{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:JZCCMLE6HJKTFTGDSRJJTZ2L3A","short_pith_number":"pith:JZCCMLE6","schema_version":"1.0","canonical_sha256":"4e44262c9e3a5532ccc3945299e74bd80f4f01a759afeb46cc92ab09b15d1281","source":{"kind":"arxiv","id":"2210.02898","version":2},"attestation_state":"computed","paper":{"title":"Learning Disentangled Representations for Natural Language Definitions","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"2) ((1) Department of Computer Science, (2) Idiap Research Institute, Andre Freitas (1, Danilo S. Carvalho (1), Giangiacomo Mercatali (1), Switzerland), United Kingdom, University of Manchester, Yingji Zhang (1)","submitted_at":"2022-09-22T14:31:55Z","abstract_excerpt":"Disentangling the encodings of neural models is a fundamental aspect for improving interpretability, semantic control and downstream task performance in Natural Language Processing. Currently, most disentanglement methods are unsupervised or rely on synthetic datasets with known generative factors. We argue that recurrent syntactic and semantic regularities in textual data can be used to provide the models with both structural biases and generative factors. We leverage the semantic structures present in a representative and semantically dense category of sentence types, definitional sentences,"},"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":"2210.02898","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-09-22T14:31:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6d9ec661311b37da5a4ccc4316d0cbc9ee80c9a7d761baea7ba0d66583f5e48c","abstract_canon_sha256":"a283d9d04fd2560e3c05ea7456718aa12b628516dd669296ebc9b8071595d017"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:42:28.094712Z","signature_b64":"cHlWovWaTGBJZanvuEUcftf5nA00d4YoG97IBdtZUcyqI249hPh2d5oisL1DZZKq1YRv0j+Y3f43bWO3Sq70Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e44262c9e3a5532ccc3945299e74bd80f4f01a759afeb46cc92ab09b15d1281","last_reissued_at":"2026-07-05T05:42:28.094260Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:42:28.094260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Disentangled Representations for Natural Language Definitions","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"2) ((1) Department of Computer Science, (2) Idiap Research Institute, Andre Freitas (1, Danilo S. Carvalho (1), Giangiacomo Mercatali (1), Switzerland), United Kingdom, University of Manchester, Yingji Zhang (1)","submitted_at":"2022-09-22T14:31:55Z","abstract_excerpt":"Disentangling the encodings of neural models is a fundamental aspect for improving interpretability, semantic control and downstream task performance in Natural Language Processing. Currently, most disentanglement methods are unsupervised or rely on synthetic datasets with known generative factors. We argue that recurrent syntactic and semantic regularities in textual data can be used to provide the models with both structural biases and generative factors. We leverage the semantic structures present in a representative and semantically dense category of sentence types, definitional sentences,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.02898","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2210.02898/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":"2210.02898","created_at":"2026-07-05T05:42:28.094328+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.02898v2","created_at":"2026-07-05T05:42:28.094328+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.02898","created_at":"2026-07-05T05:42:28.094328+00:00"},{"alias_kind":"pith_short_12","alias_value":"JZCCMLE6HJKT","created_at":"2026-07-05T05:42:28.094328+00:00"},{"alias_kind":"pith_short_16","alias_value":"JZCCMLE6HJKTFTGD","created_at":"2026-07-05T05:42:28.094328+00:00"},{"alias_kind":"pith_short_8","alias_value":"JZCCMLE6","created_at":"2026-07-05T05:42:28.094328+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/JZCCMLE6HJKTFTGDSRJJTZ2L3A","json":"https://pith.science/pith/JZCCMLE6HJKTFTGDSRJJTZ2L3A.json","graph_json":"https://pith.science/api/pith-number/JZCCMLE6HJKTFTGDSRJJTZ2L3A/graph.json","events_json":"https://pith.science/api/pith-number/JZCCMLE6HJKTFTGDSRJJTZ2L3A/events.json","paper":"https://pith.science/paper/JZCCMLE6"},"agent_actions":{"view_html":"https://pith.science/pith/JZCCMLE6HJKTFTGDSRJJTZ2L3A","download_json":"https://pith.science/pith/JZCCMLE6HJKTFTGDSRJJTZ2L3A.json","view_paper":"https://pith.science/paper/JZCCMLE6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.02898&json=true","fetch_graph":"https://pith.science/api/pith-number/JZCCMLE6HJKTFTGDSRJJTZ2L3A/graph.json","fetch_events":"https://pith.science/api/pith-number/JZCCMLE6HJKTFTGDSRJJTZ2L3A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JZCCMLE6HJKTFTGDSRJJTZ2L3A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JZCCMLE6HJKTFTGDSRJJTZ2L3A/action/storage_attestation","attest_author":"https://pith.science/pith/JZCCMLE6HJKTFTGDSRJJTZ2L3A/action/author_attestation","sign_citation":"https://pith.science/pith/JZCCMLE6HJKTFTGDSRJJTZ2L3A/action/citation_signature","submit_replication":"https://pith.science/pith/JZCCMLE6HJKTFTGDSRJJTZ2L3A/action/replication_record"}},"created_at":"2026-07-05T05:42:28.094328+00:00","updated_at":"2026-07-05T05:42:28.094328+00:00"}