{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6QVWZ2YBB7WMNCAE4TEM6JWKAG","short_pith_number":"pith:6QVWZ2YB","schema_version":"1.0","canonical_sha256":"f42b6ceb010fecc68804e4c8cf26ca01ba18874ad4518fe6a4265fba6d6f06a3","source":{"kind":"arxiv","id":"2412.11576","version":3},"attestation_state":"computed","paper":{"title":"DCBM: Data-Efficient Visual Concept Bottleneck Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christian Bartelt, Katharina Prasse, Margret Keuper, Patrick Knab, Sascha Marton","submitted_at":"2024-12-16T09:04:58Z","abstract_excerpt":"Concept Bottleneck Models (CBMs) enhance the interpretability of neural networks by basing predictions on human-understandable concepts. However, current CBMs typically rely on concept sets extracted from large language models or extensive image corpora, limiting their effectiveness in data-sparse scenarios. We propose Data-efficient CBMs (DCBMs), which reduce the need for large sample sizes during concept generation while preserving interpretability. DCBMs define concepts as image regions detected by segmentation or detection foundation models, allowing each image to generate multiple concept"},"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":"2412.11576","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-16T09:04:58Z","cross_cats_sorted":[],"title_canon_sha256":"12e3924c6183f60f0f1dcf4b616cd21109b6aa7748863d34e56ba37cf582ff82","abstract_canon_sha256":"3303d863fcfb5357f5581e6f2c0e68f4b67b43cffe72f2b319fa0b804b54013f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:39.936021Z","signature_b64":"eG+sOl7Ixl0u85t2Ks3zLMrUQShX7IbGzUkrGm6i1VgGLL3m15UdQErubDKGu4GFXpP25wBT9VDUiunulhv0CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f42b6ceb010fecc68804e4c8cf26ca01ba18874ad4518fe6a4265fba6d6f06a3","last_reissued_at":"2026-07-05T11:30:39.935491Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:39.935491Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DCBM: Data-Efficient Visual Concept Bottleneck Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christian Bartelt, Katharina Prasse, Margret Keuper, Patrick Knab, Sascha Marton","submitted_at":"2024-12-16T09:04:58Z","abstract_excerpt":"Concept Bottleneck Models (CBMs) enhance the interpretability of neural networks by basing predictions on human-understandable concepts. However, current CBMs typically rely on concept sets extracted from large language models or extensive image corpora, limiting their effectiveness in data-sparse scenarios. We propose Data-efficient CBMs (DCBMs), which reduce the need for large sample sizes during concept generation while preserving interpretability. DCBMs define concepts as image regions detected by segmentation or detection foundation models, allowing each image to generate multiple concept"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11576","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/2412.11576/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":"2412.11576","created_at":"2026-07-05T11:30:39.935554+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.11576v3","created_at":"2026-07-05T11:30:39.935554+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11576","created_at":"2026-07-05T11:30:39.935554+00:00"},{"alias_kind":"pith_short_12","alias_value":"6QVWZ2YBB7WM","created_at":"2026-07-05T11:30:39.935554+00:00"},{"alias_kind":"pith_short_16","alias_value":"6QVWZ2YBB7WMNCAE","created_at":"2026-07-05T11:30:39.935554+00:00"},{"alias_kind":"pith_short_8","alias_value":"6QVWZ2YB","created_at":"2026-07-05T11:30:39.935554+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16405","citing_title":"Concepts Worth Having: Refining VLM-Guided Concept Bottleneck Models with Minimal Annotations","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6QVWZ2YBB7WMNCAE4TEM6JWKAG","json":"https://pith.science/pith/6QVWZ2YBB7WMNCAE4TEM6JWKAG.json","graph_json":"https://pith.science/api/pith-number/6QVWZ2YBB7WMNCAE4TEM6JWKAG/graph.json","events_json":"https://pith.science/api/pith-number/6QVWZ2YBB7WMNCAE4TEM6JWKAG/events.json","paper":"https://pith.science/paper/6QVWZ2YB"},"agent_actions":{"view_html":"https://pith.science/pith/6QVWZ2YBB7WMNCAE4TEM6JWKAG","download_json":"https://pith.science/pith/6QVWZ2YBB7WMNCAE4TEM6JWKAG.json","view_paper":"https://pith.science/paper/6QVWZ2YB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.11576&json=true","fetch_graph":"https://pith.science/api/pith-number/6QVWZ2YBB7WMNCAE4TEM6JWKAG/graph.json","fetch_events":"https://pith.science/api/pith-number/6QVWZ2YBB7WMNCAE4TEM6JWKAG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6QVWZ2YBB7WMNCAE4TEM6JWKAG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6QVWZ2YBB7WMNCAE4TEM6JWKAG/action/storage_attestation","attest_author":"https://pith.science/pith/6QVWZ2YBB7WMNCAE4TEM6JWKAG/action/author_attestation","sign_citation":"https://pith.science/pith/6QVWZ2YBB7WMNCAE4TEM6JWKAG/action/citation_signature","submit_replication":"https://pith.science/pith/6QVWZ2YBB7WMNCAE4TEM6JWKAG/action/replication_record"}},"created_at":"2026-07-05T11:30:39.935554+00:00","updated_at":"2026-07-05T11:30:39.935554+00:00"}