{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KECMUOV4SAIYZB5VOLIBGWW42B","short_pith_number":"pith:KECMUOV4","canonical_record":{"source":{"id":"2402.00807","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-01T17:44:11Z","cross_cats_sorted":[],"title_canon_sha256":"442a01db5c3d6708169a7917c96c80bc341ffb344a3211cfed14b3cfa1a8afb2","abstract_canon_sha256":"15e7dc3a0b623b10eb5d07a27e687f3ccf34e329f71f31a20c86402cb70f9fa2"},"schema_version":"1.0"},"canonical_sha256":"5104ca3abc90118c87b572d0135adcd07f7e379cfd74ccd2c8474ade0001ef88","source":{"kind":"arxiv","id":"2402.00807","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.00807","created_at":"2026-07-05T09:14:53Z"},{"alias_kind":"arxiv_version","alias_value":"2402.00807v2","created_at":"2026-07-05T09:14:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.00807","created_at":"2026-07-05T09:14:53Z"},{"alias_kind":"pith_short_12","alias_value":"KECMUOV4SAIY","created_at":"2026-07-05T09:14:53Z"},{"alias_kind":"pith_short_16","alias_value":"KECMUOV4SAIYZB5V","created_at":"2026-07-05T09:14:53Z"},{"alias_kind":"pith_short_8","alias_value":"KECMUOV4","created_at":"2026-07-05T09:14:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KECMUOV4SAIYZB5VOLIBGWW42B","target":"record","payload":{"canonical_record":{"source":{"id":"2402.00807","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-01T17:44:11Z","cross_cats_sorted":[],"title_canon_sha256":"442a01db5c3d6708169a7917c96c80bc341ffb344a3211cfed14b3cfa1a8afb2","abstract_canon_sha256":"15e7dc3a0b623b10eb5d07a27e687f3ccf34e329f71f31a20c86402cb70f9fa2"},"schema_version":"1.0"},"canonical_sha256":"5104ca3abc90118c87b572d0135adcd07f7e379cfd74ccd2c8474ade0001ef88","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:53.641577Z","signature_b64":"SdnEagqT0UvCyrRRswNst5TMyUlgjLfeElKo3EFp2qTPEFSuOC/wREGz09iWhCF84usmc4McMd9dplGG9ZALBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5104ca3abc90118c87b572d0135adcd07f7e379cfd74ccd2c8474ade0001ef88","last_reissued_at":"2026-07-05T09:14:53.641099Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:53.641099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.00807","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":"2026-07-05T09:14:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3a+Cgf5d3Eu8uCkN4xViMF8CUSJzBso3pqyRQMLdu9MqbiLmOQc5+9N8oH07CdJ8MD56nlxKYWrdfc6PutEsDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:51:26.656048Z"},"content_sha256":"240fba90bc1c67ad67eed7d430f22d07d361d2d63800b03e9b8133afa560b1e2","schema_version":"1.0","event_id":"sha256:240fba90bc1c67ad67eed7d430f22d07d361d2d63800b03e9b8133afa560b1e2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KECMUOV4SAIYZB5VOLIBGWW42B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Augmenting Offline Reinforcement Learning with State-only Interactions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Shangzhe Li, Xinhua Zhang","submitted_at":"2024-02-01T17:44:11Z","abstract_excerpt":"Batch offline data have been shown considerably beneficial for reinforcement learning. Their benefit is further amplified by upsampling with generative models. In this paper, we consider a novel opportunity where interaction with environment is feasible, but only restricted to observations, i.e., \\textit{no reward} feedback is available. This setting is broadly applicable, as simulators or even real cyber-physical systems are often accessible, while in contrast reward is often difficult or expensive to obtain. As a result, the learner must make good sense of the offline data to synthesize an e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.00807","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/2402.00807/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":"2026-07-05T09:14:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KOnGR0BNikRwbcTqFhA4992QjZFIT5AHKLSDnjk+EHtHJ49FKbyhtKMZvLczTJ1YRwze3JPC8AXIXYcmlU1eDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:51:26.656535Z"},"content_sha256":"1dde23fdd53f0294d31328ac776fce59a505ab71f5a0a4623b9b574de95d751a","schema_version":"1.0","event_id":"sha256:1dde23fdd53f0294d31328ac776fce59a505ab71f5a0a4623b9b574de95d751a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KECMUOV4SAIYZB5VOLIBGWW42B/bundle.json","state_url":"https://pith.science/pith/KECMUOV4SAIYZB5VOLIBGWW42B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KECMUOV4SAIYZB5VOLIBGWW42B/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":"2026-08-07T01:51:26Z","links":{"resolver":"https://pith.science/pith/KECMUOV4SAIYZB5VOLIBGWW42B","bundle":"https://pith.science/pith/KECMUOV4SAIYZB5VOLIBGWW42B/bundle.json","state":"https://pith.science/pith/KECMUOV4SAIYZB5VOLIBGWW42B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KECMUOV4SAIYZB5VOLIBGWW42B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KECMUOV4SAIYZB5VOLIBGWW42B","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":"15e7dc3a0b623b10eb5d07a27e687f3ccf34e329f71f31a20c86402cb70f9fa2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-01T17:44:11Z","title_canon_sha256":"442a01db5c3d6708169a7917c96c80bc341ffb344a3211cfed14b3cfa1a8afb2"},"schema_version":"1.0","source":{"id":"2402.00807","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.00807","created_at":"2026-07-05T09:14:53Z"},{"alias_kind":"arxiv_version","alias_value":"2402.00807v2","created_at":"2026-07-05T09:14:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.00807","created_at":"2026-07-05T09:14:53Z"},{"alias_kind":"pith_short_12","alias_value":"KECMUOV4SAIY","created_at":"2026-07-05T09:14:53Z"},{"alias_kind":"pith_short_16","alias_value":"KECMUOV4SAIYZB5V","created_at":"2026-07-05T09:14:53Z"},{"alias_kind":"pith_short_8","alias_value":"KECMUOV4","created_at":"2026-07-05T09:14:53Z"}],"graph_snapshots":[{"event_id":"sha256:1dde23fdd53f0294d31328ac776fce59a505ab71f5a0a4623b9b574de95d751a","target":"graph","created_at":"2026-07-05T09:14:53Z","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/2402.00807/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Batch offline data have been shown considerably beneficial for reinforcement learning. Their benefit is further amplified by upsampling with generative models. In this paper, we consider a novel opportunity where interaction with environment is feasible, but only restricted to observations, i.e., \\textit{no reward} feedback is available. This setting is broadly applicable, as simulators or even real cyber-physical systems are often accessible, while in contrast reward is often difficult or expensive to obtain. As a result, the learner must make good sense of the offline data to synthesize an e","authors_text":"Shangzhe Li, Xinhua Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-01T17:44:11Z","title":"Augmenting Offline Reinforcement Learning with State-only Interactions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.00807","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":"sha256:240fba90bc1c67ad67eed7d430f22d07d361d2d63800b03e9b8133afa560b1e2","target":"record","created_at":"2026-07-05T09:14:53Z","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":"15e7dc3a0b623b10eb5d07a27e687f3ccf34e329f71f31a20c86402cb70f9fa2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-01T17:44:11Z","title_canon_sha256":"442a01db5c3d6708169a7917c96c80bc341ffb344a3211cfed14b3cfa1a8afb2"},"schema_version":"1.0","source":{"id":"2402.00807","kind":"arxiv","version":2}},"canonical_sha256":"5104ca3abc90118c87b572d0135adcd07f7e379cfd74ccd2c8474ade0001ef88","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5104ca3abc90118c87b572d0135adcd07f7e379cfd74ccd2c8474ade0001ef88","first_computed_at":"2026-07-05T09:14:53.641099Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:14:53.641099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SdnEagqT0UvCyrRRswNst5TMyUlgjLfeElKo3EFp2qTPEFSuOC/wREGz09iWhCF84usmc4McMd9dplGG9ZALBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:14:53.641577Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.00807","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:240fba90bc1c67ad67eed7d430f22d07d361d2d63800b03e9b8133afa560b1e2","sha256:1dde23fdd53f0294d31328ac776fce59a505ab71f5a0a4623b9b574de95d751a"],"state_sha256":"8ecf8370e55b7dcf50adbe7214330ab0b18e308f983b396f23f99b71c9588dc3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"23QJT//bxytOFCk0YHEpI1wTUvmXvJW3Qm0Tb2wD8kYUK1lv9wntBtBA88q99PQWq0Je8KnCQigw24QfNrudBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T01:51:26.660210Z","bundle_sha256":"2df8789b4a3bd1e8b16e014c3d7710f4d91c885dea725d23b6cffda9c1f1e5c9"}}