{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:C5D3WE6GALG4PYUOXWL2ZTK734","short_pith_number":"pith:C5D3WE6G","schema_version":"1.0","canonical_sha256":"1747bb13c602cdc7e28ebd97accd5fdf2ff01a327321a781b14d5917ea8096a7","source":{"kind":"arxiv","id":"1906.04477","version":4},"attestation_state":"computed","paper":{"title":"Causal Discovery with Reinforcement 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","submitted_at":"2019-06-11T10:09:35Z","abstract_excerpt":"Discovering causal structure among a set of variables is a fundamental problem in many empirical sciences. Traditional score-based casual discovery methods rely on various local heuristics to search for a Directed Acyclic Graph (DAG) according to a predefined score function. While these methods, e.g., greedy equivalence search, may have attractive results with infinite samples and certain model assumptions, they are usually less satisfactory in practice due to finite data and possible violation of assumptions. Motivated by recent advances in neural combinatorial optimization, we propose to use"},"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":"1906.04477","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-11T10:09:35Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f42634023e46d78d79f480e1ee8925c49221a37d72087177344c6d88d03280c6","abstract_canon_sha256":"52917a49b96df1e222261576cbc61e653a0afcb4e7aef6b060c2a10230dabf61"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:08:23.786534Z","signature_b64":"+z0sdo3LPLEQ/e5E/KGm52inxMaTYOrPJlwme04dueNCZ3mP6HUUVpcSPWDUN6+/+Co7JXMka8m+7TU9FHy3BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1747bb13c602cdc7e28ebd97accd5fdf2ff01a327321a781b14d5917ea8096a7","last_reissued_at":"2026-07-05T01:08:23.786061Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:08:23.786061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Causal Discovery with Reinforcement 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","submitted_at":"2019-06-11T10:09:35Z","abstract_excerpt":"Discovering causal structure among a set of variables is a fundamental problem in many empirical sciences. Traditional score-based casual discovery methods rely on various local heuristics to search for a Directed Acyclic Graph (DAG) according to a predefined score function. While these methods, e.g., greedy equivalence search, may have attractive results with infinite samples and certain model assumptions, they are usually less satisfactory in practice due to finite data and possible violation of assumptions. Motivated by recent advances in neural combinatorial optimization, we propose to use"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.04477","kind":"arxiv","version":4},"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/1906.04477/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":"1906.04477","created_at":"2026-07-05T01:08:23.786124+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.04477v4","created_at":"2026-07-05T01:08:23.786124+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.04477","created_at":"2026-07-05T01:08:23.786124+00:00"},{"alias_kind":"pith_short_12","alias_value":"C5D3WE6GALG4","created_at":"2026-07-05T01:08:23.786124+00:00"},{"alias_kind":"pith_short_16","alias_value":"C5D3WE6GALG4PYUO","created_at":"2026-07-05T01:08:23.786124+00:00"},{"alias_kind":"pith_short_8","alias_value":"C5D3WE6G","created_at":"2026-07-05T01:08:23.786124+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06908","citing_title":"polyDAG: Polynomial Acyclicity Constraints for Efficient Continuous Causal Discovery in Visual Semantic Graphs","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03251","citing_title":"Do Real-World Datasets Contain Natural Experiments? An Empirical Study Using Causal Feature Selection","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2412.07469","citing_title":"Score-matching-based Structure Learning for Temporal Data on Networks","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18878","citing_title":"Prognostic Value of Lung Ultrasound Biomarkers for Readmission Risk in Congestive Heart Failure: A Pilot Data-Driven Analysis","ref_index":177,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17126","citing_title":"Multi-task Linear Regression without Eigenvalue Lower Bounds: Adaptivity, Robustness, and Safety","ref_index":106,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19313","citing_title":"A Unified Framework for Structure-Aware Clustering and Heterogeneous Causal Graph Learning","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03045","citing_title":"TCD-Arena: Assessing Robustness of Time Series Causal Discovery Methods Against Assumption Violations","ref_index":285,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C5D3WE6GALG4PYUOXWL2ZTK734","json":"https://pith.science/pith/C5D3WE6GALG4PYUOXWL2ZTK734.json","graph_json":"https://pith.science/api/pith-number/C5D3WE6GALG4PYUOXWL2ZTK734/graph.json","events_json":"https://pith.science/api/pith-number/C5D3WE6GALG4PYUOXWL2ZTK734/events.json","paper":"https://pith.science/paper/C5D3WE6G"},"agent_actions":{"view_html":"https://pith.science/pith/C5D3WE6GALG4PYUOXWL2ZTK734","download_json":"https://pith.science/pith/C5D3WE6GALG4PYUOXWL2ZTK734.json","view_paper":"https://pith.science/paper/C5D3WE6G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.04477&json=true","fetch_graph":"https://pith.science/api/pith-number/C5D3WE6GALG4PYUOXWL2ZTK734/graph.json","fetch_events":"https://pith.science/api/pith-number/C5D3WE6GALG4PYUOXWL2ZTK734/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C5D3WE6GALG4PYUOXWL2ZTK734/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C5D3WE6GALG4PYUOXWL2ZTK734/action/storage_attestation","attest_author":"https://pith.science/pith/C5D3WE6GALG4PYUOXWL2ZTK734/action/author_attestation","sign_citation":"https://pith.science/pith/C5D3WE6GALG4PYUOXWL2ZTK734/action/citation_signature","submit_replication":"https://pith.science/pith/C5D3WE6GALG4PYUOXWL2ZTK734/action/replication_record"}},"created_at":"2026-07-05T01:08:23.786124+00:00","updated_at":"2026-07-05T01:08:23.786124+00:00"}