{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:QQTIXRBWGJNCXQR5JXN3QV3UWB","short_pith_number":"pith:QQTIXRBW","canonical_record":{"source":{"id":"2205.15967","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-31T17:15:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4d29900a93fe85cd5e8a990b0cac9827920fc86aee7ee6be71511b0959d17655","abstract_canon_sha256":"44fa05e02d83a1e8c8d6f3eb85cf682e112f72d274b10f38c813df23a13b79aa"},"schema_version":"1.0"},"canonical_sha256":"84268bc436325a2bc23d4ddbb85774b05d83adf1fb2ccce346daf76c582456ae","source":{"kind":"arxiv","id":"2205.15967","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.15967","created_at":"2026-07-05T05:19:53Z"},{"alias_kind":"arxiv_version","alias_value":"2205.15967v2","created_at":"2026-07-05T05:19:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.15967","created_at":"2026-07-05T05:19:53Z"},{"alias_kind":"pith_short_12","alias_value":"QQTIXRBWGJNC","created_at":"2026-07-05T05:19:53Z"},{"alias_kind":"pith_short_16","alias_value":"QQTIXRBWGJNCXQR5","created_at":"2026-07-05T05:19:53Z"},{"alias_kind":"pith_short_8","alias_value":"QQTIXRBW","created_at":"2026-07-05T05:19:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:QQTIXRBWGJNCXQR5JXN3QV3UWB","target":"record","payload":{"canonical_record":{"source":{"id":"2205.15967","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-31T17:15:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4d29900a93fe85cd5e8a990b0cac9827920fc86aee7ee6be71511b0959d17655","abstract_canon_sha256":"44fa05e02d83a1e8c8d6f3eb85cf682e112f72d274b10f38c813df23a13b79aa"},"schema_version":"1.0"},"canonical_sha256":"84268bc436325a2bc23d4ddbb85774b05d83adf1fb2ccce346daf76c582456ae","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:19:53.498551Z","signature_b64":"2p7x1AwqO5ZhPaLI+USQASZTPzXtcdnUBEyHYfVuazwMKbAjH0yq21onatNpqlTaSu4jjAlPuvi3zUWKdxZqDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84268bc436325a2bc23d4ddbb85774b05d83adf1fb2ccce346daf76c582456ae","last_reissued_at":"2026-07-05T05:19:53.498159Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:19:53.498159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.15967","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":"2026-07-05T05:19:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UJXNOfA6joOR6ctf8BRD1X25GLoRy04D5h97zWKCgN4EsPZ3/jt6C3dwnK0/2JSOGOoBh+raQvLVK39WoxA9BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T23:52:31.712922Z"},"content_sha256":"3d11dbb5d19a1f05badeec44d58b06581b29a71321d728969b568d27dd89417e","schema_version":"1.0","event_id":"sha256:3d11dbb5d19a1f05badeec44d58b06581b29a71321d728969b568d27dd89417e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:QQTIXRBWGJNCXQR5JXN3QV3UWB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"You Can't Count on Luck: Why Decision Transformers and RvS Fail in Stochastic Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jimmy Ba, Keiran Paster, Sheila McIlraith","submitted_at":"2022-05-31T17:15:44Z","abstract_excerpt":"Recently, methods such as Decision Transformer that reduce reinforcement learning to a prediction task and solve it via supervised learning (RvS) have become popular due to their simplicity, robustness to hyperparameters, and strong overall performance on offline RL tasks. However, simply conditioning a probabilistic model on a desired return and taking the predicted action can fail dramatically in stochastic environments since trajectories that result in a return may have only achieved that return due to luck. In this work, we describe the limitations of RvS approaches in stochastic environme"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.15967","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/2205.15967/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":"2026-07-05T05:19:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U0bGQwsUFCVpiT0lxOhbBF1ldIulpXVonCJL4+LMT5JWDA4AvxAgm8UacRyAsZs3yOYWO4UFR8dCjWmaWIVOBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T23:52:31.713355Z"},"content_sha256":"77484bd3b2e72df41c80d97bc58844a77991eacb7d246b4647e2dcd09e588926","schema_version":"1.0","event_id":"sha256:77484bd3b2e72df41c80d97bc58844a77991eacb7d246b4647e2dcd09e588926"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QQTIXRBWGJNCXQR5JXN3QV3UWB/bundle.json","state_url":"https://pith.science/pith/QQTIXRBWGJNCXQR5JXN3QV3UWB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QQTIXRBWGJNCXQR5JXN3QV3UWB/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":"2026-08-18T23:52:31Z","links":{"resolver":"https://pith.science/pith/QQTIXRBWGJNCXQR5JXN3QV3UWB","bundle":"https://pith.science/pith/QQTIXRBWGJNCXQR5JXN3QV3UWB/bundle.json","state":"https://pith.science/pith/QQTIXRBWGJNCXQR5JXN3QV3UWB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QQTIXRBWGJNCXQR5JXN3QV3UWB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:QQTIXRBWGJNCXQR5JXN3QV3UWB","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":"44fa05e02d83a1e8c8d6f3eb85cf682e112f72d274b10f38c813df23a13b79aa","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-31T17:15:44Z","title_canon_sha256":"4d29900a93fe85cd5e8a990b0cac9827920fc86aee7ee6be71511b0959d17655"},"schema_version":"1.0","source":{"id":"2205.15967","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.15967","created_at":"2026-07-05T05:19:53Z"},{"alias_kind":"arxiv_version","alias_value":"2205.15967v2","created_at":"2026-07-05T05:19:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.15967","created_at":"2026-07-05T05:19:53Z"},{"alias_kind":"pith_short_12","alias_value":"QQTIXRBWGJNC","created_at":"2026-07-05T05:19:53Z"},{"alias_kind":"pith_short_16","alias_value":"QQTIXRBWGJNCXQR5","created_at":"2026-07-05T05:19:53Z"},{"alias_kind":"pith_short_8","alias_value":"QQTIXRBW","created_at":"2026-07-05T05:19:53Z"}],"graph_snapshots":[{"event_id":"sha256:77484bd3b2e72df41c80d97bc58844a77991eacb7d246b4647e2dcd09e588926","target":"graph","created_at":"2026-07-05T05:19:53Z","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/2205.15967/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, methods such as Decision Transformer that reduce reinforcement learning to a prediction task and solve it via supervised learning (RvS) have become popular due to their simplicity, robustness to hyperparameters, and strong overall performance on offline RL tasks. However, simply conditioning a probabilistic model on a desired return and taking the predicted action can fail dramatically in stochastic environments since trajectories that result in a return may have only achieved that return due to luck. In this work, we describe the limitations of RvS approaches in stochastic environme","authors_text":"Jimmy Ba, Keiran Paster, Sheila McIlraith","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-31T17:15:44Z","title":"You Can't Count on Luck: Why Decision Transformers and RvS Fail in Stochastic Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.15967","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":"sha256:3d11dbb5d19a1f05badeec44d58b06581b29a71321d728969b568d27dd89417e","target":"record","created_at":"2026-07-05T05:19:53Z","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":"44fa05e02d83a1e8c8d6f3eb85cf682e112f72d274b10f38c813df23a13b79aa","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-31T17:15:44Z","title_canon_sha256":"4d29900a93fe85cd5e8a990b0cac9827920fc86aee7ee6be71511b0959d17655"},"schema_version":"1.0","source":{"id":"2205.15967","kind":"arxiv","version":2}},"canonical_sha256":"84268bc436325a2bc23d4ddbb85774b05d83adf1fb2ccce346daf76c582456ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"84268bc436325a2bc23d4ddbb85774b05d83adf1fb2ccce346daf76c582456ae","first_computed_at":"2026-07-05T05:19:53.498159Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:19:53.498159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2p7x1AwqO5ZhPaLI+USQASZTPzXtcdnUBEyHYfVuazwMKbAjH0yq21onatNpqlTaSu4jjAlPuvi3zUWKdxZqDA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:19:53.498551Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.15967","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d11dbb5d19a1f05badeec44d58b06581b29a71321d728969b568d27dd89417e","sha256:77484bd3b2e72df41c80d97bc58844a77991eacb7d246b4647e2dcd09e588926"],"state_sha256":"e5cf9e407edfd8ca1594d2b8f01ac3dc095d5bee9a8247aaab9e5366e83b82af"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BrwSDFq/uwI37WG1GWQ4cCYOec+D0wwdE8hsFvrPchqQ+thWQdN3ZmKoTBy8W0V/Mad83fjPS1GLupUCCgi+AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T23:52:31.716188Z","bundle_sha256":"a9f0be36c92c39e9aad04e2724e4e0c96765d3d77f43675fc0bdae96655cc014"}}