{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5SMLKRH6MOHEQ3MJRMACRENFIL","short_pith_number":"pith:5SMLKRH6","schema_version":"1.0","canonical_sha256":"ec98b544fe638e486d898b002891a542e08200ad105bd5be86bd646016280d4e","source":{"kind":"arxiv","id":"2401.14142","version":4},"attestation_state":"computed","paper":{"title":"Energy-Based Concept Bottleneck Models: Unifying Prediction, Concept Intervention, and Probabilistic Interpretations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Hao Wang, Lu Mi, Xiaomeng Li, Xinyue Xu, Yi Qin","submitted_at":"2024-01-25T12:46:37Z","abstract_excerpt":"Existing methods, such as concept bottleneck models (CBMs), have been successful in providing concept-based interpretations for black-box deep learning models. They typically work by predicting concepts given the input and then predicting the final class label given the predicted concepts. However, (1) they often fail to capture the high-order, nonlinear interaction between concepts, e.g., correcting a predicted concept (e.g., \"yellow breast\") does not help correct highly correlated concepts (e.g., \"yellow belly\"), leading to suboptimal final accuracy; (2) they cannot naturally quantify the co"},"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":"2401.14142","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-25T12:46:37Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"2a294e507c4888ff2a2fc19f6705650c6318a60a390794db7cf68e6e8ea0ece9","abstract_canon_sha256":"304cd68d1a11f6075e23f985007014f4ebae88142e721a449c7c13a0d303cda9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:32.474451Z","signature_b64":"GtX15QBCWxBjgqe6BWXmOROxNdZj1gH1iZRoGOAkq48L5/cHj0XLb/Q8LlJF8jFRe0FlVvzbewpP7TW6c7QEDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec98b544fe638e486d898b002891a542e08200ad105bd5be86bd646016280d4e","last_reissued_at":"2026-07-05T09:55:32.473944Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:32.473944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Energy-Based Concept Bottleneck Models: Unifying Prediction, Concept Intervention, and Probabilistic Interpretations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Hao Wang, Lu Mi, Xiaomeng Li, Xinyue Xu, Yi Qin","submitted_at":"2024-01-25T12:46:37Z","abstract_excerpt":"Existing methods, such as concept bottleneck models (CBMs), have been successful in providing concept-based interpretations for black-box deep learning models. They typically work by predicting concepts given the input and then predicting the final class label given the predicted concepts. However, (1) they often fail to capture the high-order, nonlinear interaction between concepts, e.g., correcting a predicted concept (e.g., \"yellow breast\") does not help correct highly correlated concepts (e.g., \"yellow belly\"), leading to suboptimal final accuracy; (2) they cannot naturally quantify the co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.14142","kind":"arxiv","version":4},"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/2401.14142/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":"2401.14142","created_at":"2026-07-05T09:55:32.474002+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.14142v4","created_at":"2026-07-05T09:55:32.474002+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.14142","created_at":"2026-07-05T09:55:32.474002+00:00"},{"alias_kind":"pith_short_12","alias_value":"5SMLKRH6MOHE","created_at":"2026-07-05T09:55:32.474002+00:00"},{"alias_kind":"pith_short_16","alias_value":"5SMLKRH6MOHEQ3MJ","created_at":"2026-07-05T09:55:32.474002+00:00"},{"alias_kind":"pith_short_8","alias_value":"5SMLKRH6","created_at":"2026-07-05T09:55:32.474002+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04326","citing_title":"Measuring What Matters: Synthetic Benchmarks for Concept Bottleneck Models","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20908","citing_title":"SynCB: A Synergy Concept-Based Model with Dynamic Routing Between Concepts and Complementary Neural Branches","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5SMLKRH6MOHEQ3MJRMACRENFIL","json":"https://pith.science/pith/5SMLKRH6MOHEQ3MJRMACRENFIL.json","graph_json":"https://pith.science/api/pith-number/5SMLKRH6MOHEQ3MJRMACRENFIL/graph.json","events_json":"https://pith.science/api/pith-number/5SMLKRH6MOHEQ3MJRMACRENFIL/events.json","paper":"https://pith.science/paper/5SMLKRH6"},"agent_actions":{"view_html":"https://pith.science/pith/5SMLKRH6MOHEQ3MJRMACRENFIL","download_json":"https://pith.science/pith/5SMLKRH6MOHEQ3MJRMACRENFIL.json","view_paper":"https://pith.science/paper/5SMLKRH6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.14142&json=true","fetch_graph":"https://pith.science/api/pith-number/5SMLKRH6MOHEQ3MJRMACRENFIL/graph.json","fetch_events":"https://pith.science/api/pith-number/5SMLKRH6MOHEQ3MJRMACRENFIL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5SMLKRH6MOHEQ3MJRMACRENFIL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5SMLKRH6MOHEQ3MJRMACRENFIL/action/storage_attestation","attest_author":"https://pith.science/pith/5SMLKRH6MOHEQ3MJRMACRENFIL/action/author_attestation","sign_citation":"https://pith.science/pith/5SMLKRH6MOHEQ3MJRMACRENFIL/action/citation_signature","submit_replication":"https://pith.science/pith/5SMLKRH6MOHEQ3MJRMACRENFIL/action/replication_record"}},"created_at":"2026-07-05T09:55:32.474002+00:00","updated_at":"2026-07-05T09:55:32.474002+00:00"}