{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:SLX3FD5A4XKJAUAPS7IKYTGHXK","short_pith_number":"pith:SLX3FD5A","canonical_record":{"source":{"id":"2211.02100","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-03T19:10:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f14e7b7991c7fbac12987010c44bba4b0b2504a7961f89b64ca7687fd72a9bda","abstract_canon_sha256":"861938b3851014793ef39f56be36f458f251404a3a043b9a864db9106f879dc4"},"schema_version":"1.0"},"canonical_sha256":"92efb28fa0e5d490500f97d0ac4cc7ba979998e3afb8c5680f88d67d554c580f","source":{"kind":"arxiv","id":"2211.02100","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.02100","created_at":"2026-07-05T05:13:11Z"},{"alias_kind":"arxiv_version","alias_value":"2211.02100v1","created_at":"2026-07-05T05:13:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.02100","created_at":"2026-07-05T05:13:11Z"},{"alias_kind":"pith_short_12","alias_value":"SLX3FD5A4XKJ","created_at":"2026-07-05T05:13:11Z"},{"alias_kind":"pith_short_16","alias_value":"SLX3FD5A4XKJAUAP","created_at":"2026-07-05T05:13:11Z"},{"alias_kind":"pith_short_8","alias_value":"SLX3FD5A","created_at":"2026-07-05T05:13:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:SLX3FD5A4XKJAUAPS7IKYTGHXK","target":"record","payload":{"canonical_record":{"source":{"id":"2211.02100","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-03T19:10:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f14e7b7991c7fbac12987010c44bba4b0b2504a7961f89b64ca7687fd72a9bda","abstract_canon_sha256":"861938b3851014793ef39f56be36f458f251404a3a043b9a864db9106f879dc4"},"schema_version":"1.0"},"canonical_sha256":"92efb28fa0e5d490500f97d0ac4cc7ba979998e3afb8c5680f88d67d554c580f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:13:11.563536Z","signature_b64":"Fj0ky3wZBbao2clCD0ZGF/I0/n4M2L5tfMcXp111FhAT8LNZtP8iwu5gSf2llWB+uT6eV6HFSYcxnOr8lLnIAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92efb28fa0e5d490500f97d0ac4cc7ba979998e3afb8c5680f88d67d554c580f","last_reissued_at":"2026-07-05T05:13:11.563013Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:13:11.563013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.02100","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":"2026-07-05T05:13:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CgvHY8qXgPsg8gb8uu3FUMzrHTZJ+b6TGXYbdAYROoVgZFMhpK9/tbpis4OQuOH7uC2HNHiBWOum98SnqQsQDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:10:29.227035Z"},"content_sha256":"65df569775e1834fcec10df32d8b4d6ea6f37e166da156e8e1a0c2e28ecb90e7","schema_version":"1.0","event_id":"sha256:65df569775e1834fcec10df32d8b4d6ea6f37e166da156e8e1a0c2e28ecb90e7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:SLX3FD5A4XKJAUAPS7IKYTGHXK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Contrastive Value Learning: Implicit Models for Simple Offline RL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Benjamin Eysenbach, Bogdan Mazoure, Jonathan Tompson, Ofir Nachum","submitted_at":"2022-11-03T19:10:05Z","abstract_excerpt":"Model-based reinforcement learning (RL) methods are appealing in the offline setting because they allow an agent to reason about the consequences of actions without interacting with the environment. Prior methods learn a 1-step dynamics model, which predicts the next state given the current state and action. These models do not immediately tell the agent which actions to take, but must be integrated into a larger RL framework. Can we model the environment dynamics in a different way, such that the learned model does directly indicate the value of each action? In this paper, we propose Contrast"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.02100","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/2211.02100/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":"2026-07-05T05:13:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dkIClzaca7vSjtbihD0LkyvVPapP9DczAkUi1JrBE0H4Bco7pOw0NyovUMl2umF0GQeJEBSqQktBXyGw8I7OAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:10:29.227540Z"},"content_sha256":"6f8315b46c45de0602780a8ac1ed66559c3349a532fac9db40a6cef5afae1d47","schema_version":"1.0","event_id":"sha256:6f8315b46c45de0602780a8ac1ed66559c3349a532fac9db40a6cef5afae1d47"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SLX3FD5A4XKJAUAPS7IKYTGHXK/bundle.json","state_url":"https://pith.science/pith/SLX3FD5A4XKJAUAPS7IKYTGHXK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SLX3FD5A4XKJAUAPS7IKYTGHXK/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":"2026-08-06T04:10:29Z","links":{"resolver":"https://pith.science/pith/SLX3FD5A4XKJAUAPS7IKYTGHXK","bundle":"https://pith.science/pith/SLX3FD5A4XKJAUAPS7IKYTGHXK/bundle.json","state":"https://pith.science/pith/SLX3FD5A4XKJAUAPS7IKYTGHXK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SLX3FD5A4XKJAUAPS7IKYTGHXK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:SLX3FD5A4XKJAUAPS7IKYTGHXK","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":"861938b3851014793ef39f56be36f458f251404a3a043b9a864db9106f879dc4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-03T19:10:05Z","title_canon_sha256":"f14e7b7991c7fbac12987010c44bba4b0b2504a7961f89b64ca7687fd72a9bda"},"schema_version":"1.0","source":{"id":"2211.02100","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.02100","created_at":"2026-07-05T05:13:11Z"},{"alias_kind":"arxiv_version","alias_value":"2211.02100v1","created_at":"2026-07-05T05:13:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.02100","created_at":"2026-07-05T05:13:11Z"},{"alias_kind":"pith_short_12","alias_value":"SLX3FD5A4XKJ","created_at":"2026-07-05T05:13:11Z"},{"alias_kind":"pith_short_16","alias_value":"SLX3FD5A4XKJAUAP","created_at":"2026-07-05T05:13:11Z"},{"alias_kind":"pith_short_8","alias_value":"SLX3FD5A","created_at":"2026-07-05T05:13:11Z"}],"graph_snapshots":[{"event_id":"sha256:6f8315b46c45de0602780a8ac1ed66559c3349a532fac9db40a6cef5afae1d47","target":"graph","created_at":"2026-07-05T05:13:11Z","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/2211.02100/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model-based reinforcement learning (RL) methods are appealing in the offline setting because they allow an agent to reason about the consequences of actions without interacting with the environment. Prior methods learn a 1-step dynamics model, which predicts the next state given the current state and action. These models do not immediately tell the agent which actions to take, but must be integrated into a larger RL framework. Can we model the environment dynamics in a different way, such that the learned model does directly indicate the value of each action? In this paper, we propose Contrast","authors_text":"Benjamin Eysenbach, Bogdan Mazoure, Jonathan Tompson, Ofir Nachum","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-03T19:10:05Z","title":"Contrastive Value Learning: Implicit Models for Simple Offline RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.02100","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":"sha256:65df569775e1834fcec10df32d8b4d6ea6f37e166da156e8e1a0c2e28ecb90e7","target":"record","created_at":"2026-07-05T05:13:11Z","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":"861938b3851014793ef39f56be36f458f251404a3a043b9a864db9106f879dc4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-03T19:10:05Z","title_canon_sha256":"f14e7b7991c7fbac12987010c44bba4b0b2504a7961f89b64ca7687fd72a9bda"},"schema_version":"1.0","source":{"id":"2211.02100","kind":"arxiv","version":1}},"canonical_sha256":"92efb28fa0e5d490500f97d0ac4cc7ba979998e3afb8c5680f88d67d554c580f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"92efb28fa0e5d490500f97d0ac4cc7ba979998e3afb8c5680f88d67d554c580f","first_computed_at":"2026-07-05T05:13:11.563013Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:13:11.563013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Fj0ky3wZBbao2clCD0ZGF/I0/n4M2L5tfMcXp111FhAT8LNZtP8iwu5gSf2llWB+uT6eV6HFSYcxnOr8lLnIAw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:13:11.563536Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.02100","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:65df569775e1834fcec10df32d8b4d6ea6f37e166da156e8e1a0c2e28ecb90e7","sha256:6f8315b46c45de0602780a8ac1ed66559c3349a532fac9db40a6cef5afae1d47"],"state_sha256":"aca6eeff81dcfbb8c5e34da05cdc161742e27facf851aa24dd0a5f043b9c427b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rt4YFBBQF0zkJbeHHkfZmjLMn64OpYz9ngcjGmUJeYE24oqQBjFbvrFLteCqcoKJsivJI0J+ZXsnGoQUWlcwBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T04:10:29.231428Z","bundle_sha256":"e44e731ecc4c2613ef4f924128f6570bed3b4859862390604e2ec4dd2ef46f2b"}}