{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5P3OVO6MWU7XIKZPC6HXOSNVIE","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":"1c2216ce4ff9e7a18403a533d5e5ee44e97f5832eeeadf3dba979c331de986e3","cross_cats_sorted":["cs.FL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-06-23T18:42:27Z","title_canon_sha256":"82056543290c7c218794457833244b0346093cdbb83b0d717f21e21c27540868"},"schema_version":"1.0","source":{"id":"2306.13732","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.13732","created_at":"2026-07-05T06:24:14Z"},{"alias_kind":"arxiv_version","alias_value":"2306.13732v1","created_at":"2026-07-05T06:24:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.13732","created_at":"2026-07-05T06:24:14Z"},{"alias_kind":"pith_short_12","alias_value":"5P3OVO6MWU7X","created_at":"2026-07-05T06:24:14Z"},{"alias_kind":"pith_short_16","alias_value":"5P3OVO6MWU7XIKZP","created_at":"2026-07-05T06:24:14Z"},{"alias_kind":"pith_short_8","alias_value":"5P3OVO6M","created_at":"2026-07-05T06:24:14Z"}],"graph_snapshots":[{"event_id":"sha256:0387830295852b289bf8efb644678fa466435a5fa715eb0d44efa560eb20d221","target":"graph","created_at":"2026-07-05T06:24:14Z","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/2306.13732/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study a class of reinforcement learning (RL) tasks where the objective of the agent is to accomplish temporally extended goals. In this setting, a common approach is to represent the tasks as deterministic finite automata (DFA) and integrate them into the state-space for RL algorithms. However, while these machines model the reward function, they often overlook the causal knowledge about the environment. To address this limitation, we propose the Temporal-Logic-based Causal Diagram (TL-CD) in RL, which captures the temporal causal relationships between different properties of the environmen","authors_text":"Daniel Neider, Jean-Rapha\\\"el Gaglione, Nasim Baharisangari, Rajarshi Roy, Ufuk Topcu, Xiaoming Duan, Yash Paliwal, Zhe Xu","cross_cats":["cs.FL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-06-23T18:42:27Z","title":"Reinforcement Learning with Temporal-Logic-Based Causal Diagrams"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.13732","kind":"arxiv","version":1},"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:cfa33ceafeb3dbe2716b8820700d20e4d34de41fc89cecf5fa5b53daf7609f9f","target":"record","created_at":"2026-07-05T06:24:14Z","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":"1c2216ce4ff9e7a18403a533d5e5ee44e97f5832eeeadf3dba979c331de986e3","cross_cats_sorted":["cs.FL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-06-23T18:42:27Z","title_canon_sha256":"82056543290c7c218794457833244b0346093cdbb83b0d717f21e21c27540868"},"schema_version":"1.0","source":{"id":"2306.13732","kind":"arxiv","version":1}},"canonical_sha256":"ebf6eabbccb53f742b2f178f7749b54123f3dbbe6ffd3d251681361aea010307","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ebf6eabbccb53f742b2f178f7749b54123f3dbbe6ffd3d251681361aea010307","first_computed_at":"2026-07-05T06:24:14.674441Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:24:14.674441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"603nka8SlYdDWmPJ9V+0LdGjK2lr1NnbpGqBQKpLrwyTPmf4wZDKwhS6PQLZ38ntYaC8lecz6xZrEW2pF/WlBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:24:14.674882Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.13732","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cfa33ceafeb3dbe2716b8820700d20e4d34de41fc89cecf5fa5b53daf7609f9f","sha256:0387830295852b289bf8efb644678fa466435a5fa715eb0d44efa560eb20d221"],"state_sha256":"7681be54b966dd91634db9acd18df91b7d474c8f23092ce25c907792d1d37835"}