{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FEGH4X6VBRVWNLAJVNY3RR3XJP","short_pith_number":"pith:FEGH4X6V","schema_version":"1.0","canonical_sha256":"290c7e5fd50c6b66ac09ab71b8c7774be5fb8e041e24828267273b8252f86dfb","source":{"kind":"arxiv","id":"2605.23861","version":1},"attestation_state":"computed","paper":{"title":"Leveraging Foundation Models for Causal Generative Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Aneesh Komanduri, Xintao Wu","submitted_at":"2026-05-22T17:20:17Z","abstract_excerpt":"Causal generative modeling is essential for developing reliable and transparent AI systems capable of counterfactual reasoning. While existing approaches focus on integrating causal constraints during the training of generative models, they often lack a unified framework to leverage the zero-shot reasoning capabilities of pretrained foundation models. We introduce FM-CGM, a modular framework for end-to-end visual causal reasoning using pretrained foundation models. FM-CGM formalizes the causal pipeline through three core components: a concept extractor, a concept manipulator, and a counterfact"},"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":"2605.23861","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T17:20:17Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"c010c13d1d9567adc57b1642c518e797efb9ccf75b2ad48d5f1b3e4654e90cfb","abstract_canon_sha256":"96a4d8292675da7ee3d6831b9808df285ef8ed0de57252e0dafcebc1fb17e2c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:02:36.558663Z","signature_b64":"hnwsCrpVOpqh0byg2/UJHrRharnZlxksiEZk1KxOBzGLHquV99BJ9+wyamlAyNjnhIm7QshauV3u5Zy1iwtXCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"290c7e5fd50c6b66ac09ab71b8c7774be5fb8e041e24828267273b8252f86dfb","last_reissued_at":"2026-05-25T02:02:36.558118Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:02:36.558118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Foundation Models for Causal Generative Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Aneesh Komanduri, Xintao Wu","submitted_at":"2026-05-22T17:20:17Z","abstract_excerpt":"Causal generative modeling is essential for developing reliable and transparent AI systems capable of counterfactual reasoning. While existing approaches focus on integrating causal constraints during the training of generative models, they often lack a unified framework to leverage the zero-shot reasoning capabilities of pretrained foundation models. We introduce FM-CGM, a modular framework for end-to-end visual causal reasoning using pretrained foundation models. FM-CGM formalizes the causal pipeline through three core components: a concept extractor, a concept manipulator, and a counterfact"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23861","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/2605.23861/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":"2605.23861","created_at":"2026-05-25T02:02:36.558209+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.23861v1","created_at":"2026-05-25T02:02:36.558209+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23861","created_at":"2026-05-25T02:02:36.558209+00:00"},{"alias_kind":"pith_short_12","alias_value":"FEGH4X6VBRVW","created_at":"2026-05-25T02:02:36.558209+00:00"},{"alias_kind":"pith_short_16","alias_value":"FEGH4X6VBRVWNLAJ","created_at":"2026-05-25T02:02:36.558209+00:00"},{"alias_kind":"pith_short_8","alias_value":"FEGH4X6V","created_at":"2026-05-25T02:02:36.558209+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/FEGH4X6VBRVWNLAJVNY3RR3XJP","json":"https://pith.science/pith/FEGH4X6VBRVWNLAJVNY3RR3XJP.json","graph_json":"https://pith.science/api/pith-number/FEGH4X6VBRVWNLAJVNY3RR3XJP/graph.json","events_json":"https://pith.science/api/pith-number/FEGH4X6VBRVWNLAJVNY3RR3XJP/events.json","paper":"https://pith.science/paper/FEGH4X6V"},"agent_actions":{"view_html":"https://pith.science/pith/FEGH4X6VBRVWNLAJVNY3RR3XJP","download_json":"https://pith.science/pith/FEGH4X6VBRVWNLAJVNY3RR3XJP.json","view_paper":"https://pith.science/paper/FEGH4X6V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.23861&json=true","fetch_graph":"https://pith.science/api/pith-number/FEGH4X6VBRVWNLAJVNY3RR3XJP/graph.json","fetch_events":"https://pith.science/api/pith-number/FEGH4X6VBRVWNLAJVNY3RR3XJP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FEGH4X6VBRVWNLAJVNY3RR3XJP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FEGH4X6VBRVWNLAJVNY3RR3XJP/action/storage_attestation","attest_author":"https://pith.science/pith/FEGH4X6VBRVWNLAJVNY3RR3XJP/action/author_attestation","sign_citation":"https://pith.science/pith/FEGH4X6VBRVWNLAJVNY3RR3XJP/action/citation_signature","submit_replication":"https://pith.science/pith/FEGH4X6VBRVWNLAJVNY3RR3XJP/action/replication_record"}},"created_at":"2026-05-25T02:02:36.558209+00:00","updated_at":"2026-05-25T02:02:36.558209+00:00"}