{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OQNC5CTSARRN3LUKVT5NLBNBMP","short_pith_number":"pith:OQNC5CTS","canonical_record":{"source":{"id":"2506.00795","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-01T02:49:26Z","cross_cats_sorted":[],"title_canon_sha256":"0e7fd0f0d35b30a8f9c541223603a097b4bab13d37635e2a39279da87f286319","abstract_canon_sha256":"c4f33caff0c147cf0c4c907866ad6dddebd3df66e2175085f2291ca6af822d97"},"schema_version":"1.0"},"canonical_sha256":"741a2e8a720462ddae8aacfad585a163d76be17a91f9e42050ad19d333541217","source":{"kind":"arxiv","id":"2506.00795","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00795","created_at":"2026-07-05T12:09:19Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00795v3","created_at":"2026-07-05T12:09:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00795","created_at":"2026-07-05T12:09:19Z"},{"alias_kind":"pith_short_12","alias_value":"OQNC5CTSARRN","created_at":"2026-07-05T12:09:19Z"},{"alias_kind":"pith_short_16","alias_value":"OQNC5CTSARRN3LUK","created_at":"2026-07-05T12:09:19Z"},{"alias_kind":"pith_short_8","alias_value":"OQNC5CTS","created_at":"2026-07-05T12:09:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OQNC5CTSARRN3LUKVT5NLBNBMP","target":"record","payload":{"canonical_record":{"source":{"id":"2506.00795","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-01T02:49:26Z","cross_cats_sorted":[],"title_canon_sha256":"0e7fd0f0d35b30a8f9c541223603a097b4bab13d37635e2a39279da87f286319","abstract_canon_sha256":"c4f33caff0c147cf0c4c907866ad6dddebd3df66e2175085f2291ca6af822d97"},"schema_version":"1.0"},"canonical_sha256":"741a2e8a720462ddae8aacfad585a163d76be17a91f9e42050ad19d333541217","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:19.899463Z","signature_b64":"NyXhxGhx+1++wAMt0y7T7inX/TxJmxNhZFMqw39oHVyrRFcWBaXwd1NU4yPWiw4bJkowdf4yiOPP2mW6BE5nAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"741a2e8a720462ddae8aacfad585a163d76be17a91f9e42050ad19d333541217","last_reissued_at":"2026-07-05T12:09:19.898969Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:19.898969Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.00795","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:09:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qDMYH92zK3SuR8X5PVP4jWHO2mItEKJGr8ItqOIdQvdgHcls7p4Qs5PEWNpwovWO2tWxkQTHP/HQwWjJvJ5eBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:17:45.827462Z"},"content_sha256":"38b060c5a379a122df2faf7c54db31ca5f31cdea2ae0dac8912a0fbf4b8d6f69","schema_version":"1.0","event_id":"sha256:38b060c5a379a122df2faf7c54db31ca5f31cdea2ae0dac8912a0fbf4b8d6f69"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OQNC5CTSARRN3LUKVT5NLBNBMP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Closing the Gap between TD Learning and Supervised Learning with $Q$-Conditioned Maximization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Donglin Wang, Fei Shen, Sheng Xu, Shentao Yang, Wenyan Yang, Xing Lei, Xuetao Zhang, Yunhao Luo, Zifeng Zhuang","submitted_at":"2025-06-01T02:49:26Z","abstract_excerpt":"Recently, supervised learning (SL) methodology has emerged as an effective approach for offline reinforcement learning (RL) due to their simplicity, stability, and efficiency. However, recent studies show that SL methods lack the trajectory stitching capability, typically associated with temporal difference (TD)-based approaches. A question naturally surfaces: \\textit{How can we endow SL methods with stitching capability and close its performance gap with TD learning?} To answer this question, we introduce $Q$-conditioned maximization supervised learning for offline goal-conditioned RL, which "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00795","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.00795/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:09:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F9XoBhcR0f7oc5jyJG3pMJHVGsHf/udpyvhfbtU+hbdts26r6kW2VAct5OUge5Z1Zt0LmNJaTxLRyAbUi/gAAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:17:45.827844Z"},"content_sha256":"f102b17be6760c093a2ebe998f94a0220f4b91b3ff5d27d8eba6be00126cccb2","schema_version":"1.0","event_id":"sha256:f102b17be6760c093a2ebe998f94a0220f4b91b3ff5d27d8eba6be00126cccb2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OQNC5CTSARRN3LUKVT5NLBNBMP/bundle.json","state_url":"https://pith.science/pith/OQNC5CTSARRN3LUKVT5NLBNBMP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OQNC5CTSARRN3LUKVT5NLBNBMP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T19:17:45Z","links":{"resolver":"https://pith.science/pith/OQNC5CTSARRN3LUKVT5NLBNBMP","bundle":"https://pith.science/pith/OQNC5CTSARRN3LUKVT5NLBNBMP/bundle.json","state":"https://pith.science/pith/OQNC5CTSARRN3LUKVT5NLBNBMP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OQNC5CTSARRN3LUKVT5NLBNBMP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OQNC5CTSARRN3LUKVT5NLBNBMP","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":"c4f33caff0c147cf0c4c907866ad6dddebd3df66e2175085f2291ca6af822d97","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-01T02:49:26Z","title_canon_sha256":"0e7fd0f0d35b30a8f9c541223603a097b4bab13d37635e2a39279da87f286319"},"schema_version":"1.0","source":{"id":"2506.00795","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00795","created_at":"2026-07-05T12:09:19Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00795v3","created_at":"2026-07-05T12:09:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00795","created_at":"2026-07-05T12:09:19Z"},{"alias_kind":"pith_short_12","alias_value":"OQNC5CTSARRN","created_at":"2026-07-05T12:09:19Z"},{"alias_kind":"pith_short_16","alias_value":"OQNC5CTSARRN3LUK","created_at":"2026-07-05T12:09:19Z"},{"alias_kind":"pith_short_8","alias_value":"OQNC5CTS","created_at":"2026-07-05T12:09:19Z"}],"graph_snapshots":[{"event_id":"sha256:f102b17be6760c093a2ebe998f94a0220f4b91b3ff5d27d8eba6be00126cccb2","target":"graph","created_at":"2026-07-05T12:09:19Z","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/2506.00795/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, supervised learning (SL) methodology has emerged as an effective approach for offline reinforcement learning (RL) due to their simplicity, stability, and efficiency. However, recent studies show that SL methods lack the trajectory stitching capability, typically associated with temporal difference (TD)-based approaches. A question naturally surfaces: \\textit{How can we endow SL methods with stitching capability and close its performance gap with TD learning?} To answer this question, we introduce $Q$-conditioned maximization supervised learning for offline goal-conditioned RL, which ","authors_text":"Donglin Wang, Fei Shen, Sheng Xu, Shentao Yang, Wenyan Yang, Xing Lei, Xuetao Zhang, Yunhao Luo, Zifeng Zhuang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-01T02:49:26Z","title":"Closing the Gap between TD Learning and Supervised Learning with $Q$-Conditioned Maximization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00795","kind":"arxiv","version":3},"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":"sha256:38b060c5a379a122df2faf7c54db31ca5f31cdea2ae0dac8912a0fbf4b8d6f69","target":"record","created_at":"2026-07-05T12:09:19Z","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":"c4f33caff0c147cf0c4c907866ad6dddebd3df66e2175085f2291ca6af822d97","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-01T02:49:26Z","title_canon_sha256":"0e7fd0f0d35b30a8f9c541223603a097b4bab13d37635e2a39279da87f286319"},"schema_version":"1.0","source":{"id":"2506.00795","kind":"arxiv","version":3}},"canonical_sha256":"741a2e8a720462ddae8aacfad585a163d76be17a91f9e42050ad19d333541217","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"741a2e8a720462ddae8aacfad585a163d76be17a91f9e42050ad19d333541217","first_computed_at":"2026-07-05T12:09:19.898969Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:09:19.898969Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NyXhxGhx+1++wAMt0y7T7inX/TxJmxNhZFMqw39oHVyrRFcWBaXwd1NU4yPWiw4bJkowdf4yiOPP2mW6BE5nAw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:09:19.899463Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00795","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:38b060c5a379a122df2faf7c54db31ca5f31cdea2ae0dac8912a0fbf4b8d6f69","sha256:f102b17be6760c093a2ebe998f94a0220f4b91b3ff5d27d8eba6be00126cccb2"],"state_sha256":"cd634fe6ffc630edffdfbf488b2e149ecfa346cbcb384ee36cc887c44d25b6a1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s1YJXuKMDyCS+LnHNdWBPplf+ck3RO+jacfZl87mTN/CsE6RA5QZz2ast7hycWC0mLNtjLdI0kdhjQlBEcFsCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T19:17:45.830686Z","bundle_sha256":"658a1b77046ca3759b7a714b1b24c51edf8789335b00ca92923af1e805dbe79f"}}