{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:M2GG6BJFY453MCVVU5R56P3M7A","short_pith_number":"pith:M2GG6BJF","canonical_record":{"source":{"id":"2111.10364","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-19T18:56:13Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"a5176daff0a4bfa205c72dd6a7e09b9b8ba67f8417e3d73f6e14265342508389","abstract_canon_sha256":"2568b8a3e7f34c4fad0bb34d3e897be75b3973b28357fdc60a16231ac24dbc25"},"schema_version":"1.0"},"canonical_sha256":"668c6f0525c73bb60ab5a763df3f6cf82b6719bc5fa33621ab526d110aed10fa","source":{"kind":"arxiv","id":"2111.10364","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.10364","created_at":"2026-07-05T03:54:03Z"},{"alias_kind":"arxiv_version","alias_value":"2111.10364v3","created_at":"2026-07-05T03:54:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.10364","created_at":"2026-07-05T03:54:03Z"},{"alias_kind":"pith_short_12","alias_value":"M2GG6BJFY453","created_at":"2026-07-05T03:54:03Z"},{"alias_kind":"pith_short_16","alias_value":"M2GG6BJFY453MCVV","created_at":"2026-07-05T03:54:03Z"},{"alias_kind":"pith_short_8","alias_value":"M2GG6BJF","created_at":"2026-07-05T03:54:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:M2GG6BJFY453MCVVU5R56P3M7A","target":"record","payload":{"canonical_record":{"source":{"id":"2111.10364","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-19T18:56:13Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"a5176daff0a4bfa205c72dd6a7e09b9b8ba67f8417e3d73f6e14265342508389","abstract_canon_sha256":"2568b8a3e7f34c4fad0bb34d3e897be75b3973b28357fdc60a16231ac24dbc25"},"schema_version":"1.0"},"canonical_sha256":"668c6f0525c73bb60ab5a763df3f6cf82b6719bc5fa33621ab526d110aed10fa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:54:03.848143Z","signature_b64":"EsHMQuOPWWJwn8jlPSkNCCX0i4hsRCRq3Vz+QxZi0wbf5YZxwqlMOCnm4nAcDXF0UjKeX5+FXLL6UucCnoexAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"668c6f0525c73bb60ab5a763df3f6cf82b6719bc5fa33621ab526d110aed10fa","last_reissued_at":"2026-07-05T03:54:03.847685Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:54:03.847685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.10364","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":"2026-07-05T03:54:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AmIEnyUCBsrmSUNnerSl0Pk+CG/QNVCMwP9jpJ63sBn0vQg/EEdn6M1e4CqYPRy5/KI76ctq/aK4AfG4XciIBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:56:35.315735Z"},"content_sha256":"1afb639841f78284b2d99a6ffd100eccf6a69d381aa471f393fb082cea1f9e0a","schema_version":"1.0","event_id":"sha256:1afb639841f78284b2d99a6ffd100eccf6a69d381aa471f393fb082cea1f9e0a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:M2GG6BJFY453MCVVU5R56P3M7A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generalized Decision Transformer for Offline Hindsight Information Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hiroki Furuta, Shixiang Shane Gu, Yutaka Matsuo","submitted_at":"2021-11-19T18:56:13Z","abstract_excerpt":"How to extract as much learning signal from each trajectory data has been a key problem in reinforcement learning (RL), where sample inefficiency has posed serious challenges for practical applications. Recent works have shown that using expressive policy function approximators and conditioning on future trajectory information -- such as future states in hindsight experience replay or returns-to-go in Decision Transformer (DT) -- enables efficient learning of multi-task policies, where at times online RL is fully replaced by offline behavioral cloning, e.g. sequence modeling. We demonstrate th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.10364","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/2111.10364/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":"2026-07-05T03:54:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vocDShy6OkSTU1XInzr0p6DFVYMkrnxIqlr5f5ZCqY08p/AFTq1JLdA7lo/v+G/K3qCbJ/HMnOkDCrNSdCjsAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:56:35.317489Z"},"content_sha256":"24057f6f296784484b81622e8b9e43bedfa1d403131e23d5ef0d8bb5e31b93ae","schema_version":"1.0","event_id":"sha256:24057f6f296784484b81622e8b9e43bedfa1d403131e23d5ef0d8bb5e31b93ae"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M2GG6BJFY453MCVVU5R56P3M7A/bundle.json","state_url":"https://pith.science/pith/M2GG6BJFY453MCVVU5R56P3M7A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M2GG6BJFY453MCVVU5R56P3M7A/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":"2026-08-09T04:56:35Z","links":{"resolver":"https://pith.science/pith/M2GG6BJFY453MCVVU5R56P3M7A","bundle":"https://pith.science/pith/M2GG6BJFY453MCVVU5R56P3M7A/bundle.json","state":"https://pith.science/pith/M2GG6BJFY453MCVVU5R56P3M7A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M2GG6BJFY453MCVVU5R56P3M7A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:M2GG6BJFY453MCVVU5R56P3M7A","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":"2568b8a3e7f34c4fad0bb34d3e897be75b3973b28357fdc60a16231ac24dbc25","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-19T18:56:13Z","title_canon_sha256":"a5176daff0a4bfa205c72dd6a7e09b9b8ba67f8417e3d73f6e14265342508389"},"schema_version":"1.0","source":{"id":"2111.10364","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.10364","created_at":"2026-07-05T03:54:03Z"},{"alias_kind":"arxiv_version","alias_value":"2111.10364v3","created_at":"2026-07-05T03:54:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.10364","created_at":"2026-07-05T03:54:03Z"},{"alias_kind":"pith_short_12","alias_value":"M2GG6BJFY453","created_at":"2026-07-05T03:54:03Z"},{"alias_kind":"pith_short_16","alias_value":"M2GG6BJFY453MCVV","created_at":"2026-07-05T03:54:03Z"},{"alias_kind":"pith_short_8","alias_value":"M2GG6BJF","created_at":"2026-07-05T03:54:03Z"}],"graph_snapshots":[{"event_id":"sha256:24057f6f296784484b81622e8b9e43bedfa1d403131e23d5ef0d8bb5e31b93ae","target":"graph","created_at":"2026-07-05T03:54:03Z","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/2111.10364/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"How to extract as much learning signal from each trajectory data has been a key problem in reinforcement learning (RL), where sample inefficiency has posed serious challenges for practical applications. Recent works have shown that using expressive policy function approximators and conditioning on future trajectory information -- such as future states in hindsight experience replay or returns-to-go in Decision Transformer (DT) -- enables efficient learning of multi-task policies, where at times online RL is fully replaced by offline behavioral cloning, e.g. sequence modeling. We demonstrate th","authors_text":"Hiroki Furuta, Shixiang Shane Gu, Yutaka Matsuo","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-19T18:56:13Z","title":"Generalized Decision Transformer for Offline Hindsight Information Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.10364","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":"sha256:1afb639841f78284b2d99a6ffd100eccf6a69d381aa471f393fb082cea1f9e0a","target":"record","created_at":"2026-07-05T03:54:03Z","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":"2568b8a3e7f34c4fad0bb34d3e897be75b3973b28357fdc60a16231ac24dbc25","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-19T18:56:13Z","title_canon_sha256":"a5176daff0a4bfa205c72dd6a7e09b9b8ba67f8417e3d73f6e14265342508389"},"schema_version":"1.0","source":{"id":"2111.10364","kind":"arxiv","version":3}},"canonical_sha256":"668c6f0525c73bb60ab5a763df3f6cf82b6719bc5fa33621ab526d110aed10fa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"668c6f0525c73bb60ab5a763df3f6cf82b6719bc5fa33621ab526d110aed10fa","first_computed_at":"2026-07-05T03:54:03.847685Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:54:03.847685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EsHMQuOPWWJwn8jlPSkNCCX0i4hsRCRq3Vz+QxZi0wbf5YZxwqlMOCnm4nAcDXF0UjKeX5+FXLL6UucCnoexAg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:54:03.848143Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.10364","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1afb639841f78284b2d99a6ffd100eccf6a69d381aa471f393fb082cea1f9e0a","sha256:24057f6f296784484b81622e8b9e43bedfa1d403131e23d5ef0d8bb5e31b93ae"],"state_sha256":"251f634256eada947e13ec598e10bb479e92e1260a98415800b2b673e6affbd5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N7sTSgyIEJNkWKPpHL/IXhHD2MzCLNj/H67yjgwgHIDP1iP2nhly83okWOlSLpVsvORsW+EdeTV5VPK1xUEQBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T04:56:35.321426Z","bundle_sha256":"918453930961c52366af994f566c94f67409f32982a3d1f4bc3198c2715abfd0"}}