{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:I2AHBZDENJGPCHMDP3UOFFQBJJ","short_pith_number":"pith:I2AHBZDE","canonical_record":{"source":{"id":"2411.07934","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-12T17:04:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a93d42fabef5027ad2a5612190bc5ea963221720feb84d252ff68d9e8bf99290","abstract_canon_sha256":"80e0a65e3673234e0649c3f9b8529346f8b291452f677d206456ae6b734888ea"},"schema_version":"1.0"},"canonical_sha256":"468070e4646a4cf11d837ee8e296014a6ead4366a4246bd3fa008d026058944a","source":{"kind":"arxiv","id":"2411.07934","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.07934","created_at":"2026-07-05T09:34:40Z"},{"alias_kind":"arxiv_version","alias_value":"2411.07934v2","created_at":"2026-07-05T09:34:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.07934","created_at":"2026-07-05T09:34:40Z"},{"alias_kind":"pith_short_12","alias_value":"I2AHBZDENJGP","created_at":"2026-07-05T09:34:40Z"},{"alias_kind":"pith_short_16","alias_value":"I2AHBZDENJGPCHMD","created_at":"2026-07-05T09:34:40Z"},{"alias_kind":"pith_short_8","alias_value":"I2AHBZDE","created_at":"2026-07-05T09:34:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:I2AHBZDENJGPCHMDP3UOFFQBJJ","target":"record","payload":{"canonical_record":{"source":{"id":"2411.07934","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-12T17:04:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a93d42fabef5027ad2a5612190bc5ea963221720feb84d252ff68d9e8bf99290","abstract_canon_sha256":"80e0a65e3673234e0649c3f9b8529346f8b291452f677d206456ae6b734888ea"},"schema_version":"1.0"},"canonical_sha256":"468070e4646a4cf11d837ee8e296014a6ead4366a4246bd3fa008d026058944a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:34:40.296114Z","signature_b64":"zQJhWphVH3gJ7YO5+d2w5CfjXAq9WG7lcvCH69FXuO8pHgQTVNS0AnMdCOroJpnc1ErIWCPCSBcMiwL1s1p5CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"468070e4646a4cf11d837ee8e296014a6ead4366a4246bd3fa008d026058944a","last_reissued_at":"2026-07-05T09:34:40.295630Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:34:40.295630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.07934","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":"2026-07-05T09:34:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Uyzbx8ByP12EU9B4GylihMxxtw9TC8WY5Lj6Zu/YpIJ1UgzwxwUEiCPE7S/e34xGdzJ5MKE9IHfJ1/yYNDZOBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T14:31:38.177724Z"},"content_sha256":"bdec7aae9f78dbd7095922efa8724b3c34b9bf6dedb74e8c8d9547b9237c0ef0","schema_version":"1.0","event_id":"sha256:bdec7aae9f78dbd7095922efa8724b3c34b9bf6dedb74e8c8d9547b9237c0ef0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:I2AHBZDENJGPCHMDP3UOFFQBJJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Doubly Mild Generalization for Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Qi Wang, Xiangyang Ji, Yixiu Mao, Yuhang Jiang, Yun Qu","submitted_at":"2024-11-12T17:04:56Z","abstract_excerpt":"Offline Reinforcement Learning (RL) suffers from the extrapolation error and value overestimation. From a generalization perspective, this issue can be attributed to the over-generalization of value functions or policies towards out-of-distribution (OOD) actions. Significant efforts have been devoted to mitigating such generalization, and recent in-sample learning approaches have further succeeded in entirely eschewing it. Nevertheless, we show that mild generalization beyond the dataset can be trusted and leveraged to improve performance under certain conditions. To appropriately exploit gene"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.07934","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/2411.07934/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":"2026-07-05T09:34:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/453/ogCjabYfaZq2v5SmDrzg3NhPqcQ2h+kC0P4Qx9Sv1Nt6QzgSO+BeZWSDZ6XzD0bjcEI7KjmLxbQ/Y7hBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T14:31:38.178368Z"},"content_sha256":"5b69cdd1ac2bbf6457a5c32beba16f213c7a2a96584bd42c584de569ba92f309","schema_version":"1.0","event_id":"sha256:5b69cdd1ac2bbf6457a5c32beba16f213c7a2a96584bd42c584de569ba92f309"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I2AHBZDENJGPCHMDP3UOFFQBJJ/bundle.json","state_url":"https://pith.science/pith/I2AHBZDENJGPCHMDP3UOFFQBJJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I2AHBZDENJGPCHMDP3UOFFQBJJ/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":"2026-08-17T14:31:38Z","links":{"resolver":"https://pith.science/pith/I2AHBZDENJGPCHMDP3UOFFQBJJ","bundle":"https://pith.science/pith/I2AHBZDENJGPCHMDP3UOFFQBJJ/bundle.json","state":"https://pith.science/pith/I2AHBZDENJGPCHMDP3UOFFQBJJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I2AHBZDENJGPCHMDP3UOFFQBJJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:I2AHBZDENJGPCHMDP3UOFFQBJJ","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":"80e0a65e3673234e0649c3f9b8529346f8b291452f677d206456ae6b734888ea","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-12T17:04:56Z","title_canon_sha256":"a93d42fabef5027ad2a5612190bc5ea963221720feb84d252ff68d9e8bf99290"},"schema_version":"1.0","source":{"id":"2411.07934","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.07934","created_at":"2026-07-05T09:34:40Z"},{"alias_kind":"arxiv_version","alias_value":"2411.07934v2","created_at":"2026-07-05T09:34:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.07934","created_at":"2026-07-05T09:34:40Z"},{"alias_kind":"pith_short_12","alias_value":"I2AHBZDENJGP","created_at":"2026-07-05T09:34:40Z"},{"alias_kind":"pith_short_16","alias_value":"I2AHBZDENJGPCHMD","created_at":"2026-07-05T09:34:40Z"},{"alias_kind":"pith_short_8","alias_value":"I2AHBZDE","created_at":"2026-07-05T09:34:40Z"}],"graph_snapshots":[{"event_id":"sha256:5b69cdd1ac2bbf6457a5c32beba16f213c7a2a96584bd42c584de569ba92f309","target":"graph","created_at":"2026-07-05T09:34:40Z","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/2411.07934/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline Reinforcement Learning (RL) suffers from the extrapolation error and value overestimation. From a generalization perspective, this issue can be attributed to the over-generalization of value functions or policies towards out-of-distribution (OOD) actions. Significant efforts have been devoted to mitigating such generalization, and recent in-sample learning approaches have further succeeded in entirely eschewing it. Nevertheless, we show that mild generalization beyond the dataset can be trusted and leveraged to improve performance under certain conditions. To appropriately exploit gene","authors_text":"Qi Wang, Xiangyang Ji, Yixiu Mao, Yuhang Jiang, Yun Qu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-12T17:04:56Z","title":"Doubly Mild Generalization for Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.07934","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:bdec7aae9f78dbd7095922efa8724b3c34b9bf6dedb74e8c8d9547b9237c0ef0","target":"record","created_at":"2026-07-05T09:34:40Z","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":"80e0a65e3673234e0649c3f9b8529346f8b291452f677d206456ae6b734888ea","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-12T17:04:56Z","title_canon_sha256":"a93d42fabef5027ad2a5612190bc5ea963221720feb84d252ff68d9e8bf99290"},"schema_version":"1.0","source":{"id":"2411.07934","kind":"arxiv","version":2}},"canonical_sha256":"468070e4646a4cf11d837ee8e296014a6ead4366a4246bd3fa008d026058944a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"468070e4646a4cf11d837ee8e296014a6ead4366a4246bd3fa008d026058944a","first_computed_at":"2026-07-05T09:34:40.295630Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:34:40.295630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zQJhWphVH3gJ7YO5+d2w5CfjXAq9WG7lcvCH69FXuO8pHgQTVNS0AnMdCOroJpnc1ErIWCPCSBcMiwL1s1p5CA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:34:40.296114Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.07934","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bdec7aae9f78dbd7095922efa8724b3c34b9bf6dedb74e8c8d9547b9237c0ef0","sha256:5b69cdd1ac2bbf6457a5c32beba16f213c7a2a96584bd42c584de569ba92f309"],"state_sha256":"347176f5e5a96547da965a55adc667978935df934f4cfce29a2722babf542aad"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xyak5iTuxcGApn/am4wkZSTU5T3oSUnZzsoFq/1NuJyilDWZ/paPByseMZfHtV5FC4KjnzsVBRKL5Q3g1S6RCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T14:31:38.184077Z","bundle_sha256":"1a58169a51438d06f573b658e4092f02a4d6ea51cdcc0bbd82cf4baa148f8943"}}