{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:7IULSHXG43JCXXHSWPF65LFK5R","short_pith_number":"pith:7IULSHXG","canonical_record":{"source":{"id":"2502.18955","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-26T09:08:47Z","cross_cats_sorted":[],"title_canon_sha256":"46989a99fd60bc3236af3e5b2dd1bba8721fc6f16771db860c72ecc3bd862de5","abstract_canon_sha256":"747a8bf0bd5a3f1b4c2a491ce5a2693faeafdb891d884bde33a244c6b2758503"},"schema_version":"1.0"},"canonical_sha256":"fa28b91ee6e6d22bdcf2b3cbeeacaaec547247ad03caf917d8d328ce7d53b60c","source":{"kind":"arxiv","id":"2502.18955","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.18955","created_at":"2026-07-05T10:20:23Z"},{"alias_kind":"arxiv_version","alias_value":"2502.18955v1","created_at":"2026-07-05T10:20:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.18955","created_at":"2026-07-05T10:20:23Z"},{"alias_kind":"pith_short_12","alias_value":"7IULSHXG43JC","created_at":"2026-07-05T10:20:23Z"},{"alias_kind":"pith_short_16","alias_value":"7IULSHXG43JCXXHS","created_at":"2026-07-05T10:20:23Z"},{"alias_kind":"pith_short_8","alias_value":"7IULSHXG","created_at":"2026-07-05T10:20:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:7IULSHXG43JCXXHSWPF65LFK5R","target":"record","payload":{"canonical_record":{"source":{"id":"2502.18955","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-26T09:08:47Z","cross_cats_sorted":[],"title_canon_sha256":"46989a99fd60bc3236af3e5b2dd1bba8721fc6f16771db860c72ecc3bd862de5","abstract_canon_sha256":"747a8bf0bd5a3f1b4c2a491ce5a2693faeafdb891d884bde33a244c6b2758503"},"schema_version":"1.0"},"canonical_sha256":"fa28b91ee6e6d22bdcf2b3cbeeacaaec547247ad03caf917d8d328ce7d53b60c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:20:23.919443Z","signature_b64":"BX3WUJ9LqdVPE8iohDB7si2OH3rK0Jc+b8F7Tk/av+EGFo3HUGjSD4R+q6/P6ijvpOp/bV4FmSZnv8+SVl11CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa28b91ee6e6d22bdcf2b3cbeeacaaec547247ad03caf917d8d328ce7d53b60c","last_reissued_at":"2026-07-05T10:20:23.918983Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:20:23.918983Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.18955","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":"2026-07-05T10:20:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MyzFtVjcn4AFbItH44doC+hNXb1xXD9xocMmZg/Wq8Mn64thfjGAQtqIXsG2WXppO3vLMmUkRhFucjdok2F4Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:00:56.504013Z"},"content_sha256":"5a3990376b8813767bd0996f938fe2b59e84d99f05a286a8bab157aa8fa66443","schema_version":"1.0","event_id":"sha256:5a3990376b8813767bd0996f938fe2b59e84d99f05a286a8bab157aa8fa66443"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:7IULSHXG43JCXXHSWPF65LFK5R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fewer May Be Better: Enhancing Offline Reinforcement Learning with Reduced Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chenghao Li, Chengjie Wu, Chongjie Zhang, Dianyu Zhong, Hao Hu, Qianchuan Zhao, Quanwei Wang, Xu bo, Yiqin Yang, Yuhua Jiang, Ziyou Zhang","submitted_at":"2025-02-26T09:08:47Z","abstract_excerpt":"Offline reinforcement learning (RL) represents a significant shift in RL research, allowing agents to learn from pre-collected datasets without further interaction with the environment. A key, yet underexplored, challenge in offline RL is selecting an optimal subset of the offline dataset that enhances both algorithm performance and training efficiency. Reducing dataset size can also reveal the minimal data requirements necessary for solving similar problems. In response to this challenge, we introduce ReDOR (Reduced Datasets for Offline RL), a method that frames dataset selection as a gradien"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.18955","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/2502.18955/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":"2026-07-05T10:20:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CpqnpH/lIhvPDLoHRp+9TCcg3f98EgYmoYB9WNGyxR/k8heTx8t2WTerWn/W8qiwGAX5q5ZANeZx7FB94by6CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:00:56.504403Z"},"content_sha256":"ea3dd3a2ab2ec2855e30aea4567f374bca353c7cf9f66b6c1d28f72f6326a8f0","schema_version":"1.0","event_id":"sha256:ea3dd3a2ab2ec2855e30aea4567f374bca353c7cf9f66b6c1d28f72f6326a8f0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7IULSHXG43JCXXHSWPF65LFK5R/bundle.json","state_url":"https://pith.science/pith/7IULSHXG43JCXXHSWPF65LFK5R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7IULSHXG43JCXXHSWPF65LFK5R/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":"2026-07-07T08:00:56Z","links":{"resolver":"https://pith.science/pith/7IULSHXG43JCXXHSWPF65LFK5R","bundle":"https://pith.science/pith/7IULSHXG43JCXXHSWPF65LFK5R/bundle.json","state":"https://pith.science/pith/7IULSHXG43JCXXHSWPF65LFK5R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7IULSHXG43JCXXHSWPF65LFK5R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7IULSHXG43JCXXHSWPF65LFK5R","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":"747a8bf0bd5a3f1b4c2a491ce5a2693faeafdb891d884bde33a244c6b2758503","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-26T09:08:47Z","title_canon_sha256":"46989a99fd60bc3236af3e5b2dd1bba8721fc6f16771db860c72ecc3bd862de5"},"schema_version":"1.0","source":{"id":"2502.18955","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.18955","created_at":"2026-07-05T10:20:23Z"},{"alias_kind":"arxiv_version","alias_value":"2502.18955v1","created_at":"2026-07-05T10:20:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.18955","created_at":"2026-07-05T10:20:23Z"},{"alias_kind":"pith_short_12","alias_value":"7IULSHXG43JC","created_at":"2026-07-05T10:20:23Z"},{"alias_kind":"pith_short_16","alias_value":"7IULSHXG43JCXXHS","created_at":"2026-07-05T10:20:23Z"},{"alias_kind":"pith_short_8","alias_value":"7IULSHXG","created_at":"2026-07-05T10:20:23Z"}],"graph_snapshots":[{"event_id":"sha256:ea3dd3a2ab2ec2855e30aea4567f374bca353c7cf9f66b6c1d28f72f6326a8f0","target":"graph","created_at":"2026-07-05T10:20:23Z","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/2502.18955/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) represents a significant shift in RL research, allowing agents to learn from pre-collected datasets without further interaction with the environment. A key, yet underexplored, challenge in offline RL is selecting an optimal subset of the offline dataset that enhances both algorithm performance and training efficiency. Reducing dataset size can also reveal the minimal data requirements necessary for solving similar problems. In response to this challenge, we introduce ReDOR (Reduced Datasets for Offline RL), a method that frames dataset selection as a gradien","authors_text":"Chenghao Li, Chengjie Wu, Chongjie Zhang, Dianyu Zhong, Hao Hu, Qianchuan Zhao, Quanwei Wang, Xu bo, Yiqin Yang, Yuhua Jiang, Ziyou Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-26T09:08:47Z","title":"Fewer May Be Better: Enhancing Offline Reinforcement Learning with Reduced Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.18955","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":"sha256:5a3990376b8813767bd0996f938fe2b59e84d99f05a286a8bab157aa8fa66443","target":"record","created_at":"2026-07-05T10:20:23Z","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":"747a8bf0bd5a3f1b4c2a491ce5a2693faeafdb891d884bde33a244c6b2758503","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-26T09:08:47Z","title_canon_sha256":"46989a99fd60bc3236af3e5b2dd1bba8721fc6f16771db860c72ecc3bd862de5"},"schema_version":"1.0","source":{"id":"2502.18955","kind":"arxiv","version":1}},"canonical_sha256":"fa28b91ee6e6d22bdcf2b3cbeeacaaec547247ad03caf917d8d328ce7d53b60c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fa28b91ee6e6d22bdcf2b3cbeeacaaec547247ad03caf917d8d328ce7d53b60c","first_computed_at":"2026-07-05T10:20:23.918983Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:20:23.918983Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BX3WUJ9LqdVPE8iohDB7si2OH3rK0Jc+b8F7Tk/av+EGFo3HUGjSD4R+q6/P6ijvpOp/bV4FmSZnv8+SVl11CA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:20:23.919443Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.18955","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a3990376b8813767bd0996f938fe2b59e84d99f05a286a8bab157aa8fa66443","sha256:ea3dd3a2ab2ec2855e30aea4567f374bca353c7cf9f66b6c1d28f72f6326a8f0"],"state_sha256":"f41f7b5fe43c864a55f9cd974b60592f2af6db796345e312cccd9d9beea3ce43"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pklOPgGyzoH3Qf/lFGyfjfekmFWgZQlOhf+WTqeUnjvQjnti4WGQ59YA8ITofa9yv5Av/Zvl25BOZgRrLgYGBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T08:00:56.506415Z","bundle_sha256":"a88a5c3b1f5cf55929115ff0cd87e83740b1db58f6ee6b44e08e2bec824134fb"}}