{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZGJJAKLE5P36MF2ZN45HR3Z34F","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":"20c9d29a744e9a2615f75e0844616aaf37c1b927b763fa50dcbe58e347a1160a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-30T07:03:14Z","title_canon_sha256":"757f8349913194cf6e315f0fb4fbc75b1a783c063fa1a065a78d27abf55d6a50"},"schema_version":"1.0","source":{"id":"2310.19308","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.19308","created_at":"2026-07-05T07:19:23Z"},{"alias_kind":"arxiv_version","alias_value":"2310.19308v2","created_at":"2026-07-05T07:19:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.19308","created_at":"2026-07-05T07:19:23Z"},{"alias_kind":"pith_short_12","alias_value":"ZGJJAKLE5P36","created_at":"2026-07-05T07:19:23Z"},{"alias_kind":"pith_short_16","alias_value":"ZGJJAKLE5P36MF2Z","created_at":"2026-07-05T07:19:23Z"},{"alias_kind":"pith_short_8","alias_value":"ZGJJAKLE","created_at":"2026-07-05T07:19:23Z"}],"graph_snapshots":[{"event_id":"sha256:989c7f5d652f83c6235e6822d60b3ca6aa4d94e7432e6486a4253e8a1d7ab184","target":"graph","created_at":"2026-07-05T07:19:23Z","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/2310.19308/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Off-policy dynamic programming (DP) techniques such as $Q$-learning have proven to be important in sequential decision-making problems. In the presence of function approximation, however, these techniques often diverge due to the absence of Bellman completeness in the function classes considered, a crucial condition for the success of DP-based methods. In this paper, we show how off-policy learning techniques based on return-conditioned supervised learning (RCSL) are able to circumvent these challenges of Bellman completeness, converging under significantly more relaxed assumptions inherited f","authors_text":"Abhishek Gupta, Chuning Zhu, Qiwen Cui, Runlong Zhou, Simon Shaolei Du, Zhaoyi Zhou","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-30T07:03:14Z","title":"Free from Bellman Completeness: Trajectory Stitching via Model-based Return-conditioned Supervised Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.19308","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:a1f3b20fbc070984597ff9e66f52a73cdc2bb4fad8e4a57f9c54385c89b9eb54","target":"record","created_at":"2026-07-05T07:19:23Z","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":"20c9d29a744e9a2615f75e0844616aaf37c1b927b763fa50dcbe58e347a1160a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-30T07:03:14Z","title_canon_sha256":"757f8349913194cf6e315f0fb4fbc75b1a783c063fa1a065a78d27abf55d6a50"},"schema_version":"1.0","source":{"id":"2310.19308","kind":"arxiv","version":2}},"canonical_sha256":"c992902964ebf7e617596f3a78ef3be1766012d8e63b16233f142f671b068cce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c992902964ebf7e617596f3a78ef3be1766012d8e63b16233f142f671b068cce","first_computed_at":"2026-07-05T07:19:23.332803Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:19:23.332803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f8jvfWyhUDAfnm0WGstK9fY8Gqt9qEkB0OsflhEYTgnOZzazdqPhkL85a2F39QuVmj2DpdX5uu09JzOHHk0RCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:19:23.333420Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.19308","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a1f3b20fbc070984597ff9e66f52a73cdc2bb4fad8e4a57f9c54385c89b9eb54","sha256:989c7f5d652f83c6235e6822d60b3ca6aa4d94e7432e6486a4253e8a1d7ab184"],"state_sha256":"2de9b418a718356e4620aa3202728eebc938768d607e15f8cb44a6b8021499d0"}