{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:7SJV2NI5BOJP4Q5Z2V7DZR4S3A","short_pith_number":"pith:7SJV2NI5","canonical_record":{"source":{"id":"2309.05915","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-12T02:05:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0974ff1da01b0f8ea99646377c7dae1fd5a68f2dc1d2da1bf381358daac4f535","abstract_canon_sha256":"e163e4196c9e3272d07d4e9f738f04c8d542a6650d8511e6d938fd5e08a31d67"},"schema_version":"1.0"},"canonical_sha256":"fc935d351d0b92fe43b9d57e3cc792d83872c02ea7ab18712aedf976970a2fba","source":{"kind":"arxiv","id":"2309.05915","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.05915","created_at":"2026-07-05T08:35:36Z"},{"alias_kind":"arxiv_version","alias_value":"2309.05915v2","created_at":"2026-07-05T08:35:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.05915","created_at":"2026-07-05T08:35:36Z"},{"alias_kind":"pith_short_12","alias_value":"7SJV2NI5BOJP","created_at":"2026-07-05T08:35:36Z"},{"alias_kind":"pith_short_16","alias_value":"7SJV2NI5BOJP4Q5Z","created_at":"2026-07-05T08:35:36Z"},{"alias_kind":"pith_short_8","alias_value":"7SJV2NI5","created_at":"2026-07-05T08:35:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:7SJV2NI5BOJP4Q5Z2V7DZR4S3A","target":"record","payload":{"canonical_record":{"source":{"id":"2309.05915","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-12T02:05:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0974ff1da01b0f8ea99646377c7dae1fd5a68f2dc1d2da1bf381358daac4f535","abstract_canon_sha256":"e163e4196c9e3272d07d4e9f738f04c8d542a6650d8511e6d938fd5e08a31d67"},"schema_version":"1.0"},"canonical_sha256":"fc935d351d0b92fe43b9d57e3cc792d83872c02ea7ab18712aedf976970a2fba","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:36.783126Z","signature_b64":"7aYYemq83/nCjYfXD2FgNFRRwODQ3/xXf1RHzBJ4tRjWexkd0HM/mxVbeQmELkhSPPsIG0Njt0HAyo4yA7BeAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc935d351d0b92fe43b9d57e3cc792d83872c02ea7ab18712aedf976970a2fba","last_reissued_at":"2026-07-05T08:35:36.782696Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:36.782696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.05915","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:35:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1BpdD6w29dnVy8MEt8ankS/ysFDViGxZraU47wFEk0HNHVaa1DY2IhDHsjK0rkVJMy0sr2E0cO3RmHBEeBpMBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T01:26:07.385652Z"},"content_sha256":"a08852dfa4f99ae221d1f00e6e99ee0e111ee890a23f455c66396bb2eeb88d99","schema_version":"1.0","event_id":"sha256:a08852dfa4f99ae221d1f00e6e99ee0e111ee890a23f455c66396bb2eeb88d99"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:7SJV2NI5BOJP4Q5Z2V7DZR4S3A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ACT: Empowering Decision Transformer with Dynamic Programming via Advantage Conditioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chen-Xiao Gao, Chenyang Wu, Mingjun Cao, Rui Kong, Yang Yu, Zongzhang Zhang","submitted_at":"2023-09-12T02:05:43Z","abstract_excerpt":"Decision Transformer (DT), which employs expressive sequence modeling techniques to perform action generation, has emerged as a promising approach to offline policy optimization. However, DT generates actions conditioned on a desired future return, which is known to bear some weaknesses such as the susceptibility to environmental stochasticity. To overcome DT's weaknesses, we propose to empower DT with dynamic programming. Our method comprises three steps. First, we employ in-sample value iteration to obtain approximated value functions, which involves dynamic programming over the MDP structur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.05915","kind":"arxiv","version":2},"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/2309.05915/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":"2026-07-05T08:35:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MZ8dmEJHG6ACn5s9AhHmpe9CR39YpHzkiiskyNWIH5XfCviyoCP2vQQWc/W/KFRoz44zh2v8RfAy/Y87WUHuBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T01:26:07.386223Z"},"content_sha256":"7f05251fa87c5b70b4994dae250547712ee0d97c5c94de86ea4f027a97ab8035","schema_version":"1.0","event_id":"sha256:7f05251fa87c5b70b4994dae250547712ee0d97c5c94de86ea4f027a97ab8035"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7SJV2NI5BOJP4Q5Z2V7DZR4S3A/bundle.json","state_url":"https://pith.science/pith/7SJV2NI5BOJP4Q5Z2V7DZR4S3A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7SJV2NI5BOJP4Q5Z2V7DZR4S3A/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":"2026-08-24T01:26:07Z","links":{"resolver":"https://pith.science/pith/7SJV2NI5BOJP4Q5Z2V7DZR4S3A","bundle":"https://pith.science/pith/7SJV2NI5BOJP4Q5Z2V7DZR4S3A/bundle.json","state":"https://pith.science/pith/7SJV2NI5BOJP4Q5Z2V7DZR4S3A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7SJV2NI5BOJP4Q5Z2V7DZR4S3A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7SJV2NI5BOJP4Q5Z2V7DZR4S3A","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":"e163e4196c9e3272d07d4e9f738f04c8d542a6650d8511e6d938fd5e08a31d67","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-12T02:05:43Z","title_canon_sha256":"0974ff1da01b0f8ea99646377c7dae1fd5a68f2dc1d2da1bf381358daac4f535"},"schema_version":"1.0","source":{"id":"2309.05915","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.05915","created_at":"2026-07-05T08:35:36Z"},{"alias_kind":"arxiv_version","alias_value":"2309.05915v2","created_at":"2026-07-05T08:35:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.05915","created_at":"2026-07-05T08:35:36Z"},{"alias_kind":"pith_short_12","alias_value":"7SJV2NI5BOJP","created_at":"2026-07-05T08:35:36Z"},{"alias_kind":"pith_short_16","alias_value":"7SJV2NI5BOJP4Q5Z","created_at":"2026-07-05T08:35:36Z"},{"alias_kind":"pith_short_8","alias_value":"7SJV2NI5","created_at":"2026-07-05T08:35:36Z"}],"graph_snapshots":[{"event_id":"sha256:7f05251fa87c5b70b4994dae250547712ee0d97c5c94de86ea4f027a97ab8035","target":"graph","created_at":"2026-07-05T08:35:36Z","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/2309.05915/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Decision Transformer (DT), which employs expressive sequence modeling techniques to perform action generation, has emerged as a promising approach to offline policy optimization. However, DT generates actions conditioned on a desired future return, which is known to bear some weaknesses such as the susceptibility to environmental stochasticity. To overcome DT's weaknesses, we propose to empower DT with dynamic programming. Our method comprises three steps. First, we employ in-sample value iteration to obtain approximated value functions, which involves dynamic programming over the MDP structur","authors_text":"Chen-Xiao Gao, Chenyang Wu, Mingjun Cao, Rui Kong, Yang Yu, Zongzhang Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-12T02:05:43Z","title":"ACT: Empowering Decision Transformer with Dynamic Programming via Advantage Conditioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.05915","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:a08852dfa4f99ae221d1f00e6e99ee0e111ee890a23f455c66396bb2eeb88d99","target":"record","created_at":"2026-07-05T08:35:36Z","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":"e163e4196c9e3272d07d4e9f738f04c8d542a6650d8511e6d938fd5e08a31d67","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-12T02:05:43Z","title_canon_sha256":"0974ff1da01b0f8ea99646377c7dae1fd5a68f2dc1d2da1bf381358daac4f535"},"schema_version":"1.0","source":{"id":"2309.05915","kind":"arxiv","version":2}},"canonical_sha256":"fc935d351d0b92fe43b9d57e3cc792d83872c02ea7ab18712aedf976970a2fba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc935d351d0b92fe43b9d57e3cc792d83872c02ea7ab18712aedf976970a2fba","first_computed_at":"2026-07-05T08:35:36.782696Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:35:36.782696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7aYYemq83/nCjYfXD2FgNFRRwODQ3/xXf1RHzBJ4tRjWexkd0HM/mxVbeQmELkhSPPsIG0Njt0HAyo4yA7BeAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:35:36.783126Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.05915","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a08852dfa4f99ae221d1f00e6e99ee0e111ee890a23f455c66396bb2eeb88d99","sha256:7f05251fa87c5b70b4994dae250547712ee0d97c5c94de86ea4f027a97ab8035"],"state_sha256":"257c29f1f850b27412327fce993a4052a8ff9e22311ecdf9d914a19901206358"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rlUEzIQ4KabCyu6tD+l//asLu9HUXJi1YT9dQK2jhwoxL6qOLO8RcgWt82jxKivBSRYNeQVxcz4aPsQFqJp+Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-24T01:26:07.391521Z","bundle_sha256":"43c9bbfb3565c92a7b8c6e7b0cae9532ffe78ebe7939039d3bde88cb9e5dd1a4"}}