{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UTAQTC6O3RK5E6JBEVLE3IA3O6","short_pith_number":"pith:UTAQTC6O","schema_version":"1.0","canonical_sha256":"a4c1098bcedc55d2792125564da01b77ab3679065e746d2af44ca14f87dbbfe2","source":{"kind":"arxiv","id":"2501.19335","version":2},"attestation_state":"computed","paper":{"title":"What is causal about causal models and representations?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Frederik Hytting J{\\o}rgensen, Luigi Gresele, Sebastian Weichwald","submitted_at":"2025-01-31T17:35:21Z","abstract_excerpt":"Causal Bayesian networks are 'causal' models since they make predictions about interventional distributions. To connect such causal model predictions to real-world outcomes, we must determine which actions in the world correspond to which interventions in the model. For example, to interpret an action as an intervention on a treatment variable, the action will presumably have to a) change the distribution of treatment in a way that corresponds to the intervention, and b) not change other aspects, such as how the outcome depends on the treatment; while the marginal distributions of some variabl"},"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":"2501.19335","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-01-31T17:35:21Z","cross_cats_sorted":["cs.AI","cs.LG","math.ST","stat.TH"],"title_canon_sha256":"0f9301cc1cb31edbdd8bbecb3735469ea0829e4878a72c057ef1187ad263d854","abstract_canon_sha256":"803522ee95e0fdca14b3dca9b5f6eb396309e0e30bfdeaf48b85a3cefd095dcc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:54.622591Z","signature_b64":"2K9XT7CQT4J9+087n3G6LDMkp4gTYS4/RkERut6PhOa0fnzTrpQAvt4y+GcQAoYVO6CmBUlFwno7FJuZQhh8AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4c1098bcedc55d2792125564da01b77ab3679065e746d2af44ca14f87dbbfe2","last_reissued_at":"2026-07-05T10:08:54.622088Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:54.622088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What is causal about causal models and representations?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Frederik Hytting J{\\o}rgensen, Luigi Gresele, Sebastian Weichwald","submitted_at":"2025-01-31T17:35:21Z","abstract_excerpt":"Causal Bayesian networks are 'causal' models since they make predictions about interventional distributions. To connect such causal model predictions to real-world outcomes, we must determine which actions in the world correspond to which interventions in the model. For example, to interpret an action as an intervention on a treatment variable, the action will presumably have to a) change the distribution of treatment in a way that corresponds to the intervention, and b) not change other aspects, such as how the outcome depends on the treatment; while the marginal distributions of some variabl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.19335","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/2501.19335/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":"2501.19335","created_at":"2026-07-05T10:08:54.622145+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.19335v2","created_at":"2026-07-05T10:08:54.622145+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.19335","created_at":"2026-07-05T10:08:54.622145+00:00"},{"alias_kind":"pith_short_12","alias_value":"UTAQTC6O3RK5","created_at":"2026-07-05T10:08:54.622145+00:00"},{"alias_kind":"pith_short_16","alias_value":"UTAQTC6O3RK5E6JB","created_at":"2026-07-05T10:08:54.622145+00:00"},{"alias_kind":"pith_short_8","alias_value":"UTAQTC6O","created_at":"2026-07-05T10:08:54.622145+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19594","citing_title":"Unsupervised Causal Abstractions Discovery","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19594","citing_title":"Unsupervised Causal Abstractions Discovery","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00248","citing_title":"Causal Foundations of Collective Agency","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UTAQTC6O3RK5E6JBEVLE3IA3O6","json":"https://pith.science/pith/UTAQTC6O3RK5E6JBEVLE3IA3O6.json","graph_json":"https://pith.science/api/pith-number/UTAQTC6O3RK5E6JBEVLE3IA3O6/graph.json","events_json":"https://pith.science/api/pith-number/UTAQTC6O3RK5E6JBEVLE3IA3O6/events.json","paper":"https://pith.science/paper/UTAQTC6O"},"agent_actions":{"view_html":"https://pith.science/pith/UTAQTC6O3RK5E6JBEVLE3IA3O6","download_json":"https://pith.science/pith/UTAQTC6O3RK5E6JBEVLE3IA3O6.json","view_paper":"https://pith.science/paper/UTAQTC6O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.19335&json=true","fetch_graph":"https://pith.science/api/pith-number/UTAQTC6O3RK5E6JBEVLE3IA3O6/graph.json","fetch_events":"https://pith.science/api/pith-number/UTAQTC6O3RK5E6JBEVLE3IA3O6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UTAQTC6O3RK5E6JBEVLE3IA3O6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UTAQTC6O3RK5E6JBEVLE3IA3O6/action/storage_attestation","attest_author":"https://pith.science/pith/UTAQTC6O3RK5E6JBEVLE3IA3O6/action/author_attestation","sign_citation":"https://pith.science/pith/UTAQTC6O3RK5E6JBEVLE3IA3O6/action/citation_signature","submit_replication":"https://pith.science/pith/UTAQTC6O3RK5E6JBEVLE3IA3O6/action/replication_record"}},"created_at":"2026-07-05T10:08:54.622145+00:00","updated_at":"2026-07-05T10:08:54.622145+00:00"}