{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:37WOZUNJSULFB7OZWD5AOZC7PU","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":"2d1531ab7ed42b9ac52855b4df6f560bb83cf3c9047a4967c004169a5be606c7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T19:24:35Z","title_canon_sha256":"4e265d3d93a65d1a9ea1676c27489efd68f92e68839442be613810ad8a1b4cde"},"schema_version":"1.0","source":{"id":"2605.29028","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29028","created_at":"2026-05-29T01:04:43Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29028v1","created_at":"2026-05-29T01:04:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29028","created_at":"2026-05-29T01:04:43Z"},{"alias_kind":"pith_short_12","alias_value":"37WOZUNJSULF","created_at":"2026-05-29T01:04:43Z"},{"alias_kind":"pith_short_16","alias_value":"37WOZUNJSULFB7OZ","created_at":"2026-05-29T01:04:43Z"},{"alias_kind":"pith_short_8","alias_value":"37WOZUNJ","created_at":"2026-05-29T01:04:43Z"}],"graph_snapshots":[{"event_id":"sha256:a95c1bf1d543ba93ced2057e62a90b0c11d4af139595b5384b4bd0f3ee928a0b","target":"graph","created_at":"2026-05-29T01:04:43Z","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/2605.29028/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Conditioned Sequence Models (CSMs) learn policies by treating return-to-go (RTG) as a control signal. However, existing CSMs often treat the RTGs as simple numerical inputs rather than aligning them with the performance of their policies. In this paper, we propose Q-ALIGN DT, a framework that enforces this alignment by ensuring the $Q$-value of the output policy is consistent with the input RTG. By leveraging a $Q$ function to provide dense guidance to CSMs and further fine-tuning it using an RTG-perturbation technique with the CSM, our method ensures that higher RTGs are consistently mapped t","authors_text":"Weitong Zhang, Yuxiao Yang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T19:24:35Z","title":"Return-to-Go Is More Than a Number: Q-Guided Alignment for Return-Conditioned Supervised Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29028","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":"sha256:9a68fb1f8c9e107083139b893b967ab018abeaccd33da24645f0451a41607775","target":"record","created_at":"2026-05-29T01:04:43Z","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":"2d1531ab7ed42b9ac52855b4df6f560bb83cf3c9047a4967c004169a5be606c7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T19:24:35Z","title_canon_sha256":"4e265d3d93a65d1a9ea1676c27489efd68f92e68839442be613810ad8a1b4cde"},"schema_version":"1.0","source":{"id":"2605.29028","kind":"arxiv","version":1}},"canonical_sha256":"dfececd1a9951650fdd9b0fa07645f7d13d7e635f0a07df9d16a931570a17ad7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dfececd1a9951650fdd9b0fa07645f7d13d7e635f0a07df9d16a931570a17ad7","first_computed_at":"2026-05-29T01:04:43.862629Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:04:43.862629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vPQe+5Sw2aHgOUuszhz3eItr/24gJwq0oYqAnANNrIqMrNNDnJ2OxTu6pX8Ep910Luo9qHr+2468M2XHqSEiBw==","signature_status":"signed_v1","signed_at":"2026-05-29T01:04:43.863084Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.29028","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a68fb1f8c9e107083139b893b967ab018abeaccd33da24645f0451a41607775","sha256:a95c1bf1d543ba93ced2057e62a90b0c11d4af139595b5384b4bd0f3ee928a0b"],"state_sha256":"befc6ca198809a664a70a148cb3cb5a10ac26d327f1999ace4cdcc5c00d974e8"}