{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QQV3DR4GM6MLMK7LJREKCOGTJ3","short_pith_number":"pith:QQV3DR4G","schema_version":"1.0","canonical_sha256":"842bb1c7866798b62beb4c48a138d34effb975280a14fe6c4b9370892d72d97f","source":{"kind":"arxiv","id":"2303.02186","version":2},"attestation_state":"computed","paper":{"title":"Causal Deep Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jeroen Berrevoets, Krzysztof Kacprzyk, Mihaela van der Schaar, Zhaozhi Qian","submitted_at":"2023-03-03T19:19:18Z","abstract_excerpt":"Causality has the potential to truly transform the way we solve a large number of real-world problems. Yet, so far, its potential largely remains to be unlocked as causality often requires crucial assumptions which cannot be tested in practice. To address this challenge, we propose a new way of thinking about causality -- we call this causal deep learning. Our causal deep learning framework spans three dimensions: (1) a structural dimension, which incorporates partial yet testable causal knowledge rather than assuming either complete or no causal knowledge among the variables of interest; (2) "},"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":"2303.02186","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-03T19:19:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8991a306a71e5e43d30b4ebe9e3f8919f86f2f99d1fd15af28ddd417b08f5c92","abstract_canon_sha256":"d2e032961758f5f6db693d1f1e71a7f3be9dbf37c90889c08c5c2e734d440cdb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:44:53.099831Z","signature_b64":"vByoVL2d7ZrhbP2WRsXffipkPzoSj8jObcXgZACBda8TXvvRh43iZUMEGrV4mBgK6kANvcx+q2uRhx6Sgx/8Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"842bb1c7866798b62beb4c48a138d34effb975280a14fe6c4b9370892d72d97f","last_reissued_at":"2026-07-05T07:44:53.099360Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:44:53.099360Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Causal Deep Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jeroen Berrevoets, Krzysztof Kacprzyk, Mihaela van der Schaar, Zhaozhi Qian","submitted_at":"2023-03-03T19:19:18Z","abstract_excerpt":"Causality has the potential to truly transform the way we solve a large number of real-world problems. Yet, so far, its potential largely remains to be unlocked as causality often requires crucial assumptions which cannot be tested in practice. To address this challenge, we propose a new way of thinking about causality -- we call this causal deep learning. Our causal deep learning framework spans three dimensions: (1) a structural dimension, which incorporates partial yet testable causal knowledge rather than assuming either complete or no causal knowledge among the variables of interest; (2) "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.02186","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/2303.02186/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":"2303.02186","created_at":"2026-07-05T07:44:53.099418+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.02186v2","created_at":"2026-07-05T07:44:53.099418+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.02186","created_at":"2026-07-05T07:44:53.099418+00:00"},{"alias_kind":"pith_short_12","alias_value":"QQV3DR4GM6ML","created_at":"2026-07-05T07:44:53.099418+00:00"},{"alias_kind":"pith_short_16","alias_value":"QQV3DR4GM6MLMK7L","created_at":"2026-07-05T07:44:53.099418+00:00"},{"alias_kind":"pith_short_8","alias_value":"QQV3DR4G","created_at":"2026-07-05T07:44:53.099418+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.02640","citing_title":"Trustworthy AI Suffers from Invariance Conflicts and Causality is The Solution","ref_index":113,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QQV3DR4GM6MLMK7LJREKCOGTJ3","json":"https://pith.science/pith/QQV3DR4GM6MLMK7LJREKCOGTJ3.json","graph_json":"https://pith.science/api/pith-number/QQV3DR4GM6MLMK7LJREKCOGTJ3/graph.json","events_json":"https://pith.science/api/pith-number/QQV3DR4GM6MLMK7LJREKCOGTJ3/events.json","paper":"https://pith.science/paper/QQV3DR4G"},"agent_actions":{"view_html":"https://pith.science/pith/QQV3DR4GM6MLMK7LJREKCOGTJ3","download_json":"https://pith.science/pith/QQV3DR4GM6MLMK7LJREKCOGTJ3.json","view_paper":"https://pith.science/paper/QQV3DR4G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.02186&json=true","fetch_graph":"https://pith.science/api/pith-number/QQV3DR4GM6MLMK7LJREKCOGTJ3/graph.json","fetch_events":"https://pith.science/api/pith-number/QQV3DR4GM6MLMK7LJREKCOGTJ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QQV3DR4GM6MLMK7LJREKCOGTJ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QQV3DR4GM6MLMK7LJREKCOGTJ3/action/storage_attestation","attest_author":"https://pith.science/pith/QQV3DR4GM6MLMK7LJREKCOGTJ3/action/author_attestation","sign_citation":"https://pith.science/pith/QQV3DR4GM6MLMK7LJREKCOGTJ3/action/citation_signature","submit_replication":"https://pith.science/pith/QQV3DR4GM6MLMK7LJREKCOGTJ3/action/replication_record"}},"created_at":"2026-07-05T07:44:53.099418+00:00","updated_at":"2026-07-05T07:44:53.099418+00:00"}