{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:DZYL4VM6XMESHUZD6JOGOFPBXH","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ba9ce34741e7b6963c8de36d7e8116aa06b9493bd775feee9e0263d4c9544d8e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-14T03:49:59Z","title_canon_sha256":"bf0f102f67334a88a47948b646f2c8cac68c4f4a8c994c94d77123c34b2d8147"},"schema_version":"1.0","source":{"id":"2105.06631","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.06631","created_at":"2026-07-05T03:14:45Z"},{"alias_kind":"arxiv_version","alias_value":"2105.06631v4","created_at":"2026-07-05T03:14:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.06631","created_at":"2026-07-05T03:14:45Z"},{"alias_kind":"pith_short_12","alias_value":"DZYL4VM6XMES","created_at":"2026-07-05T03:14:45Z"},{"alias_kind":"pith_short_16","alias_value":"DZYL4VM6XMESHUZD","created_at":"2026-07-05T03:14:45Z"},{"alias_kind":"pith_short_8","alias_value":"DZYL4VM6","created_at":"2026-07-05T03:14:45Z"}],"graph_snapshots":[{"event_id":"sha256:bf9ed8e0734861bd08e636092b3c9f5d9656287d35d2f47b7e85bbd26f9e6cdf","target":"graph","created_at":"2026-07-05T03:14:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2105.06631/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"It is a long-standing question to discover causal relations among a set of variables in many empirical sciences. Recently, Reinforcement Learning (RL) has achieved promising results in causal discovery from observational data. However, searching the space of directed graphs and enforcing acyclicity by implicit penalties tend to be inefficient and restrict the existing RL-based method to small scale problems. In this work, we propose a novel RL-based approach for causal discovery, by incorporating RL into the ordering-based paradigm. Specifically, we formulate the ordering search problem as a m","authors_text":"Jianye Hao, Jun Wang, Liangjun Ke, Shengyu Zhu, Xiaoqiang Wang, Yali Du, Zhitang Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-14T03:49:59Z","title":"Ordering-Based Causal Discovery with Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.06631","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e8206a1cf2a7db092e1efefe01a3ad78e9278499f4c21cda2240cbd3523cbbd9","target":"record","created_at":"2026-07-05T03:14:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ba9ce34741e7b6963c8de36d7e8116aa06b9493bd775feee9e0263d4c9544d8e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-14T03:49:59Z","title_canon_sha256":"bf0f102f67334a88a47948b646f2c8cac68c4f4a8c994c94d77123c34b2d8147"},"schema_version":"1.0","source":{"id":"2105.06631","kind":"arxiv","version":4}},"canonical_sha256":"1e70be559ebb0923d323f25c6715e1b9c25e4488ecd83238c679863da535e0f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1e70be559ebb0923d323f25c6715e1b9c25e4488ecd83238c679863da535e0f7","first_computed_at":"2026-07-05T03:14:45.912552Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:14:45.912552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bqOOJx1KPnenTUFEzsbQAMEnLdkS/PgYcldnuw1N6MqCdiu1lLOTEMoiS22dSBdwwpSawVsK/gAHivnASzv+DA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:14:45.912973Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.06631","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e8206a1cf2a7db092e1efefe01a3ad78e9278499f4c21cda2240cbd3523cbbd9","sha256:bf9ed8e0734861bd08e636092b3c9f5d9656287d35d2f47b7e85bbd26f9e6cdf"],"state_sha256":"80a2d09e20afc4644eeb8db36f72868cfc836d2247dd7f68daf70c059e6765ba"}