{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:HC7OI6Q7XZ5SF245U2WSBTIGIK","short_pith_number":"pith:HC7OI6Q7","schema_version":"1.0","canonical_sha256":"38bee47a1fbe7b22eb9da6ad20cd0642aaa4f76954b68c3cb058e610d743ff15","source":{"kind":"arxiv","id":"1911.07420","version":1},"attestation_state":"computed","paper":{"title":"A Graph Autoencoder Approach to Causal Structure Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ignavier Ng, Shengyu Zhu, Zhitang Chen, Zhuangyan Fang","submitted_at":"2019-11-18T04:22:00Z","abstract_excerpt":"Causal structure learning has been a challenging task in the past decades and several mainstream approaches such as constraint- and score-based methods have been studied with theoretical guarantees. Recently, a new approach has transformed the combinatorial structure learning problem into a continuous one and then solved it using gradient-based optimization methods. Following the recent state-of-the-arts, we propose a new gradient-based method to learn causal structures from observational data. The proposed method generalizes the recent gradient-based methods to a graph autoencoder framework t"},"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":"1911.07420","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-18T04:22:00Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0b966d6d1d3247ffd7b5b79397bd1e2e330645e5505a525f1d703204010d86e5","abstract_canon_sha256":"5dcfd5fbafa481551d2c475d175b7af094092cea67d9424ff01b0c9868bb4edb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:20:03.681926Z","signature_b64":"Y5c7VgWFeyqW4Lqx/MBhzpXd87HmtGuIgaAsW2neMzGJ/Mcs1O6gmHhSSDvfkyCiOeZg4/mSXNQEAOwV1hWDAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38bee47a1fbe7b22eb9da6ad20cd0642aaa4f76954b68c3cb058e610d743ff15","last_reissued_at":"2026-07-05T00:20:03.681385Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:20:03.681385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Graph Autoencoder Approach to Causal Structure Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ignavier Ng, Shengyu Zhu, Zhitang Chen, Zhuangyan Fang","submitted_at":"2019-11-18T04:22:00Z","abstract_excerpt":"Causal structure learning has been a challenging task in the past decades and several mainstream approaches such as constraint- and score-based methods have been studied with theoretical guarantees. Recently, a new approach has transformed the combinatorial structure learning problem into a continuous one and then solved it using gradient-based optimization methods. Following the recent state-of-the-arts, we propose a new gradient-based method to learn causal structures from observational data. The proposed method generalizes the recent gradient-based methods to a graph autoencoder framework t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.07420","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/1911.07420/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":"1911.07420","created_at":"2026-07-05T00:20:03.681450+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.07420v1","created_at":"2026-07-05T00:20:03.681450+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.07420","created_at":"2026-07-05T00:20:03.681450+00:00"},{"alias_kind":"pith_short_12","alias_value":"HC7OI6Q7XZ5S","created_at":"2026-07-05T00:20:03.681450+00:00"},{"alias_kind":"pith_short_16","alias_value":"HC7OI6Q7XZ5SF245","created_at":"2026-07-05T00:20:03.681450+00:00"},{"alias_kind":"pith_short_8","alias_value":"HC7OI6Q7","created_at":"2026-07-05T00:20:03.681450+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.03045","citing_title":"TCD-Arena: Assessing Robustness of Time Series Causal Discovery Methods Against Assumption Violations","ref_index":232,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HC7OI6Q7XZ5SF245U2WSBTIGIK","json":"https://pith.science/pith/HC7OI6Q7XZ5SF245U2WSBTIGIK.json","graph_json":"https://pith.science/api/pith-number/HC7OI6Q7XZ5SF245U2WSBTIGIK/graph.json","events_json":"https://pith.science/api/pith-number/HC7OI6Q7XZ5SF245U2WSBTIGIK/events.json","paper":"https://pith.science/paper/HC7OI6Q7"},"agent_actions":{"view_html":"https://pith.science/pith/HC7OI6Q7XZ5SF245U2WSBTIGIK","download_json":"https://pith.science/pith/HC7OI6Q7XZ5SF245U2WSBTIGIK.json","view_paper":"https://pith.science/paper/HC7OI6Q7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.07420&json=true","fetch_graph":"https://pith.science/api/pith-number/HC7OI6Q7XZ5SF245U2WSBTIGIK/graph.json","fetch_events":"https://pith.science/api/pith-number/HC7OI6Q7XZ5SF245U2WSBTIGIK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HC7OI6Q7XZ5SF245U2WSBTIGIK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HC7OI6Q7XZ5SF245U2WSBTIGIK/action/storage_attestation","attest_author":"https://pith.science/pith/HC7OI6Q7XZ5SF245U2WSBTIGIK/action/author_attestation","sign_citation":"https://pith.science/pith/HC7OI6Q7XZ5SF245U2WSBTIGIK/action/citation_signature","submit_replication":"https://pith.science/pith/HC7OI6Q7XZ5SF245U2WSBTIGIK/action/replication_record"}},"created_at":"2026-07-05T00:20:03.681450+00:00","updated_at":"2026-07-05T00:20:03.681450+00:00"}