{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:7R5Q65SXGNXUEDHBW5LV473EJL","short_pith_number":"pith:7R5Q65SX","canonical_record":{"source":{"id":"2012.11547","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-21T18:28:17Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"4389b3928c6a620af07420aa3f5df7137e36d3277a17ff7ffdde2e6620c3f81a","abstract_canon_sha256":"2c72b9faf37c09906f0213cebc54ade00f451f26d2ca68262c92b3c333392315"},"schema_version":"1.0"},"canonical_sha256":"fc7b0f7657336f420ce1b7575e7f644ad460532a1da4fdb38d9b56bcf91ff4b1","source":{"kind":"arxiv","id":"2012.11547","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.11547","created_at":"2026-07-05T02:01:02Z"},{"alias_kind":"arxiv_version","alias_value":"2012.11547v1","created_at":"2026-07-05T02:01:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.11547","created_at":"2026-07-05T02:01:02Z"},{"alias_kind":"pith_short_12","alias_value":"7R5Q65SXGNXU","created_at":"2026-07-05T02:01:02Z"},{"alias_kind":"pith_short_16","alias_value":"7R5Q65SXGNXUEDHB","created_at":"2026-07-05T02:01:02Z"},{"alias_kind":"pith_short_8","alias_value":"7R5Q65SX","created_at":"2026-07-05T02:01:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:7R5Q65SXGNXUEDHBW5LV473EJL","target":"record","payload":{"canonical_record":{"source":{"id":"2012.11547","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-21T18:28:17Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"4389b3928c6a620af07420aa3f5df7137e36d3277a17ff7ffdde2e6620c3f81a","abstract_canon_sha256":"2c72b9faf37c09906f0213cebc54ade00f451f26d2ca68262c92b3c333392315"},"schema_version":"1.0"},"canonical_sha256":"fc7b0f7657336f420ce1b7575e7f644ad460532a1da4fdb38d9b56bcf91ff4b1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:01:02.757161Z","signature_b64":"ejYYWQC2OA4Nz+vi4IjtPuUkMWkPED3oZSZEZJkDsQJ3VZN6qux4zDVgoc/JkGZQUPqHi4f+J/Dv0sH1OXsTAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc7b0f7657336f420ce1b7575e7f644ad460532a1da4fdb38d9b56bcf91ff4b1","last_reissued_at":"2026-07-05T02:01:02.756707Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:01:02.756707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.11547","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":"2026-07-05T02:01:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ytLC3161Zcn+273LIbPgHR0Tdxd9npEfb8CsDBEKyhmxl5l3DjmJz16lLV26Oy2Cy5P6MKpf9+ATmbVx8GSBDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T18:57:42.039956Z"},"content_sha256":"fa7680809abb9a76bb597f9c775a9f65a764190b0dbe459912161b751948398f","schema_version":"1.0","event_id":"sha256:fa7680809abb9a76bb597f9c775a9f65a764190b0dbe459912161b751948398f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:7R5Q65SXGNXUEDHBW5LV473EJL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Offline Reinforcement Learning from Images with Latent Space Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Aravind Rajeswaran, Chelsea Finn, Rafael Rafailov, Tianhe Yu","submitted_at":"2020-12-21T18:28:17Z","abstract_excerpt":"Offline reinforcement learning (RL) refers to the problem of learning policies from a static dataset of environment interactions. Offline RL enables extensive use and re-use of historical datasets, while also alleviating safety concerns associated with online exploration, thereby expanding the real-world applicability of RL. Most prior work in offline RL has focused on tasks with compact state representations. However, the ability to learn directly from rich observation spaces like images is critical for real-world applications such as robotics. In this work, we build on recent advances in mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.11547","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/2012.11547/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":"2026-07-05T02:01:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8jtlKg6zCKoiCuEhuz+uDsh19960ADaeJgYp1uS/iOsIOEMC+vY2Jl9hSobJA9BadHEUeXg/RMWeb3zFdkTQDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T18:57:42.040569Z"},"content_sha256":"d0e6a70dcfef990dc1a0aefef8ac47058e978cc1e54ba6b7935c8fce81e2fbf3","schema_version":"1.0","event_id":"sha256:d0e6a70dcfef990dc1a0aefef8ac47058e978cc1e54ba6b7935c8fce81e2fbf3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7R5Q65SXGNXUEDHBW5LV473EJL/bundle.json","state_url":"https://pith.science/pith/7R5Q65SXGNXUEDHBW5LV473EJL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7R5Q65SXGNXUEDHBW5LV473EJL/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":"2026-08-21T18:57:42Z","links":{"resolver":"https://pith.science/pith/7R5Q65SXGNXUEDHBW5LV473EJL","bundle":"https://pith.science/pith/7R5Q65SXGNXUEDHBW5LV473EJL/bundle.json","state":"https://pith.science/pith/7R5Q65SXGNXUEDHBW5LV473EJL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7R5Q65SXGNXUEDHBW5LV473EJL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:7R5Q65SXGNXUEDHBW5LV473EJL","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":"2c72b9faf37c09906f0213cebc54ade00f451f26d2ca68262c92b3c333392315","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-21T18:28:17Z","title_canon_sha256":"4389b3928c6a620af07420aa3f5df7137e36d3277a17ff7ffdde2e6620c3f81a"},"schema_version":"1.0","source":{"id":"2012.11547","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.11547","created_at":"2026-07-05T02:01:02Z"},{"alias_kind":"arxiv_version","alias_value":"2012.11547v1","created_at":"2026-07-05T02:01:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.11547","created_at":"2026-07-05T02:01:02Z"},{"alias_kind":"pith_short_12","alias_value":"7R5Q65SXGNXU","created_at":"2026-07-05T02:01:02Z"},{"alias_kind":"pith_short_16","alias_value":"7R5Q65SXGNXUEDHB","created_at":"2026-07-05T02:01:02Z"},{"alias_kind":"pith_short_8","alias_value":"7R5Q65SX","created_at":"2026-07-05T02:01:02Z"}],"graph_snapshots":[{"event_id":"sha256:d0e6a70dcfef990dc1a0aefef8ac47058e978cc1e54ba6b7935c8fce81e2fbf3","target":"graph","created_at":"2026-07-05T02:01:02Z","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/2012.11547/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) refers to the problem of learning policies from a static dataset of environment interactions. Offline RL enables extensive use and re-use of historical datasets, while also alleviating safety concerns associated with online exploration, thereby expanding the real-world applicability of RL. Most prior work in offline RL has focused on tasks with compact state representations. However, the ability to learn directly from rich observation spaces like images is critical for real-world applications such as robotics. In this work, we build on recent advances in mod","authors_text":"Aravind Rajeswaran, Chelsea Finn, Rafael Rafailov, Tianhe Yu","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-21T18:28:17Z","title":"Offline Reinforcement Learning from Images with Latent Space Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.11547","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:fa7680809abb9a76bb597f9c775a9f65a764190b0dbe459912161b751948398f","target":"record","created_at":"2026-07-05T02:01:02Z","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":"2c72b9faf37c09906f0213cebc54ade00f451f26d2ca68262c92b3c333392315","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-21T18:28:17Z","title_canon_sha256":"4389b3928c6a620af07420aa3f5df7137e36d3277a17ff7ffdde2e6620c3f81a"},"schema_version":"1.0","source":{"id":"2012.11547","kind":"arxiv","version":1}},"canonical_sha256":"fc7b0f7657336f420ce1b7575e7f644ad460532a1da4fdb38d9b56bcf91ff4b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc7b0f7657336f420ce1b7575e7f644ad460532a1da4fdb38d9b56bcf91ff4b1","first_computed_at":"2026-07-05T02:01:02.756707Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:01:02.756707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ejYYWQC2OA4Nz+vi4IjtPuUkMWkPED3oZSZEZJkDsQJ3VZN6qux4zDVgoc/JkGZQUPqHi4f+J/Dv0sH1OXsTAA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:01:02.757161Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.11547","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fa7680809abb9a76bb597f9c775a9f65a764190b0dbe459912161b751948398f","sha256:d0e6a70dcfef990dc1a0aefef8ac47058e978cc1e54ba6b7935c8fce81e2fbf3"],"state_sha256":"3b6bd157ecaea6f25b9a8b074031e43668396be170b25f161708504feeb3ae2d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ywccxnoezkPps3mSsj9WgssIbZk4gPCLcHyv18HsIMjF6ask9h4DdJvWkMmiBJ8128pBMoYnn8l4Hpc0Sv+zAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T18:57:42.046070Z","bundle_sha256":"d7fe5f1f0403483fa66c1865966e5ffd1c671ff169c23e7020996a1ac1bb8537"}}