T15:08:32Z"},{"alias_kind":"pith_short_16","alias_value":"J22HF6X4MCZO7EY6","created_at":"2026-07-04T15:08:32Z"},{"alias_kind":"pith_short_8","alias_value":"J22HF6X4","created_at":"2026-07-04T15:08:32Z"}],"graph_snapshots":[{"event_id":"sha256:ab504293a4a1b65f9c9783588f1c446f45614e2a62f9c7c268ee8fd01bc11756","target":"graph","created_at":"2026-07-04T15:08:32Z","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/cmp-lg/9708010/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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.","authors_text":"Fernando Pereira (AT&T Labs -- Research), Ido Dagan (Bar-Ilan University), Lillian Lee (Cornell University)","cross_cats":["cs.CL"],"headline":"","license":"","primary_cat":"cmp-lg","submitted_at":"1997-08-18T23:20:40Z","title":"Similarity-Based Methods For Word Sense Disambiguation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"cmp-lg/9708010","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":"sha256:783dc390343a6d11081641a9b88c277db87bcfaff847150a9d50fed74d62b91d","target":"record","created_at":"2026-07-04T15:08:32Z","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":"139e17fce02d67cb0f76588b3401bb6ee63dc3374441501c516b85f2d8f669da","cross_cats_sorted":["cs.CL"],"license":"","primary_cat":"cmp-lg","submitted_at":"1997-08-18T23:20:40Z","title_canon_sha256":"f61508565df15854808159ec4b04ae1779c866713fd42842e6d07267232f1fa2"},"schema_version":"1.0","source":{"id":"cmp-lg/9708010","kind":"arxiv","version":1}},"canonical_sha256":"4eb472fafc60b2ef931e22c88a1cd3fbe7ce78500e3a13f0588fa52ecfbc90ce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4eb472fafc60b2ef931e22c88a1cd3fbe7ce78500e3a13f0588fa52ecfbc90ce","first_computed_at":"2026-07-04T15:08:32.076917Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T15:08:32.076917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"osXRob1eSRyZU+rHe4GxoxI4OdJC9TBNiuyVmB23PAFANzyGzCRZiIiGLM86zGxrWTrHu9YGuqbOf+extTpEBA==","signature_status":"signed_v1","signed_at":"2026-07-04T15:08:32.077294Z","signed_message":"canonical_sha256_bytes"},"source_id":"cmp-lg/9708010","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:783dc390343a6d11081641a9b88c277db87bcfaff847150a9d50fed74d62b91d","sha256:ab504293a4a1b65f9c9783588f1c446f45614e2a62f9c7c268ee8fd01bc11756"],"state_sha256":"8e5d51cb7228340462e09adde3e5747e15823d7a0cba77cee98e2196571b02e2"}