{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FIMBJ34AOQJT2RP6S2G6OEAIIL","short_pith_number":"pith:FIMBJ34A","schema_version":"1.0","canonical_sha256":"2a1814ef8074133d45fe968de7100842dfcc6a2a39ff81a871c6ae3f228ce8ad","source":{"kind":"arxiv","id":"2605.20612","version":1},"attestation_state":"computed","paper":{"title":"Matryoshka Concept Bottleneck Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hongbin Lin, Jie Li, Lijie Hu, Xinyue Xu, Ziye Chen","submitted_at":"2026-05-20T01:59:06Z","abstract_excerpt":"Concept Bottleneck Models (CBMs) have emerged as a prominent paradigm for interpretable deep learning, learning by grounding predictions in human-understandable concepts. However, their practical deployment is hindered by the high cost of test-time intervention, as correcting model errors typically requires human experts to manually inspect and verify a large set of predicted concepts. Existing approaches suffer from a fundamental structural limitation: they either adopt a single static concept set, forcing experts to exhaustively annotate concepts and incurring prohibitive intervention costs,"},"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":"2605.20612","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T01:59:06Z","cross_cats_sorted":[],"title_canon_sha256":"dca83202d704810d2d08314002ed1f2af5f26372327ecd700f0258e018552963","abstract_canon_sha256":"fb2f4b657db4c3ff1c7caec6b0e80cee1512a365a1170708c589e67d81218125"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:44.547744Z","signature_b64":"adxvH8vJ6cb64R1C4yfTS129aWEwsMKjS2YLe3UZpyOG/RjwhrevzbH3ql3DKQ8NUi8zSzPbV+RBY1qsBQWwBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a1814ef8074133d45fe968de7100842dfcc6a2a39ff81a871c6ae3f228ce8ad","last_reissued_at":"2026-05-21T01:04:44.547094Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:44.547094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Matryoshka Concept Bottleneck Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hongbin Lin, Jie Li, Lijie Hu, Xinyue Xu, Ziye Chen","submitted_at":"2026-05-20T01:59:06Z","abstract_excerpt":"Concept Bottleneck Models (CBMs) have emerged as a prominent paradigm for interpretable deep learning, learning by grounding predictions in human-understandable concepts. However, their practical deployment is hindered by the high cost of test-time intervention, as correcting model errors typically requires human experts to manually inspect and verify a large set of predicted concepts. Existing approaches suffer from a fundamental structural limitation: they either adopt a single static concept set, forcing experts to exhaustively annotate concepts and incurring prohibitive intervention costs,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20612","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/2605.20612/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":"2605.20612","created_at":"2026-05-21T01:04:44.547202+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.20612v1","created_at":"2026-05-21T01:04:44.547202+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20612","created_at":"2026-05-21T01:04:44.547202+00:00"},{"alias_kind":"pith_short_12","alias_value":"FIMBJ34AOQJT","created_at":"2026-05-21T01:04:44.547202+00:00"},{"alias_kind":"pith_short_16","alias_value":"FIMBJ34AOQJT2RP6","created_at":"2026-05-21T01:04:44.547202+00:00"},{"alias_kind":"pith_short_8","alias_value":"FIMBJ34A","created_at":"2026-05-21T01:04:44.547202+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/FIMBJ34AOQJT2RP6S2G6OEAIIL","json":"https://pith.science/pith/FIMBJ34AOQJT2RP6S2G6OEAIIL.json","graph_json":"https://pith.science/api/pith-number/FIMBJ34AOQJT2RP6S2G6OEAIIL/graph.json","events_json":"https://pith.science/api/pith-number/FIMBJ34AOQJT2RP6S2G6OEAIIL/events.json","paper":"https://pith.science/paper/FIMBJ34A"},"agent_actions":{"view_html":"https://pith.science/pith/FIMBJ34AOQJT2RP6S2G6OEAIIL","download_json":"https://pith.science/pith/FIMBJ34AOQJT2RP6S2G6OEAIIL.json","view_paper":"https://pith.science/paper/FIMBJ34A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.20612&json=true","fetch_graph":"https://pith.science/api/pith-number/FIMBJ34AOQJT2RP6S2G6OEAIIL/graph.json","fetch_events":"https://pith.science/api/pith-number/FIMBJ34AOQJT2RP6S2G6OEAIIL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FIMBJ34AOQJT2RP6S2G6OEAIIL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FIMBJ34AOQJT2RP6S2G6OEAIIL/action/storage_attestation","attest_author":"https://pith.science/pith/FIMBJ34AOQJT2RP6S2G6OEAIIL/action/author_attestation","sign_citation":"https://pith.science/pith/FIMBJ34AOQJT2RP6S2G6OEAIIL/action/citation_signature","submit_replication":"https://pith.science/pith/FIMBJ34AOQJT2RP6S2G6OEAIIL/action/replication_record"}},"created_at":"2026-05-21T01:04:44.547202+00:00","updated_at":"2026-05-21T01:04:44.547202+00:00"}