{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:YI33NFG3FNN5IQN6PXP3GUXOW4","short_pith_number":"pith:YI33NFG3","schema_version":"1.0","canonical_sha256":"c237b694db2b5bd441be7ddfb352eeb7179671d2a7c6b5db289ede6e9cf56b2a","source":{"kind":"arxiv","id":"2210.05422","version":1},"attestation_state":"computed","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"},"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":"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2210.05422","created_at":"2026-07-05T07:52:07.540775+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.05422v1","created_at":"2026-07-05T07:52:07.540775+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05422","created_at":"2026-07-05T07:52:07.540775+00:00"},{"alias_kind":"pith_short_12","alias_value":"YI33NFG3FNN5","created_at":"2026-07-05T07:52:07.540775+00:00"},{"alias_kind":"pith_short_16","alias_value":"YI33NFG3FNN5IQN6","created_at":"2026-07-05T07:52:07.540775+00:00"},{"alias_kind":"pith_short_8","alias_value":"YI33NFG3","created_at":"2026-07-05T07:52:07.540775+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YI33NFG3FNN5IQN6PXP3GUXOW4","json":"https://pith.science/pith/YI33NFG3FNN5IQN6PXP3GUXOW4.json","graph_json":"https://pith.science/api/pith-number/YI33NFG3FNN5IQN6PXP3GUXOW4/graph.json","events_json":"https://pith.science/api/pith-number/YI33NFG3FNN5IQN6PXP3GUXOW4/events.json","paper":"https://pith.science/paper/YI33NFG3"},"agent_actions":{"view_html":"https://pith.science/pith/YI33NFG3FNN5IQN6PXP3GUXOW4","download_json":"https://pith.science/pith/YI33NFG3FNN5IQN6PXP3GUXOW4.json","view_paper":"https://pith.science/paper/YI33NFG3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.05422&json=true","fetch_graph":"https://pith.science/api/pith-number/YI33NFG3FNN5IQN6PXP3GUXOW4/graph.json","fetch_events":"https://pith.science/api/pith-number/YI33NFG3FNN5IQN6PXP3GUXOW4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YI33NFG3FNN5IQN6PXP3GUXOW4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YI33NFG3FNN5IQN6PXP3GUXOW4/action/storage_attestation","attest_author":"https://pith.science/pith/YI33NFG3FNN5IQN6PXP3GUXOW4/action/author_attestation","sign_citation":"https://pith.science/pith/YI33NFG3FNN5IQN6PXP3GUXOW4/action/citation_signature","submit_replication":"https://pith.science/pith/YI33NFG3FNN5IQN6PXP3GUXOW4/action/replication_record"}},"created_at":"2026-07-05T07:52:07.540775+00:00","updated_at":"2026-07-05T07:52:07.540775+00:00"}