{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:I3SEJOXOWCT6KZI4VAQRNRCG2J","short_pith_number":"pith:I3SEJOXO","canonical_record":{"source":{"id":"2312.13716","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-21T10:29:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"128198eb345e10bcd9870cfb46ef5dc360b775523ab1d32ba3b29bbf91c6c824","abstract_canon_sha256":"f0703d971c2f1be4308146fadd3905f8f7dae9b540a0db67c88e1e051cc7d45a"},"schema_version":"1.0"},"canonical_sha256":"46e444baeeb0a7e5651ca82116c446d27b857af898ec6108588195c4667cae47","source":{"kind":"arxiv","id":"2312.13716","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.13716","created_at":"2026-07-05T07:26:48Z"},{"alias_kind":"arxiv_version","alias_value":"2312.13716v1","created_at":"2026-07-05T07:26:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.13716","created_at":"2026-07-05T07:26:48Z"},{"alias_kind":"pith_short_12","alias_value":"I3SEJOXOWCT6","created_at":"2026-07-05T07:26:48Z"},{"alias_kind":"pith_short_16","alias_value":"I3SEJOXOWCT6KZI4","created_at":"2026-07-05T07:26:48Z"},{"alias_kind":"pith_short_8","alias_value":"I3SEJOXO","created_at":"2026-07-05T07:26:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:I3SEJOXOWCT6KZI4VAQRNRCG2J","target":"record","payload":{"canonical_record":{"source":{"id":"2312.13716","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-21T10:29:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"128198eb345e10bcd9870cfb46ef5dc360b775523ab1d32ba3b29bbf91c6c824","abstract_canon_sha256":"f0703d971c2f1be4308146fadd3905f8f7dae9b540a0db67c88e1e051cc7d45a"},"schema_version":"1.0"},"canonical_sha256":"46e444baeeb0a7e5651ca82116c446d27b857af898ec6108588195c4667cae47","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:26:48.767039Z","signature_b64":"g7UhQweu2G5DKj6F+T++M/YgwXu0TIQfXlJE4jg0CcHYvTaT3ciCCBua0QrmaK4tJgXcQ/hMy6/EyB7zQKXgDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46e444baeeb0a7e5651ca82116c446d27b857af898ec6108588195c4667cae47","last_reissued_at":"2026-07-05T07:26:48.766606Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:26:48.766606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.13716","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:26:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ivBkNtVqpXz90MX4lAcWs++eILRU6QhsFSnzBBqEKHDo6xkvvpzDiKYPGoJfoMfRW47c5r3LfIWBstqfshnQBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T07:59:27.696809Z"},"content_sha256":"1d5fd28b403d79d44fa2cc4b8abc79f304c31cf60372dcdd160c8e824d328091","schema_version":"1.0","event_id":"sha256:1d5fd28b403d79d44fa2cc4b8abc79f304c31cf60372dcdd160c8e824d328091"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:I3SEJOXOWCT6KZI4VAQRNRCG2J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Critic-Guided Decision Transformer for Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chao Yang, Ying Wen, Yuanfu Wang, Yu Liu, Yu Qiao","submitted_at":"2023-12-21T10:29:17Z","abstract_excerpt":"Recent advancements in offline reinforcement learning (RL) have underscored the capabilities of Return-Conditioned Supervised Learning (RCSL), a paradigm that learns the action distribution based on target returns for each state in a supervised manner. However, prevailing RCSL methods largely focus on deterministic trajectory modeling, disregarding stochastic state transitions and the diversity of future trajectory distributions. A fundamental challenge arises from the inconsistency between the sampled returns within individual trajectories and the expected returns across multiple trajectories"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.13716","kind":"arxiv","version":1},"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/2312.13716/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":"2026-07-05T07:26:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GDyEJtqd3TY5HLC2j2vqqQPqFg7L8MpGkZW5HYdcbloBfzwpDhwLF3jEmQQxaKX5BszlBwKQuZhNYARWkjqJBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T07:59:27.697289Z"},"content_sha256":"431bd22cbcefc0cce0dba4bd0ecb61ff3864061943e0abfc1002a59c6986eb6d","schema_version":"1.0","event_id":"sha256:431bd22cbcefc0cce0dba4bd0ecb61ff3864061943e0abfc1002a59c6986eb6d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I3SEJOXOWCT6KZI4VAQRNRCG2J/bundle.json","state_url":"https://pith.science/pith/I3SEJOXOWCT6KZI4VAQRNRCG2J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I3SEJOXOWCT6KZI4VAQRNRCG2J/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":"2026-08-01T07:59:27Z","links":{"resolver":"https://pith.science/pith/I3SEJOXOWCT6KZI4VAQRNRCG2J","bundle":"https://pith.science/pith/I3SEJOXOWCT6KZI4VAQRNRCG2J/bundle.json","state":"https://pith.science/pith/I3SEJOXOWCT6KZI4VAQRNRCG2J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I3SEJOXOWCT6KZI4VAQRNRCG2J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:I3SEJOXOWCT6KZI4VAQRNRCG2J","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":"f0703d971c2f1be4308146fadd3905f8f7dae9b540a0db67c88e1e051cc7d45a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-21T10:29:17Z","title_canon_sha256":"128198eb345e10bcd9870cfb46ef5dc360b775523ab1d32ba3b29bbf91c6c824"},"schema_version":"1.0","source":{"id":"2312.13716","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.13716","created_at":"2026-07-05T07:26:48Z"},{"alias_kind":"arxiv_version","alias_value":"2312.13716v1","created_at":"2026-07-05T07:26:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.13716","created_at":"2026-07-05T07:26:48Z"},{"alias_kind":"pith_short_12","alias_value":"I3SEJOXOWCT6","created_at":"2026-07-05T07:26:48Z"},{"alias_kind":"pith_short_16","alias_value":"I3SEJOXOWCT6KZI4","created_at":"2026-07-05T07:26:48Z"},{"alias_kind":"pith_short_8","alias_value":"I3SEJOXO","created_at":"2026-07-05T07:26:48Z"}],"graph_snapshots":[{"event_id":"sha256:431bd22cbcefc0cce0dba4bd0ecb61ff3864061943e0abfc1002a59c6986eb6d","target":"graph","created_at":"2026-07-05T07:26:48Z","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/2312.13716/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in offline reinforcement learning (RL) have underscored the capabilities of Return-Conditioned Supervised Learning (RCSL), a paradigm that learns the action distribution based on target returns for each state in a supervised manner. However, prevailing RCSL methods largely focus on deterministic trajectory modeling, disregarding stochastic state transitions and the diversity of future trajectory distributions. A fundamental challenge arises from the inconsistency between the sampled returns within individual trajectories and the expected returns across multiple trajectories","authors_text":"Chao Yang, Ying Wen, Yuanfu Wang, Yu Liu, Yu Qiao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-21T10:29:17Z","title":"Critic-Guided Decision Transformer for Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.13716","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":"sha256:1d5fd28b403d79d44fa2cc4b8abc79f304c31cf60372dcdd160c8e824d328091","target":"record","created_at":"2026-07-05T07:26:48Z","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":"f0703d971c2f1be4308146fadd3905f8f7dae9b540a0db67c88e1e051cc7d45a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-21T10:29:17Z","title_canon_sha256":"128198eb345e10bcd9870cfb46ef5dc360b775523ab1d32ba3b29bbf91c6c824"},"schema_version":"1.0","source":{"id":"2312.13716","kind":"arxiv","version":1}},"canonical_sha256":"46e444baeeb0a7e5651ca82116c446d27b857af898ec6108588195c4667cae47","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"46e444baeeb0a7e5651ca82116c446d27b857af898ec6108588195c4667cae47","first_computed_at":"2026-07-05T07:26:48.766606Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:26:48.766606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"g7UhQweu2G5DKj6F+T++M/YgwXu0TIQfXlJE4jg0CcHYvTaT3ciCCBua0QrmaK4tJgXcQ/hMy6/EyB7zQKXgDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:26:48.767039Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.13716","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d5fd28b403d79d44fa2cc4b8abc79f304c31cf60372dcdd160c8e824d328091","sha256:431bd22cbcefc0cce0dba4bd0ecb61ff3864061943e0abfc1002a59c6986eb6d"],"state_sha256":"2bd88494873f8852bba3923a55e32f74adc86ceceab1de9af17a8921c843fa27"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qQJBlCQMri1UjYPi1ile4Z0GbBT8sdIFb5pKV3WcE+syvdqR9T3wxoHNHmqjJp+3ru+juLnX5sN04yNwflWbBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T07:59:27.702816Z","bundle_sha256":"df5f0ab97d2da43df4e88c28f549b49a2e9ddc47141457811e0a463d1ac62cad"}}