{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PKWA2FE2X5MFE6NZPUSK6MMATQ","short_pith_number":"pith:PKWA2FE2","schema_version":"1.0","canonical_sha256":"7aac0d149abf585279b97d24af31809c1fc19087a50c2b8c81ccf62e88b4857e","source":{"kind":"arxiv","id":"2305.09785","version":1},"attestation_state":"computed","paper":{"title":"Distilling Semantic Concept Embeddings from Contrastively Fine-Tuned Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hanane Kteich, Na Li, Steven Schockaert, Zied Bouraoui","submitted_at":"2023-05-16T20:17:02Z","abstract_excerpt":"Learning vectors that capture the meaning of concepts remains a fundamental challenge. Somewhat surprisingly, perhaps, pre-trained language models have thus far only enabled modest improvements to the quality of such concept embeddings. Current strategies for using language models typically represent a concept by averaging the contextualised representations of its mentions in some corpus. This is potentially sub-optimal for at least two reasons. First, contextualised word vectors have an unusual geometry, which hampers downstream tasks. Second, concept embeddings should capture the semantic pr"},"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":"2305.09785","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-16T20:17:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"48c3a1fbe5fe61247babcf3f857d7be7b8fa7f239850c30455cc7a1e628e16c1","abstract_canon_sha256":"aa4c11f8a6d6f19009f67c29a79c2baba49c4d6b17075c32a8db96933f9500e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:10:53.943577Z","signature_b64":"wAPVrEGflANGU8tI0AbHXDYD3cxPwOgEKb52M8Jl0UlZNTQgwIJvPXO7IjGOJ67CjfL0c7XnZmHo/2IdGPPFCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7aac0d149abf585279b97d24af31809c1fc19087a50c2b8c81ccf62e88b4857e","last_reissued_at":"2026-07-05T06:10:53.943211Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:10:53.943211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distilling Semantic Concept Embeddings from Contrastively Fine-Tuned Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hanane Kteich, Na Li, Steven Schockaert, Zied Bouraoui","submitted_at":"2023-05-16T20:17:02Z","abstract_excerpt":"Learning vectors that capture the meaning of concepts remains a fundamental challenge. Somewhat surprisingly, perhaps, pre-trained language models have thus far only enabled modest improvements to the quality of such concept embeddings. Current strategies for using language models typically represent a concept by averaging the contextualised representations of its mentions in some corpus. This is potentially sub-optimal for at least two reasons. First, contextualised word vectors have an unusual geometry, which hampers downstream tasks. Second, concept embeddings should capture the semantic pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.09785","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/2305.09785/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":"2305.09785","created_at":"2026-07-05T06:10:53.943274+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.09785v1","created_at":"2026-07-05T06:10:53.943274+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.09785","created_at":"2026-07-05T06:10:53.943274+00:00"},{"alias_kind":"pith_short_12","alias_value":"PKWA2FE2X5MF","created_at":"2026-07-05T06:10:53.943274+00:00"},{"alias_kind":"pith_short_16","alias_value":"PKWA2FE2X5MFE6NZ","created_at":"2026-07-05T06:10:53.943274+00:00"},{"alias_kind":"pith_short_8","alias_value":"PKWA2FE2","created_at":"2026-07-05T06:10:53.943274+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.13732","citing_title":"Modeling Multi-modal Cross-interaction for Multi-label Few-shot Image Classification Based on Local Feature Selection","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PKWA2FE2X5MFE6NZPUSK6MMATQ","json":"https://pith.science/pith/PKWA2FE2X5MFE6NZPUSK6MMATQ.json","graph_json":"https://pith.science/api/pith-number/PKWA2FE2X5MFE6NZPUSK6MMATQ/graph.json","events_json":"https://pith.science/api/pith-number/PKWA2FE2X5MFE6NZPUSK6MMATQ/events.json","paper":"https://pith.science/paper/PKWA2FE2"},"agent_actions":{"view_html":"https://pith.science/pith/PKWA2FE2X5MFE6NZPUSK6MMATQ","download_json":"https://pith.science/pith/PKWA2FE2X5MFE6NZPUSK6MMATQ.json","view_paper":"https://pith.science/paper/PKWA2FE2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.09785&json=true","fetch_graph":"https://pith.science/api/pith-number/PKWA2FE2X5MFE6NZPUSK6MMATQ/graph.json","fetch_events":"https://pith.science/api/pith-number/PKWA2FE2X5MFE6NZPUSK6MMATQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PKWA2FE2X5MFE6NZPUSK6MMATQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PKWA2FE2X5MFE6NZPUSK6MMATQ/action/storage_attestation","attest_author":"https://pith.science/pith/PKWA2FE2X5MFE6NZPUSK6MMATQ/action/author_attestation","sign_citation":"https://pith.science/pith/PKWA2FE2X5MFE6NZPUSK6MMATQ/action/citation_signature","submit_replication":"https://pith.science/pith/PKWA2FE2X5MFE6NZPUSK6MMATQ/action/replication_record"}},"created_at":"2026-07-05T06:10:53.943274+00:00","updated_at":"2026-07-05T06:10:53.943274+00:00"}