{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UITG3DLHTTG4IRMOTABG3NU7YA","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":"dddee4b9a2d5a6380a607e47ae8242353a8c90c3e0c16ea900f009f64a804888","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-08T00:48:29Z","title_canon_sha256":"40c6412ca8ae09a72b1f8223148d62ed24a299bd4c477c5b85fcbe5e0804304c"},"schema_version":"1.0","source":{"id":"2504.05585","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.05585","created_at":"2026-07-05T11:07:23Z"},{"alias_kind":"arxiv_version","alias_value":"2504.05585v2","created_at":"2026-07-05T11:07:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.05585","created_at":"2026-07-05T11:07:23Z"},{"alias_kind":"pith_short_12","alias_value":"UITG3DLHTTG4","created_at":"2026-07-05T11:07:23Z"},{"alias_kind":"pith_short_16","alias_value":"UITG3DLHTTG4IRMO","created_at":"2026-07-05T11:07:23Z"},{"alias_kind":"pith_short_8","alias_value":"UITG3DLH","created_at":"2026-07-05T11:07:23Z"}],"graph_snapshots":[{"event_id":"sha256:55fdc97bf41758aa5bb3c29538b2f4338c67f321d4327874ed404d2c9a64b896","target":"graph","created_at":"2026-07-05T11:07:23Z","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/2504.05585/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Episodic tasks in Reinforcement Learning (RL) often pose challenges due to sparse reward signals and high-dimensional state spaces, which hinder efficient learning. Additionally, these tasks often feature hidden \"trap states\" -- irreversible failures that prevent task completion but do not provide explicit negative rewards to guide agents away from repeated errors. To address these issues, we propose Time-Weighted Contrastive Reward Learning (TW-CRL), an Inverse Reinforcement Learning (IRL) framework that leverages both successful and failed demonstrations. By incorporating temporal informatio","authors_text":"Ning Yang, Stephen Xia, Yicheng Gao, Yuxuan Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-08T00:48:29Z","title":"TW-CRL: Time-Weighted Contrastive Reward Learning for Efficient Inverse Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.05585","kind":"arxiv","version":2},"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":"sha256:4dac6dcd91fb85a2e1f8909063f640a9a413b439c24a94cba19a611f6f22b6af","target":"record","created_at":"2026-07-05T11:07:23Z","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":"dddee4b9a2d5a6380a607e47ae8242353a8c90c3e0c16ea900f009f64a804888","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-08T00:48:29Z","title_canon_sha256":"40c6412ca8ae09a72b1f8223148d62ed24a299bd4c477c5b85fcbe5e0804304c"},"schema_version":"1.0","source":{"id":"2504.05585","kind":"arxiv","version":2}},"canonical_sha256":"a2266d8d679ccdc4458e98026db69fc0267cd348d5e3311a78fac27722fe192d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a2266d8d679ccdc4458e98026db69fc0267cd348d5e3311a78fac27722fe192d","first_computed_at":"2026-07-05T11:07:23.336346Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:23.336346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5NhTlRd9LDSWYGokn8BpuhNTlmqPWmIfn/XvvJl+tvvd9/BCWS9P53wmO4vc+aVbY4qEL32ZW5dlXauWSaWHBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:23.336833Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.05585","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4dac6dcd91fb85a2e1f8909063f640a9a413b439c24a94cba19a611f6f22b6af","sha256:55fdc97bf41758aa5bb3c29538b2f4338c67f321d4327874ed404d2c9a64b896"],"state_sha256":"0208f4823843d153c9c129a8671ed09b660a6cc4ec031763f9cb1ce5d477f46c"}