{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NLDWFBHZY23DV3V4U7P7MBHBLD","short_pith_number":"pith:NLDWFBHZ","schema_version":"1.0","canonical_sha256":"6ac76284f9c6b63aeebca7dff604e158e447a03168b365de0d10665b77111cd9","source":{"kind":"arxiv","id":"2606.19594","version":1},"attestation_state":"computed","paper":{"title":"Unsupervised Causal Abstractions Discovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dhanya Sridhar, Simon Lacoste-Julien, Th\\'eo Saulus","submitted_at":"2026-06-17T20:56:44Z","abstract_excerpt":"Causal abstractions formalize when a high-level structural causal model (SCM) captures the interventional behavior of a lower-level SCM. Existing applications of this notion largely follow a hypothesis-testing paradigm: an expert proposes a candidate high-level model and then evaluates if the low-level system implements it. We study the complementary problem of learning a high-level model directly from low-level measurements. Our contributions leverage hypotheses from low-rank causal discovery, and can be summarized as follows: (1) we show that observations generated by a low-rank graph induce"},"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":"2606.19594","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-17T20:56:44Z","cross_cats_sorted":[],"title_canon_sha256":"a398670c18667949ffbcf1e6d83da484b4673c83beb1cb94bd1f6b82a8972b96","abstract_canon_sha256":"c5bd0f033827f1df0d4c723f8d935d9e608ea0ed075e3d423be9c4f215c2d331"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:29.711766Z","signature_b64":"ruLSPP7flZusexhOpnpWdSfnU9Itr7I1XkPaoGbjpvBMmdu5BLyz8HXMIZcE57j3JAJGzg7/l8BEFidVG6KhCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ac76284f9c6b63aeebca7dff604e158e447a03168b365de0d10665b77111cd9","last_reissued_at":"2026-06-19T16:12:29.711420Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:29.711420Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Causal Abstractions Discovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dhanya Sridhar, Simon Lacoste-Julien, Th\\'eo Saulus","submitted_at":"2026-06-17T20:56:44Z","abstract_excerpt":"Causal abstractions formalize when a high-level structural causal model (SCM) captures the interventional behavior of a lower-level SCM. Existing applications of this notion largely follow a hypothesis-testing paradigm: an expert proposes a candidate high-level model and then evaluates if the low-level system implements it. We study the complementary problem of learning a high-level model directly from low-level measurements. Our contributions leverage hypotheses from low-rank causal discovery, and can be summarized as follows: (1) we show that observations generated by a low-rank graph induce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19594","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/2606.19594/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":"2606.19594","created_at":"2026-06-19T16:12:29.711482+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.19594v1","created_at":"2026-06-19T16:12:29.711482+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19594","created_at":"2026-06-19T16:12:29.711482+00:00"},{"alias_kind":"pith_short_12","alias_value":"NLDWFBHZY23D","created_at":"2026-06-19T16:12:29.711482+00:00"},{"alias_kind":"pith_short_16","alias_value":"NLDWFBHZY23DV3V4","created_at":"2026-06-19T16:12:29.711482+00:00"},{"alias_kind":"pith_short_8","alias_value":"NLDWFBHZ","created_at":"2026-06-19T16:12:29.711482+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/NLDWFBHZY23DV3V4U7P7MBHBLD","json":"https://pith.science/pith/NLDWFBHZY23DV3V4U7P7MBHBLD.json","graph_json":"https://pith.science/api/pith-number/NLDWFBHZY23DV3V4U7P7MBHBLD/graph.json","events_json":"https://pith.science/api/pith-number/NLDWFBHZY23DV3V4U7P7MBHBLD/events.json","paper":"https://pith.science/paper/NLDWFBHZ"},"agent_actions":{"view_html":"https://pith.science/pith/NLDWFBHZY23DV3V4U7P7MBHBLD","download_json":"https://pith.science/pith/NLDWFBHZY23DV3V4U7P7MBHBLD.json","view_paper":"https://pith.science/paper/NLDWFBHZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.19594&json=true","fetch_graph":"https://pith.science/api/pith-number/NLDWFBHZY23DV3V4U7P7MBHBLD/graph.json","fetch_events":"https://pith.science/api/pith-number/NLDWFBHZY23DV3V4U7P7MBHBLD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NLDWFBHZY23DV3V4U7P7MBHBLD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NLDWFBHZY23DV3V4U7P7MBHBLD/action/storage_attestation","attest_author":"https://pith.science/pith/NLDWFBHZY23DV3V4U7P7MBHBLD/action/author_attestation","sign_citation":"https://pith.science/pith/NLDWFBHZY23DV3V4U7P7MBHBLD/action/citation_signature","submit_replication":"https://pith.science/pith/NLDWFBHZY23DV3V4U7P7MBHBLD/action/replication_record"}},"created_at":"2026-06-19T16:12:29.711482+00:00","updated_at":"2026-06-19T16:12:29.711482+00:00"}