{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:D7IH6GMUPDWEKK3MJDWB7RAF55","short_pith_number":"pith:D7IH6GMU","schema_version":"1.0","canonical_sha256":"1fd07f199478ec452b6c48ec1fc405ef5a6b982ebbc5fa55ad5e7c019f0f66f3","source":{"kind":"arxiv","id":"2502.11100","version":3},"attestation_state":"computed","paper":{"title":"Towards Achieving Concept Completeness for Textual Concept Bottleneck Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jean-Noel Vittaut, Marie-Jeanne Lesot, Milan Bhan, Nicolas Chesneau, Pierre Moreau, Yann Choho","submitted_at":"2025-02-16T12:28:43Z","abstract_excerpt":"Textual Concept Bottleneck Models (TCBMs) are interpretable-by-design models for text classification that predict a set of salient concepts before making the final prediction. This paper proposes Complete Textual Concept Bottleneck Model (CT-CBM), a novel TCBM generator building concept labels in a fully unsupervised manner using a small language model, eliminating both the need for predefined human labeled concepts and LLM annotations. CT-CBM iteratively targets and adds important and identifiable concepts in the bottleneck layer to create a complete concept basis. CT-CBM achieves striking re"},"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":"2502.11100","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-16T12:28:43Z","cross_cats_sorted":[],"title_canon_sha256":"f90e9b7f3393b5a930c9d9e177caef910cd821c7ff592c5b25e0349e1b8b1be4","abstract_canon_sha256":"34a5891dd23c127a368baad47493c6540c9ff4048f96f7ece66e3234505b7c3d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:52.564450Z","signature_b64":"GUMUKU5yiNtYw0BPntzqueZqcR63G7Dj7PVSIr6dLEiEDhN+YUenttzKLiwkcWFPEgmIXoYL5s9PZBwCdW9BCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1fd07f199478ec452b6c48ec1fc405ef5a6b982ebbc5fa55ad5e7c019f0f66f3","last_reissued_at":"2026-07-05T11:10:52.563983Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:52.563983Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Achieving Concept Completeness for Textual Concept Bottleneck Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jean-Noel Vittaut, Marie-Jeanne Lesot, Milan Bhan, Nicolas Chesneau, Pierre Moreau, Yann Choho","submitted_at":"2025-02-16T12:28:43Z","abstract_excerpt":"Textual Concept Bottleneck Models (TCBMs) are interpretable-by-design models for text classification that predict a set of salient concepts before making the final prediction. This paper proposes Complete Textual Concept Bottleneck Model (CT-CBM), a novel TCBM generator building concept labels in a fully unsupervised manner using a small language model, eliminating both the need for predefined human labeled concepts and LLM annotations. CT-CBM iteratively targets and adds important and identifiable concepts in the bottleneck layer to create a complete concept basis. CT-CBM achieves striking re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11100","kind":"arxiv","version":3},"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/2502.11100/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":"2502.11100","created_at":"2026-07-05T11:10:52.564036+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.11100v3","created_at":"2026-07-05T11:10:52.564036+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11100","created_at":"2026-07-05T11:10:52.564036+00:00"},{"alias_kind":"pith_short_12","alias_value":"D7IH6GMUPDWE","created_at":"2026-07-05T11:10:52.564036+00:00"},{"alias_kind":"pith_short_16","alias_value":"D7IH6GMUPDWEKK3M","created_at":"2026-07-05T11:10:52.564036+00:00"},{"alias_kind":"pith_short_8","alias_value":"D7IH6GMU","created_at":"2026-07-05T11:10:52.564036+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.22506","citing_title":"Sparsification and Reconstruction from the Perspective of Representation Geometry","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D7IH6GMUPDWEKK3MJDWB7RAF55","json":"https://pith.science/pith/D7IH6GMUPDWEKK3MJDWB7RAF55.json","graph_json":"https://pith.science/api/pith-number/D7IH6GMUPDWEKK3MJDWB7RAF55/graph.json","events_json":"https://pith.science/api/pith-number/D7IH6GMUPDWEKK3MJDWB7RAF55/events.json","paper":"https://pith.science/paper/D7IH6GMU"},"agent_actions":{"view_html":"https://pith.science/pith/D7IH6GMUPDWEKK3MJDWB7RAF55","download_json":"https://pith.science/pith/D7IH6GMUPDWEKK3MJDWB7RAF55.json","view_paper":"https://pith.science/paper/D7IH6GMU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.11100&json=true","fetch_graph":"https://pith.science/api/pith-number/D7IH6GMUPDWEKK3MJDWB7RAF55/graph.json","fetch_events":"https://pith.science/api/pith-number/D7IH6GMUPDWEKK3MJDWB7RAF55/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D7IH6GMUPDWEKK3MJDWB7RAF55/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D7IH6GMUPDWEKK3MJDWB7RAF55/action/storage_attestation","attest_author":"https://pith.science/pith/D7IH6GMUPDWEKK3MJDWB7RAF55/action/author_attestation","sign_citation":"https://pith.science/pith/D7IH6GMUPDWEKK3MJDWB7RAF55/action/citation_signature","submit_replication":"https://pith.science/pith/D7IH6GMUPDWEKK3MJDWB7RAF55/action/replication_record"}},"created_at":"2026-07-05T11:10:52.564036+00:00","updated_at":"2026-07-05T11:10:52.564036+00:00"}