{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ITYZ62QQAFIHBI6ZEZAWMOVLYT","short_pith_number":"pith:ITYZ62QQ","canonical_record":{"source":{"id":"2407.10839","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-15T15:53:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b4070a675cc9a330bd1361ae14192638e817529618a530a1e648a8afd9dc63a2","abstract_canon_sha256":"bff1745d79085f870c44464735debef1e0018af056c8a8a712616a6ffee41af8"},"schema_version":"1.0"},"canonical_sha256":"44f19f6a10015070a3d92641663aabc4fb0a81c78caf94855e12dd0c1618e3b3","source":{"kind":"arxiv","id":"2407.10839","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.10839","created_at":"2026-07-05T08:44:04Z"},{"alias_kind":"arxiv_version","alias_value":"2407.10839v1","created_at":"2026-07-05T08:44:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10839","created_at":"2026-07-05T08:44:04Z"},{"alias_kind":"pith_short_12","alias_value":"ITYZ62QQAFIH","created_at":"2026-07-05T08:44:04Z"},{"alias_kind":"pith_short_16","alias_value":"ITYZ62QQAFIHBI6Z","created_at":"2026-07-05T08:44:04Z"},{"alias_kind":"pith_short_8","alias_value":"ITYZ62QQ","created_at":"2026-07-05T08:44:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ITYZ62QQAFIHBI6ZEZAWMOVLYT","target":"record","payload":{"canonical_record":{"source":{"id":"2407.10839","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-15T15:53:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b4070a675cc9a330bd1361ae14192638e817529618a530a1e648a8afd9dc63a2","abstract_canon_sha256":"bff1745d79085f870c44464735debef1e0018af056c8a8a712616a6ffee41af8"},"schema_version":"1.0"},"canonical_sha256":"44f19f6a10015070a3d92641663aabc4fb0a81c78caf94855e12dd0c1618e3b3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:04.947774Z","signature_b64":"f0EbrFGk6kYPsDWw1oZCztXSw27S4+jWJV1wZyumM6ceJsCaUBUKrRWihHxsnJGj91sVm1AGJVUxZ7uOydWZCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44f19f6a10015070a3d92641663aabc4fb0a81c78caf94855e12dd0c1618e3b3","last_reissued_at":"2026-07-05T08:44:04.947356Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:04.947356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.10839","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":"2026-07-05T08:44:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4dnld3pNaPXvUmHurK7qpzd3PZaJzpV5zTSa9lCopOlEMbxKWEqsJZfVcjnUAr+GUtZu71GUXEVuJv+ypakBCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T04:07:54.043688Z"},"content_sha256":"8665630562405e24a8e57c114239dffb8024346d2e70c6ca861a8bbc2c5109fd","schema_version":"1.0","event_id":"sha256:8665630562405e24a8e57c114239dffb8024346d2e70c6ca861a8bbc2c5109fd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ITYZ62QQAFIHBI6ZEZAWMOVLYT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Offline Reinforcement Learning with Imputed Rewards","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Andrew D. Bagdanov, Carlo Romeo","submitted_at":"2024-07-15T15:53:13Z","abstract_excerpt":"Offline Reinforcement Learning (ORL) offers a robust solution to training agents in applications where interactions with the environment must be strictly limited due to cost, safety, or lack of accurate simulation environments. Despite its potential to facilitate deployment of artificial agents in the real world, Offline Reinforcement Learning typically requires very many demonstrations annotated with ground-truth rewards. Consequently, state-of-the-art ORL algorithms can be difficult or impossible to apply in data-scarce scenarios. In this paper we propose a simple but effective Reward Model "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10839","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/2407.10839/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":"2026-07-05T08:44:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+JdzVxs+0Pkf4BhRZx4mP1sldsicgUXpfs/m+ntfAS3ydC9ekf7U0Y/EfWHWRK4D6Y7sjoaZxvJV03RhNfF9CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T04:07:54.044300Z"},"content_sha256":"8725779f3db436816ba331fea9403a0cb68fd3ce1aca26d4b890e97d0856134d","schema_version":"1.0","event_id":"sha256:8725779f3db436816ba331fea9403a0cb68fd3ce1aca26d4b890e97d0856134d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ITYZ62QQAFIHBI6ZEZAWMOVLYT/bundle.json","state_url":"https://pith.science/pith/ITYZ62QQAFIHBI6ZEZAWMOVLYT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ITYZ62QQAFIHBI6ZEZAWMOVLYT/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":"2026-08-13T04:07:54Z","links":{"resolver":"https://pith.science/pith/ITYZ62QQAFIHBI6ZEZAWMOVLYT","bundle":"https://pith.science/pith/ITYZ62QQAFIHBI6ZEZAWMOVLYT/bundle.json","state":"https://pith.science/pith/ITYZ62QQAFIHBI6ZEZAWMOVLYT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ITYZ62QQAFIHBI6ZEZAWMOVLYT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ITYZ62QQAFIHBI6ZEZAWMOVLYT","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":"bff1745d79085f870c44464735debef1e0018af056c8a8a712616a6ffee41af8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-15T15:53:13Z","title_canon_sha256":"b4070a675cc9a330bd1361ae14192638e817529618a530a1e648a8afd9dc63a2"},"schema_version":"1.0","source":{"id":"2407.10839","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.10839","created_at":"2026-07-05T08:44:04Z"},{"alias_kind":"arxiv_version","alias_value":"2407.10839v1","created_at":"2026-07-05T08:44:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10839","created_at":"2026-07-05T08:44:04Z"},{"alias_kind":"pith_short_12","alias_value":"ITYZ62QQAFIH","created_at":"2026-07-05T08:44:04Z"},{"alias_kind":"pith_short_16","alias_value":"ITYZ62QQAFIHBI6Z","created_at":"2026-07-05T08:44:04Z"},{"alias_kind":"pith_short_8","alias_value":"ITYZ62QQ","created_at":"2026-07-05T08:44:04Z"}],"graph_snapshots":[{"event_id":"sha256:8725779f3db436816ba331fea9403a0cb68fd3ce1aca26d4b890e97d0856134d","target":"graph","created_at":"2026-07-05T08:44:04Z","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/2407.10839/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline Reinforcement Learning (ORL) offers a robust solution to training agents in applications where interactions with the environment must be strictly limited due to cost, safety, or lack of accurate simulation environments. Despite its potential to facilitate deployment of artificial agents in the real world, Offline Reinforcement Learning typically requires very many demonstrations annotated with ground-truth rewards. Consequently, state-of-the-art ORL algorithms can be difficult or impossible to apply in data-scarce scenarios. In this paper we propose a simple but effective Reward Model ","authors_text":"Andrew D. Bagdanov, Carlo Romeo","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-15T15:53:13Z","title":"Offline Reinforcement Learning with Imputed Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10839","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":"sha256:8665630562405e24a8e57c114239dffb8024346d2e70c6ca861a8bbc2c5109fd","target":"record","created_at":"2026-07-05T08:44:04Z","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":"bff1745d79085f870c44464735debef1e0018af056c8a8a712616a6ffee41af8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-15T15:53:13Z","title_canon_sha256":"b4070a675cc9a330bd1361ae14192638e817529618a530a1e648a8afd9dc63a2"},"schema_version":"1.0","source":{"id":"2407.10839","kind":"arxiv","version":1}},"canonical_sha256":"44f19f6a10015070a3d92641663aabc4fb0a81c78caf94855e12dd0c1618e3b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"44f19f6a10015070a3d92641663aabc4fb0a81c78caf94855e12dd0c1618e3b3","first_computed_at":"2026-07-05T08:44:04.947356Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:44:04.947356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f0EbrFGk6kYPsDWw1oZCztXSw27S4+jWJV1wZyumM6ceJsCaUBUKrRWihHxsnJGj91sVm1AGJVUxZ7uOydWZCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:44:04.947774Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.10839","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8665630562405e24a8e57c114239dffb8024346d2e70c6ca861a8bbc2c5109fd","sha256:8725779f3db436816ba331fea9403a0cb68fd3ce1aca26d4b890e97d0856134d"],"state_sha256":"1bca085066c7d4ac7da6c2178a32fd4de450fd5db7f3c54e42d0d28370fc0cc2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R+mdGbSEVkrXt5svXBBNbVijiFKaTpee63IH71Rv2zYjEXuf+FubFKwLWmwyzMr/nhtl2RiOlxEY/LE8MGzDCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T04:07:54.048062Z","bundle_sha256":"b497bf004343dc34520bba73546fcec730a106cbdbc104e3dd77faab646f5330"}}