{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:FU7VR4VYHTZAPSOJVJWHAVSAOD","short_pith_number":"pith:FU7VR4VY","canonical_record":{"source":{"id":"2308.03882","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-07T19:24:47Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"fc6dd574f4b70c77d012721db0d31fca26e9e231c280eb77170f042755595421","abstract_canon_sha256":"30a186b3e838f9e58084ddc991ca0bf2378124caddb1815bfb5fa602bc8a3156"},"schema_version":"1.0"},"canonical_sha256":"2d3f58f2b83cf207c9c9aa6c70564070dba2531cb98a12114550b2e8fb960b29","source":{"kind":"arxiv","id":"2308.03882","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.03882","created_at":"2026-07-05T06:53:43Z"},{"alias_kind":"arxiv_version","alias_value":"2308.03882v2","created_at":"2026-07-05T06:53:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.03882","created_at":"2026-07-05T06:53:43Z"},{"alias_kind":"pith_short_12","alias_value":"FU7VR4VYHTZA","created_at":"2026-07-05T06:53:43Z"},{"alias_kind":"pith_short_16","alias_value":"FU7VR4VYHTZAPSOJ","created_at":"2026-07-05T06:53:43Z"},{"alias_kind":"pith_short_8","alias_value":"FU7VR4VY","created_at":"2026-07-05T06:53:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:FU7VR4VYHTZAPSOJVJWHAVSAOD","target":"record","payload":{"canonical_record":{"source":{"id":"2308.03882","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-07T19:24:47Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"fc6dd574f4b70c77d012721db0d31fca26e9e231c280eb77170f042755595421","abstract_canon_sha256":"30a186b3e838f9e58084ddc991ca0bf2378124caddb1815bfb5fa602bc8a3156"},"schema_version":"1.0"},"canonical_sha256":"2d3f58f2b83cf207c9c9aa6c70564070dba2531cb98a12114550b2e8fb960b29","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:53:43.200336Z","signature_b64":"7Hp57GTzcTcIQ7IMIkOJUbWzigi1yUuPV7Q42U+nSpYbZtMsaGODDBGFRkgCRUWfCpUCTW0zSY/NXswDP7WEAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d3f58f2b83cf207c9c9aa6c70564070dba2531cb98a12114550b2e8fb960b29","last_reissued_at":"2026-07-05T06:53:43.199803Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:53:43.199803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.03882","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":"2026-07-05T06:53:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X3aF5UflH9fxYiO/VNE2dmyyCa4QrcArUlp6uKthiACI+67f1BO+717J2UMpJoqRG7AOuQogos4SITLQv1xNDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T16:14:43.137487Z"},"content_sha256":"6a41abd11c40891d773d83e14962eba1ed54b5e16f321e7510ec63a9c29ca0bb","schema_version":"1.0","event_id":"sha256:6a41abd11c40891d773d83e14962eba1ed54b5e16f321e7510ec63a9c29ca0bb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:FU7VR4VYHTZAPSOJVJWHAVSAOD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploiting Generalization in Offline Reinforcement Learning via Unseen State Augmentations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ashwin Kalyan, Dhruv Batra, Gaurav Sukhatme, Govind Thattai, Nirbhay Modhe, Qiaozi Gao","submitted_at":"2023-08-07T19:24:47Z","abstract_excerpt":"Offline reinforcement learning (RL) methods strike a balance between exploration and exploitation by conservative value estimation -- penalizing values of unseen states and actions. Model-free methods penalize values at all unseen actions, while model-based methods are able to further exploit unseen states via model rollouts. However, such methods are handicapped in their ability to find unseen states far away from the available offline data due to two factors -- (a) very short rollout horizons in models due to cascading model errors, and (b) model rollouts originating solely from states obser"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.03882","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/2308.03882/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":"2026-07-05T06:53:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8cBqGfJA+oeMvnHtY4rsqUMxg+737U1huYL9TvcTri4jNWuEHJ7RAMLpUiqj9fzE/H9ECH2nnYw1RbGMrq5hAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T16:14:43.137857Z"},"content_sha256":"9eb50468b7cd76694a5f484465139a95fbaef72bdbfa7677f93fedc359349ec4","schema_version":"1.0","event_id":"sha256:9eb50468b7cd76694a5f484465139a95fbaef72bdbfa7677f93fedc359349ec4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FU7VR4VYHTZAPSOJVJWHAVSAOD/bundle.json","state_url":"https://pith.science/pith/FU7VR4VYHTZAPSOJVJWHAVSAOD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FU7VR4VYHTZAPSOJVJWHAVSAOD/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":"2026-07-06T16:14:43Z","links":{"resolver":"https://pith.science/pith/FU7VR4VYHTZAPSOJVJWHAVSAOD","bundle":"https://pith.science/pith/FU7VR4VYHTZAPSOJVJWHAVSAOD/bundle.json","state":"https://pith.science/pith/FU7VR4VYHTZAPSOJVJWHAVSAOD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FU7VR4VYHTZAPSOJVJWHAVSAOD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FU7VR4VYHTZAPSOJVJWHAVSAOD","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":"30a186b3e838f9e58084ddc991ca0bf2378124caddb1815bfb5fa602bc8a3156","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-07T19:24:47Z","title_canon_sha256":"fc6dd574f4b70c77d012721db0d31fca26e9e231c280eb77170f042755595421"},"schema_version":"1.0","source":{"id":"2308.03882","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.03882","created_at":"2026-07-05T06:53:43Z"},{"alias_kind":"arxiv_version","alias_value":"2308.03882v2","created_at":"2026-07-05T06:53:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.03882","created_at":"2026-07-05T06:53:43Z"},{"alias_kind":"pith_short_12","alias_value":"FU7VR4VYHTZA","created_at":"2026-07-05T06:53:43Z"},{"alias_kind":"pith_short_16","alias_value":"FU7VR4VYHTZAPSOJ","created_at":"2026-07-05T06:53:43Z"},{"alias_kind":"pith_short_8","alias_value":"FU7VR4VY","created_at":"2026-07-05T06:53:43Z"}],"graph_snapshots":[{"event_id":"sha256:9eb50468b7cd76694a5f484465139a95fbaef72bdbfa7677f93fedc359349ec4","target":"graph","created_at":"2026-07-05T06:53:43Z","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/2308.03882/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) methods strike a balance between exploration and exploitation by conservative value estimation -- penalizing values of unseen states and actions. Model-free methods penalize values at all unseen actions, while model-based methods are able to further exploit unseen states via model rollouts. However, such methods are handicapped in their ability to find unseen states far away from the available offline data due to two factors -- (a) very short rollout horizons in models due to cascading model errors, and (b) model rollouts originating solely from states obser","authors_text":"Ashwin Kalyan, Dhruv Batra, Gaurav Sukhatme, Govind Thattai, Nirbhay Modhe, Qiaozi Gao","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-07T19:24:47Z","title":"Exploiting Generalization in Offline Reinforcement Learning via Unseen State Augmentations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.03882","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":"sha256:6a41abd11c40891d773d83e14962eba1ed54b5e16f321e7510ec63a9c29ca0bb","target":"record","created_at":"2026-07-05T06:53:43Z","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":"30a186b3e838f9e58084ddc991ca0bf2378124caddb1815bfb5fa602bc8a3156","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-07T19:24:47Z","title_canon_sha256":"fc6dd574f4b70c77d012721db0d31fca26e9e231c280eb77170f042755595421"},"schema_version":"1.0","source":{"id":"2308.03882","kind":"arxiv","version":2}},"canonical_sha256":"2d3f58f2b83cf207c9c9aa6c70564070dba2531cb98a12114550b2e8fb960b29","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d3f58f2b83cf207c9c9aa6c70564070dba2531cb98a12114550b2e8fb960b29","first_computed_at":"2026-07-05T06:53:43.199803Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:53:43.199803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7Hp57GTzcTcIQ7IMIkOJUbWzigi1yUuPV7Q42U+nSpYbZtMsaGODDBGFRkgCRUWfCpUCTW0zSY/NXswDP7WEAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:53:43.200336Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.03882","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a41abd11c40891d773d83e14962eba1ed54b5e16f321e7510ec63a9c29ca0bb","sha256:9eb50468b7cd76694a5f484465139a95fbaef72bdbfa7677f93fedc359349ec4"],"state_sha256":"523a9c13370c2d3d2a2915729ed2408efaf5c7e051c190e5f3c180b695a9c259"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y5pKnCponIAQ/zH/DRLrmiB49sdaUkZXwSAxl/VkKruJzsTYiO9Nnduj3gH7cnOBcYtSrmzlf9ks+KYEmepTAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T16:14:43.139816Z","bundle_sha256":"67a02dd8abd2ef355ddbf477fbd0e662ef9583cbcc58c89469d3a50f13873c58"}}