{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:YI33NFG3FNN5IQN6PXP3GUXOW4","short_pith_number":"pith:YI33NFG3","canonical_record":{"source":{"id":"2210.05422","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-11T13:04:06Z","cross_cats_sorted":[],"title_canon_sha256":"4c1fb436c858cd1edb16db49386fe1df09f034927ca7781dd18c9d1aa8529075","abstract_canon_sha256":"77c9cec4db9e9631e6ae08c0cfbe3e29cd75efb94e0f3afeee408d229c8c1cf0"},"schema_version":"1.0"},"canonical_sha256":"c237b694db2b5bd441be7ddfb352eeb7179671d2a7c6b5db289ede6e9cf56b2a","source":{"kind":"arxiv","id":"2210.05422","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.05422","created_at":"2026-07-05T07:52:07Z"},{"alias_kind":"arxiv_version","alias_value":"2210.05422v1","created_at":"2026-07-05T07:52:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05422","created_at":"2026-07-05T07:52:07Z"},{"alias_kind":"pith_short_12","alias_value":"YI33NFG3FNN5","created_at":"2026-07-05T07:52:07Z"},{"alias_kind":"pith_short_16","alias_value":"YI33NFG3FNN5IQN6","created_at":"2026-07-05T07:52:07Z"},{"alias_kind":"pith_short_8","alias_value":"YI33NFG3","created_at":"2026-07-05T07:52:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:YI33NFG3FNN5IQN6PXP3GUXOW4","target":"record","payload":{"canonical_record":{"source":{"id":"2210.05422","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-11T13:04:06Z","cross_cats_sorted":[],"title_canon_sha256":"4c1fb436c858cd1edb16db49386fe1df09f034927ca7781dd18c9d1aa8529075","abstract_canon_sha256":"77c9cec4db9e9631e6ae08c0cfbe3e29cd75efb94e0f3afeee408d229c8c1cf0"},"schema_version":"1.0"},"canonical_sha256":"c237b694db2b5bd441be7ddfb352eeb7179671d2a7c6b5db289ede6e9cf56b2a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:52:07.541065Z","signature_b64":"aotgCwj0rLUtDk/zpIVgn95K/2caqiucQWAQKPNoxRhCDInFvBmG7zqzmSzDcNnHqzcB/n1Ttq9+FXPsbAjrCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c237b694db2b5bd441be7ddfb352eeb7179671d2a7c6b5db289ede6e9cf56b2a","last_reissued_at":"2026-07-05T07:52:07.540713Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:52:07.540713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.05422","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":"2026-07-05T07:52:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6qAGbB4BNV+zYeYP4LBWjRVzwQ07gARCw4/aM0VYfc9Hze6aypYFw06I63vbeFKBRlIsyVufmsXHsns5FXLfCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T20:18:02.023497Z"},"content_sha256":"6bf437eff8a6c1e29ddb936283c9a4c46ae91cb83d6651c4055e3713552859a2","schema_version":"1.0","event_id":"sha256:6bf437eff8a6c1e29ddb936283c9a4c46ae91cb83d6651c4055e3713552859a2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:YI33NFG3FNN5IQN6PXP3GUXOW4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Word Sense Induction with Hierarchical Clustering and Mutual Information Maximization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Davide Buscaldi, Hadi Abdine, Michalis Vazirgiannis, Moussa Kamal Eddine","submitted_at":"2022-10-11T13:04:06Z","abstract_excerpt":"Word sense induction (WSI) is a difficult problem in natural language processing that involves the unsupervised automatic detection of a word's senses (i.e. meanings). Recent work achieves significant results on the WSI task by pre-training a language model that can exclusively disambiguate word senses, whereas others employ previously pre-trained language models in conjunction with additional strategies to induce senses. In this paper, we propose a novel unsupervised method based on hierarchical clustering and invariant information clustering (IIC). The IIC is used to train a small model to o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05422","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/2210.05422/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:52:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VzCCiAPCqhEq7oiDbwC0+DLlpJnixcZ7ZNOkvKYaTGAc+5Bms/g6qYcPFavoZ4aSO1d6xtE6voj/eNWQChGWBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T20:18:02.023994Z"},"content_sha256":"721a9db708c59487cfd59ef67f57a516e8677bcb3f273aaa7f15a9da4c6a4cc7","schema_version":"1.0","event_id":"sha256:721a9db708c59487cfd59ef67f57a516e8677bcb3f273aaa7f15a9da4c6a4cc7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YI33NFG3FNN5IQN6PXP3GUXOW4/bundle.json","state_url":"https://pith.science/pith/YI33NFG3FNN5IQN6PXP3GUXOW4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YI33NFG3FNN5IQN6PXP3GUXOW4/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":"2026-08-17T20:18:02Z","links":{"resolver":"https://pith.science/pith/YI33NFG3FNN5IQN6PXP3GUXOW4","bundle":"https://pith.science/pith/YI33NFG3FNN5IQN6PXP3GUXOW4/bundle.json","state":"https://pith.science/pith/YI33NFG3FNN5IQN6PXP3GUXOW4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YI33NFG3FNN5IQN6PXP3GUXOW4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:YI33NFG3FNN5IQN6PXP3GUXOW4","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":"77c9cec4db9e9631e6ae08c0cfbe3e29cd75efb94e0f3afeee408d229c8c1cf0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-11T13:04:06Z","title_canon_sha256":"4c1fb436c858cd1edb16db49386fe1df09f034927ca7781dd18c9d1aa8529075"},"schema_version":"1.0","source":{"id":"2210.05422","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.05422","created_at":"2026-07-05T07:52:07Z"},{"alias_kind":"arxiv_version","alias_value":"2210.05422v1","created_at":"2026-07-05T07:52:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05422","created_at":"2026-07-05T07:52:07Z"},{"alias_kind":"pith_short_12","alias_value":"YI33NFG3FNN5","created_at":"2026-07-05T07:52:07Z"},{"alias_kind":"pith_short_16","alias_value":"YI33NFG3FNN5IQN6","created_at":"2026-07-05T07:52:07Z"},{"alias_kind":"pith_short_8","alias_value":"YI33NFG3","created_at":"2026-07-05T07:52:07Z"}],"graph_snapshots":[{"event_id":"sha256:721a9db708c59487cfd59ef67f57a516e8677bcb3f273aaa7f15a9da4c6a4cc7","target":"graph","created_at":"2026-07-05T07:52:07Z","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/2210.05422/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Word sense induction (WSI) is a difficult problem in natural language processing that involves the unsupervised automatic detection of a word's senses (i.e. meanings). Recent work achieves significant results on the WSI task by pre-training a language model that can exclusively disambiguate word senses, whereas others employ previously pre-trained language models in conjunction with additional strategies to induce senses. In this paper, we propose a novel unsupervised method based on hierarchical clustering and invariant information clustering (IIC). The IIC is used to train a small model to o","authors_text":"Davide Buscaldi, Hadi Abdine, Michalis Vazirgiannis, Moussa Kamal Eddine","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-11T13:04:06Z","title":"Word Sense Induction with Hierarchical Clustering and Mutual Information Maximization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05422","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":"sha256:6bf437eff8a6c1e29ddb936283c9a4c46ae91cb83d6651c4055e3713552859a2","target":"record","created_at":"2026-07-05T07:52:07Z","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":"77c9cec4db9e9631e6ae08c0cfbe3e29cd75efb94e0f3afeee408d229c8c1cf0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-11T13:04:06Z","title_canon_sha256":"4c1fb436c858cd1edb16db49386fe1df09f034927ca7781dd18c9d1aa8529075"},"schema_version":"1.0","source":{"id":"2210.05422","kind":"arxiv","version":1}},"canonical_sha256":"c237b694db2b5bd441be7ddfb352eeb7179671d2a7c6b5db289ede6e9cf56b2a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c237b694db2b5bd441be7ddfb352eeb7179671d2a7c6b5db289ede6e9cf56b2a","first_computed_at":"2026-07-05T07:52:07.540713Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:52:07.540713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aotgCwj0rLUtDk/zpIVgn95K/2caqiucQWAQKPNoxRhCDInFvBmG7zqzmSzDcNnHqzcB/n1Ttq9+FXPsbAjrCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:52:07.541065Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.05422","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6bf437eff8a6c1e29ddb936283c9a4c46ae91cb83d6651c4055e3713552859a2","sha256:721a9db708c59487cfd59ef67f57a516e8677bcb3f273aaa7f15a9da4c6a4cc7"],"state_sha256":"a159c51f8bacbef9bc58e1c584409b9cb1bdc0bc6139010f5b8ed06540183c5a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e1MaGRhgWaxkYkbU+Fru4urw0gg/yp9EABqv3FPPAQ/KKC/teYnqLokdBhMb7b2Y1elDfAlOjgbJ51a42w8pAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T20:18:02.028060Z","bundle_sha256":"0ae4f2f770744a3924c0581068d370c1297d30f12412e97d9a734488ed331ff4"}}