{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:R34N3QCD2DKM2QPONSKJMU26CN","short_pith_number":"pith:R34N3QCD","schema_version":"1.0","canonical_sha256":"8ef8ddc043d0d4cd41ee6c9496535e13718ccd6ceb4a7d6ab4226a3d19703828","source":{"kind":"arxiv","id":"2311.10263","version":2},"attestation_state":"computed","paper":{"title":"Stable Differentiable Causal Discovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ME"],"primary_cat":"cs.LG","authors_text":"Achille Nazaret, David Blei, Elham Azizi, Justin Hong","submitted_at":"2023-11-17T01:14:24Z","abstract_excerpt":"Inferring causal relationships as directed acyclic graphs (DAGs) is an important but challenging problem. Differentiable Causal Discovery (DCD) is a promising approach to this problem, framing the search as a continuous optimization. But existing DCD methods are numerically unstable, with poor performance beyond tens of variables. In this paper, we propose Stable Differentiable Causal Discovery (SDCD), a new method that improves previous DCD methods in two ways: (1) It employs an alternative constraint for acyclicity; this constraint is more stable, both theoretically and empirically, and fast"},"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":"2311.10263","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-17T01:14:24Z","cross_cats_sorted":["stat.ME"],"title_canon_sha256":"508a36b9c8d0ceca124b68816dcf6c5559bf2c3ab830a73138dacf24a04b016d","abstract_canon_sha256":"15575db17d355926be9bc4a570a9de5c02c9299545c99a07b98471af8b03c4be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:37:15.497374Z","signature_b64":"RYyBSVh3gwSHswcYo5NgukcSjO78N7diNFl+4zHBfTMpSAs3Y5wKOK/Egzreg3GiBh8jAG/5Ltls2lqM2/QHBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ef8ddc043d0d4cd41ee6c9496535e13718ccd6ceb4a7d6ab4226a3d19703828","last_reissued_at":"2026-07-05T08:37:15.496876Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:37:15.496876Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stable Differentiable Causal Discovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ME"],"primary_cat":"cs.LG","authors_text":"Achille Nazaret, David Blei, Elham Azizi, Justin Hong","submitted_at":"2023-11-17T01:14:24Z","abstract_excerpt":"Inferring causal relationships as directed acyclic graphs (DAGs) is an important but challenging problem. Differentiable Causal Discovery (DCD) is a promising approach to this problem, framing the search as a continuous optimization. But existing DCD methods are numerically unstable, with poor performance beyond tens of variables. In this paper, we propose Stable Differentiable Causal Discovery (SDCD), a new method that improves previous DCD methods in two ways: (1) It employs an alternative constraint for acyclicity; this constraint is more stable, both theoretically and empirically, and fast"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.10263","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/2311.10263/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":"2311.10263","created_at":"2026-07-05T08:37:15.496936+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.10263v2","created_at":"2026-07-05T08:37:15.496936+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.10263","created_at":"2026-07-05T08:37:15.496936+00:00"},{"alias_kind":"pith_short_12","alias_value":"R34N3QCD2DKM","created_at":"2026-07-05T08:37:15.496936+00:00"},{"alias_kind":"pith_short_16","alias_value":"R34N3QCD2DKM2QPO","created_at":"2026-07-05T08:37:15.496936+00:00"},{"alias_kind":"pith_short_8","alias_value":"R34N3QCD","created_at":"2026-07-05T08:37:15.496936+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31156","citing_title":"TabCausal: Pretraining Across Causal Environments for Tabular Causal Discovery","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R34N3QCD2DKM2QPONSKJMU26CN","json":"https://pith.science/pith/R34N3QCD2DKM2QPONSKJMU26CN.json","graph_json":"https://pith.science/api/pith-number/R34N3QCD2DKM2QPONSKJMU26CN/graph.json","events_json":"https://pith.science/api/pith-number/R34N3QCD2DKM2QPONSKJMU26CN/events.json","paper":"https://pith.science/paper/R34N3QCD"},"agent_actions":{"view_html":"https://pith.science/pith/R34N3QCD2DKM2QPONSKJMU26CN","download_json":"https://pith.science/pith/R34N3QCD2DKM2QPONSKJMU26CN.json","view_paper":"https://pith.science/paper/R34N3QCD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.10263&json=true","fetch_graph":"https://pith.science/api/pith-number/R34N3QCD2DKM2QPONSKJMU26CN/graph.json","fetch_events":"https://pith.science/api/pith-number/R34N3QCD2DKM2QPONSKJMU26CN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R34N3QCD2DKM2QPONSKJMU26CN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R34N3QCD2DKM2QPONSKJMU26CN/action/storage_attestation","attest_author":"https://pith.science/pith/R34N3QCD2DKM2QPONSKJMU26CN/action/author_attestation","sign_citation":"https://pith.science/pith/R34N3QCD2DKM2QPONSKJMU26CN/action/citation_signature","submit_replication":"https://pith.science/pith/R34N3QCD2DKM2QPONSKJMU26CN/action/replication_record"}},"created_at":"2026-07-05T08:37:15.496936+00:00","updated_at":"2026-07-05T08:37:15.496936+00:00"}