{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:D3KYU2THJL5SENLDOFPX37JZH3","short_pith_number":"pith:D3KYU2TH","canonical_record":{"source":{"id":"1905.12598","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-29T17:20:11Z","cross_cats_sorted":[],"title_canon_sha256":"29071dc8f3186f3965cb07c19d983f72776d56f41022c1f9ca36a8e19af19435","abstract_canon_sha256":"f3f8de9d89dee8bcead065330162890ded284848f0ac67f613e111ca14248b27"},"schema_version":"1.0"},"canonical_sha256":"1ed58a6a674afb223563715f7dfd393ee40f7cad8b1eeb595ffd2ccf03489009","source":{"kind":"arxiv","id":"1905.12598","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.12598","created_at":"2026-05-17T23:44:37Z"},{"alias_kind":"arxiv_version","alias_value":"1905.12598v2","created_at":"2026-05-17T23:44:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.12598","created_at":"2026-05-17T23:44:37Z"},{"alias_kind":"pith_short_12","alias_value":"D3KYU2THJL5S","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"D3KYU2THJL5SENLD","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"D3KYU2TH","created_at":"2026-05-18T12:33:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:D3KYU2THJL5SENLDOFPX37JZH3","target":"record","payload":{"canonical_record":{"source":{"id":"1905.12598","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-29T17:20:11Z","cross_cats_sorted":[],"title_canon_sha256":"29071dc8f3186f3965cb07c19d983f72776d56f41022c1f9ca36a8e19af19435","abstract_canon_sha256":"f3f8de9d89dee8bcead065330162890ded284848f0ac67f613e111ca14248b27"},"schema_version":"1.0"},"canonical_sha256":"1ed58a6a674afb223563715f7dfd393ee40f7cad8b1eeb595ffd2ccf03489009","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:37.343339Z","signature_b64":"DqmG312ed3fY5fpAVo6fW0WD4qvkBY35gITLpoiGGmwGPDl77JEHBIOpYwIK/BuYydFzcQhQCeH8O/kf5uxlDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ed58a6a674afb223563715f7dfd393ee40f7cad8b1eeb595ffd2ccf03489009","last_reissued_at":"2026-05-17T23:44:37.342810Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:37.342810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.12598","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:44:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EvFo7Z3LVEjW035J970E9LyJSNF2K0bmNSN0/bY4oLkzWK/SVirPIN6eh32eceOLupvcqZEDRHV6EhwnqJ5mCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T20:38:35.971801Z"},"content_sha256":"9060308f6cef79b69809402ce5074f05170b0a520782e8fa9ee5413c29eec9f1","schema_version":"1.0","event_id":"sha256:9060308f6cef79b69809402ce5074f05170b0a520782e8fa9ee5413c29eec9f1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:D3KYU2THJL5SENLDOFPX37JZH3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards better substitution-based word sense induction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Asaf Amrami, Yoav Goldberg","submitted_at":"2019-05-29T17:20:11Z","abstract_excerpt":"Word sense induction (WSI) is the task of unsupervised clustering of word usages within a sentence to distinguish senses. Recent work obtain strong results by clustering lexical substitutes derived from pre-trained RNN language models (ELMo). Adapting the method to BERT improves the scores even further. We extend the previous method to support a dynamic rather than a fixed number of clusters as supported by other prominent methods, and propose a method for interpreting the resulting clusters by associating them with their most informative substitutes. We then perform extensive error analysis r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.12598","kind":"arxiv","version":2},"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":"2026-05-17T23:44:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"57Go8NTJHviXmQpgANaAh38sEsCrfAQLdakrUthtRnK3JFJ49LwQa0gHpZNakXnMfqquxB9Pi2ObISLSVqwNDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T20:38:35.972343Z"},"content_sha256":"df3d1088b288583cbcf03b3eee5b76e5bba9975b95b322a0b908e8de9dbdbf07","schema_version":"1.0","event_id":"sha256:df3d1088b288583cbcf03b3eee5b76e5bba9975b95b322a0b908e8de9dbdbf07"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D3KYU2THJL5SENLDOFPX37JZH3/bundle.json","state_url":"https://pith.science/pith/D3KYU2THJL5SENLDOFPX37JZH3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D3KYU2THJL5SENLDOFPX37JZH3/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":"2026-06-01T20:38:35Z","links":{"resolver":"https://pith.science/pith/D3KYU2THJL5SENLDOFPX37JZH3","bundle":"https://pith.science/pith/D3KYU2THJL5SENLDOFPX37JZH3/bundle.json","state":"https://pith.science/pith/D3KYU2THJL5SENLDOFPX37JZH3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D3KYU2THJL5SENLDOFPX37JZH3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:D3KYU2THJL5SENLDOFPX37JZH3","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":"f3f8de9d89dee8bcead065330162890ded284848f0ac67f613e111ca14248b27","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-29T17:20:11Z","title_canon_sha256":"29071dc8f3186f3965cb07c19d983f72776d56f41022c1f9ca36a8e19af19435"},"schema_version":"1.0","source":{"id":"1905.12598","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.12598","created_at":"2026-05-17T23:44:37Z"},{"alias_kind":"arxiv_version","alias_value":"1905.12598v2","created_at":"2026-05-17T23:44:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.12598","created_at":"2026-05-17T23:44:37Z"},{"alias_kind":"pith_short_12","alias_value":"D3KYU2THJL5S","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"D3KYU2THJL5SENLD","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"D3KYU2TH","created_at":"2026-05-18T12:33:15Z"}],"graph_snapshots":[{"event_id":"sha256:df3d1088b288583cbcf03b3eee5b76e5bba9975b95b322a0b908e8de9dbdbf07","target":"graph","created_at":"2026-05-17T23:44:37Z","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":"Word sense induction (WSI) is the task of unsupervised clustering of word usages within a sentence to distinguish senses. Recent work obtain strong results by clustering lexical substitutes derived from pre-trained RNN language models (ELMo). Adapting the method to BERT improves the scores even further. We extend the previous method to support a dynamic rather than a fixed number of clusters as supported by other prominent methods, and propose a method for interpreting the resulting clusters by associating them with their most informative substitutes. We then perform extensive error analysis r","authors_text":"Asaf Amrami, Yoav Goldberg","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-29T17:20:11Z","title":"Towards better substitution-based word sense induction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.12598","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":"sha256:9060308f6cef79b69809402ce5074f05170b0a520782e8fa9ee5413c29eec9f1","target":"record","created_at":"2026-05-17T23:44:37Z","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":"f3f8de9d89dee8bcead065330162890ded284848f0ac67f613e111ca14248b27","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-29T17:20:11Z","title_canon_sha256":"29071dc8f3186f3965cb07c19d983f72776d56f41022c1f9ca36a8e19af19435"},"schema_version":"1.0","source":{"id":"1905.12598","kind":"arxiv","version":2}},"canonical_sha256":"1ed58a6a674afb223563715f7dfd393ee40f7cad8b1eeb595ffd2ccf03489009","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ed58a6a674afb223563715f7dfd393ee40f7cad8b1eeb595ffd2ccf03489009","first_computed_at":"2026-05-17T23:44:37.342810Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:37.342810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DqmG312ed3fY5fpAVo6fW0WD4qvkBY35gITLpoiGGmwGPDl77JEHBIOpYwIK/BuYydFzcQhQCeH8O/kf5uxlDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:37.343339Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.12598","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9060308f6cef79b69809402ce5074f05170b0a520782e8fa9ee5413c29eec9f1","sha256:df3d1088b288583cbcf03b3eee5b76e5bba9975b95b322a0b908e8de9dbdbf07"],"state_sha256":"a93209d26934b677e6b7a14286dc922ff1fd4892d0ca039a2fba5f6e85bc0e14"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jVBTJpjWPWY405rMaOyQEcBOjGjMw82do6TyHjqKq9FX9HNVZqCOO9QcGYTl6u0uAGW0a9cl93fd7CNVmX6OBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T20:38:35.974917Z","bundle_sha256":"3409d6dc9b754c49c61173cdfff7a817b9d66420d034eab052ef25105b56cd30"}}