{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FYSW5HAOFNNRT2NCX2L5LWX6IE","short_pith_number":"pith:FYSW5HAO","schema_version":"1.0","canonical_sha256":"2e256e9c0e2b5b19e9a2be97d5dafe412305854275889d0cdd1306e076a943af","source":{"kind":"arxiv","id":"2603.01372","version":2},"attestation_state":"computed","paper":{"title":"Causal Neural Probabilistic Circuits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Han Zhao, Weixin Chen","submitted_at":"2026-03-02T02:15:24Z","abstract_excerpt":"Concept Bottleneck Models (CBMs) enhance the interpretability of end-to-end neural networks by introducing a layer of concepts and predicting the class label from the concept predictions. A key property of CBMs is that they support interventions, i.e., domain experts can correct mispredicted concept values at test time to improve the final accuracy. However, typical CBMs apply interventions by overwriting only the corrected concept while leaving other concept predictions unchanged, which ignores causal dependencies among concepts. To address this, we propose the Causal Neural Probabilistic Cir"},"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":"2603.01372","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-02T02:15:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e0219f6f4a10d62564df9a558720fdefe2dcc1d529f1e0404ee8ae5747d71b5e","abstract_canon_sha256":"9368274e67c7475d3c382f763833a380d0a0f7655d1584164f02103cee42d03b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:11.106599Z","signature_b64":"IxjZ+HMFDjK9dz7+yeHtL3RNZNZ/lIivZgsZ9QE5VcG4R4dY32FoOAvdLDnATtMFTpqaS9AgLhg3foJdvVz/Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e256e9c0e2b5b19e9a2be97d5dafe412305854275889d0cdd1306e076a943af","last_reissued_at":"2026-06-03T01:05:11.106123Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:11.106123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Causal Neural Probabilistic Circuits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Han Zhao, Weixin Chen","submitted_at":"2026-03-02T02:15:24Z","abstract_excerpt":"Concept Bottleneck Models (CBMs) enhance the interpretability of end-to-end neural networks by introducing a layer of concepts and predicting the class label from the concept predictions. A key property of CBMs is that they support interventions, i.e., domain experts can correct mispredicted concept values at test time to improve the final accuracy. However, typical CBMs apply interventions by overwriting only the corrected concept while leaving other concept predictions unchanged, which ignores causal dependencies among concepts. To address this, we propose the Causal Neural Probabilistic Cir"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.01372","kind":"arxiv","version":2},"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/2603.01372/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":"2603.01372","created_at":"2026-06-03T01:05:11.106180+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.01372v2","created_at":"2026-06-03T01:05:11.106180+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.01372","created_at":"2026-06-03T01:05:11.106180+00:00"},{"alias_kind":"pith_short_12","alias_value":"FYSW5HAOFNNR","created_at":"2026-06-03T01:05:11.106180+00:00"},{"alias_kind":"pith_short_16","alias_value":"FYSW5HAOFNNRT2NC","created_at":"2026-06-03T01:05:11.106180+00:00"},{"alias_kind":"pith_short_8","alias_value":"FYSW5HAO","created_at":"2026-06-03T01:05:11.106180+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/FYSW5HAOFNNRT2NCX2L5LWX6IE","json":"https://pith.science/pith/FYSW5HAOFNNRT2NCX2L5LWX6IE.json","graph_json":"https://pith.science/api/pith-number/FYSW5HAOFNNRT2NCX2L5LWX6IE/graph.json","events_json":"https://pith.science/api/pith-number/FYSW5HAOFNNRT2NCX2L5LWX6IE/events.json","paper":"https://pith.science/paper/FYSW5HAO"},"agent_actions":{"view_html":"https://pith.science/pith/FYSW5HAOFNNRT2NCX2L5LWX6IE","download_json":"https://pith.science/pith/FYSW5HAOFNNRT2NCX2L5LWX6IE.json","view_paper":"https://pith.science/paper/FYSW5HAO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.01372&json=true","fetch_graph":"https://pith.science/api/pith-number/FYSW5HAOFNNRT2NCX2L5LWX6IE/graph.json","fetch_events":"https://pith.science/api/pith-number/FYSW5HAOFNNRT2NCX2L5LWX6IE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FYSW5HAOFNNRT2NCX2L5LWX6IE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FYSW5HAOFNNRT2NCX2L5LWX6IE/action/storage_attestation","attest_author":"https://pith.science/pith/FYSW5HAOFNNRT2NCX2L5LWX6IE/action/author_attestation","sign_citation":"https://pith.science/pith/FYSW5HAOFNNRT2NCX2L5LWX6IE/action/citation_signature","submit_replication":"https://pith.science/pith/FYSW5HAOFNNRT2NCX2L5LWX6IE/action/replication_record"}},"created_at":"2026-06-03T01:05:11.106180+00:00","updated_at":"2026-06-03T01:05:11.106180+00:00"}