{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:7QRFGGDJEVP5QFSGJ5S7GF335K","short_pith_number":"pith:7QRFGGDJ","canonical_record":{"source":{"id":"2112.10751","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-20T18:55:16Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"70cc29ca3780cc34035a2665a310244768a319658feb75f8543d8a389fe07587","abstract_canon_sha256":"7eae074ab6a903443324aff9c5dfa7a47bad8c85a56760f6e51c182508965be4"},"schema_version":"1.0"},"canonical_sha256":"fc22531869255fd816464f65f3177beaad7c9ed2df9ab5edb3b1e3437e0ecd21","source":{"kind":"arxiv","id":"2112.10751","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.10751","created_at":"2026-07-05T04:22:18Z"},{"alias_kind":"arxiv_version","alias_value":"2112.10751v2","created_at":"2026-07-05T04:22:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.10751","created_at":"2026-07-05T04:22:18Z"},{"alias_kind":"pith_short_12","alias_value":"7QRFGGDJEVP5","created_at":"2026-07-05T04:22:18Z"},{"alias_kind":"pith_short_16","alias_value":"7QRFGGDJEVP5QFSG","created_at":"2026-07-05T04:22:18Z"},{"alias_kind":"pith_short_8","alias_value":"7QRFGGDJ","created_at":"2026-07-05T04:22:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:7QRFGGDJEVP5QFSGJ5S7GF335K","target":"record","payload":{"canonical_record":{"source":{"id":"2112.10751","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-20T18:55:16Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"70cc29ca3780cc34035a2665a310244768a319658feb75f8543d8a389fe07587","abstract_canon_sha256":"7eae074ab6a903443324aff9c5dfa7a47bad8c85a56760f6e51c182508965be4"},"schema_version":"1.0"},"canonical_sha256":"fc22531869255fd816464f65f3177beaad7c9ed2df9ab5edb3b1e3437e0ecd21","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:22:18.989277Z","signature_b64":"/kF1afTuS3OIidddj+oUzKkKx3gFxybjDj+oINQk0LDnEuCZZ+AIITH6V0HndOWJs1Pg0AqJ6eFGptZ3NH9tAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc22531869255fd816464f65f3177beaad7c9ed2df9ab5edb3b1e3437e0ecd21","last_reissued_at":"2026-07-05T04:22:18.988792Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:22:18.988792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.10751","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":"2026-07-05T04:22:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"82xKrQdQIYEYYg+h6G89fh19xYen3mGeOvX+nriE6lfI5AbFQkkxoWSsPDNUr8J/x3EEpLnPEnVz4/tr2xDCCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:05:19.368678Z"},"content_sha256":"dffafba5d711075e9ab3ecbd32f28a2811d8f00d6c199e8c283d691fa96e8878","schema_version":"1.0","event_id":"sha256:dffafba5d711075e9ab3ecbd32f28a2811d8f00d6c199e8c283d691fa96e8878"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:7QRFGGDJEVP5QFSGJ5S7GF335K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RvS: What is Essential for Offline RL via Supervised Learning?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Benjamin Eysenbach, Ilya Kostrikov, Scott Emmons, Sergey Levine","submitted_at":"2021-12-20T18:55:16Z","abstract_excerpt":"Recent work has shown that supervised learning alone, without temporal difference (TD) learning, can be remarkably effective for offline RL. When does this hold true, and which algorithmic components are necessary? Through extensive experiments, we boil supervised learning for offline RL down to its essential elements. In every environment suite we consider, simply maximizing likelihood with a two-layer feedforward MLP is competitive with state-of-the-art results of substantially more complex methods based on TD learning or sequence modeling with Transformers. Carefully choosing model capacity"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.10751","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/2112.10751/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":"2026-07-05T04:22:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1g1hFjDeXvNp3co4V6/wkyZRuiq+VkBjtOYnQPavLNeXysjB8IF7v99QdTAJgx5Y6Dz8HGIZQWFCnPtSPiLqAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:05:19.369188Z"},"content_sha256":"37ba16d0694d1f17a244e57684de23423192414f042e904beb5a90b982859046","schema_version":"1.0","event_id":"sha256:37ba16d0694d1f17a244e57684de23423192414f042e904beb5a90b982859046"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7QRFGGDJEVP5QFSGJ5S7GF335K/bundle.json","state_url":"https://pith.science/pith/7QRFGGDJEVP5QFSGJ5S7GF335K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7QRFGGDJEVP5QFSGJ5S7GF335K/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":"2026-08-07T18:05:19Z","links":{"resolver":"https://pith.science/pith/7QRFGGDJEVP5QFSGJ5S7GF335K","bundle":"https://pith.science/pith/7QRFGGDJEVP5QFSGJ5S7GF335K/bundle.json","state":"https://pith.science/pith/7QRFGGDJEVP5QFSGJ5S7GF335K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7QRFGGDJEVP5QFSGJ5S7GF335K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:7QRFGGDJEVP5QFSGJ5S7GF335K","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":"7eae074ab6a903443324aff9c5dfa7a47bad8c85a56760f6e51c182508965be4","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-20T18:55:16Z","title_canon_sha256":"70cc29ca3780cc34035a2665a310244768a319658feb75f8543d8a389fe07587"},"schema_version":"1.0","source":{"id":"2112.10751","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.10751","created_at":"2026-07-05T04:22:18Z"},{"alias_kind":"arxiv_version","alias_value":"2112.10751v2","created_at":"2026-07-05T04:22:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.10751","created_at":"2026-07-05T04:22:18Z"},{"alias_kind":"pith_short_12","alias_value":"7QRFGGDJEVP5","created_at":"2026-07-05T04:22:18Z"},{"alias_kind":"pith_short_16","alias_value":"7QRFGGDJEVP5QFSG","created_at":"2026-07-05T04:22:18Z"},{"alias_kind":"pith_short_8","alias_value":"7QRFGGDJ","created_at":"2026-07-05T04:22:18Z"}],"graph_snapshots":[{"event_id":"sha256:37ba16d0694d1f17a244e57684de23423192414f042e904beb5a90b982859046","target":"graph","created_at":"2026-07-05T04:22:18Z","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/2112.10751/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent work has shown that supervised learning alone, without temporal difference (TD) learning, can be remarkably effective for offline RL. When does this hold true, and which algorithmic components are necessary? Through extensive experiments, we boil supervised learning for offline RL down to its essential elements. In every environment suite we consider, simply maximizing likelihood with a two-layer feedforward MLP is competitive with state-of-the-art results of substantially more complex methods based on TD learning or sequence modeling with Transformers. Carefully choosing model capacity","authors_text":"Benjamin Eysenbach, Ilya Kostrikov, Scott Emmons, Sergey Levine","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-20T18:55:16Z","title":"RvS: What is Essential for Offline RL via Supervised Learning?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.10751","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:dffafba5d711075e9ab3ecbd32f28a2811d8f00d6c199e8c283d691fa96e8878","target":"record","created_at":"2026-07-05T04:22:18Z","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":"7eae074ab6a903443324aff9c5dfa7a47bad8c85a56760f6e51c182508965be4","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-20T18:55:16Z","title_canon_sha256":"70cc29ca3780cc34035a2665a310244768a319658feb75f8543d8a389fe07587"},"schema_version":"1.0","source":{"id":"2112.10751","kind":"arxiv","version":2}},"canonical_sha256":"fc22531869255fd816464f65f3177beaad7c9ed2df9ab5edb3b1e3437e0ecd21","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc22531869255fd816464f65f3177beaad7c9ed2df9ab5edb3b1e3437e0ecd21","first_computed_at":"2026-07-05T04:22:18.988792Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:22:18.988792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/kF1afTuS3OIidddj+oUzKkKx3gFxybjDj+oINQk0LDnEuCZZ+AIITH6V0HndOWJs1Pg0AqJ6eFGptZ3NH9tAw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:22:18.989277Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.10751","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dffafba5d711075e9ab3ecbd32f28a2811d8f00d6c199e8c283d691fa96e8878","sha256:37ba16d0694d1f17a244e57684de23423192414f042e904beb5a90b982859046"],"state_sha256":"b91e42173293a7033b0736049b11d8a0951b80eae58566777cf59a165a165ef7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yye9QkvarSvc/pSr8SE4g5v6APNLuySj4vIm5G/YcfsZKaf/Rwxv7lEzzYaWzI4lJAtmOAjTX4Ldi7hPaokqCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T18:05:19.373865Z","bundle_sha256":"ddf6c1309d1316118ba4eb54350b0d9d25361f054ab7212aa7d0367d916a1375"}}