{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:46BPFQR65Z3KCEG4ULUKQFXU7X","short_pith_number":"pith:46BPFQR6","canonical_record":{"source":{"id":"2412.16848","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-22T04:18:02Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"c96346afb469f62620ff383b7c2e62b03611ae03df91273854eb618f3de184ba","abstract_canon_sha256":"8f312d49edb565700b071f312f1268c1a21953e1b012502757ba5b342a7c79e4"},"schema_version":"1.0"},"canonical_sha256":"e782f2c23eee76a110dca2e8a816f4fde785c0253f7cc971bbd5c9e03c64ca46","source":{"kind":"arxiv","id":"2412.16848","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.16848","created_at":"2026-07-05T10:32:36Z"},{"alias_kind":"arxiv_version","alias_value":"2412.16848v2","created_at":"2026-07-05T10:32:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16848","created_at":"2026-07-05T10:32:36Z"},{"alias_kind":"pith_short_12","alias_value":"46BPFQR65Z3K","created_at":"2026-07-05T10:32:36Z"},{"alias_kind":"pith_short_16","alias_value":"46BPFQR65Z3KCEG4","created_at":"2026-07-05T10:32:36Z"},{"alias_kind":"pith_short_8","alias_value":"46BPFQR6","created_at":"2026-07-05T10:32:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:46BPFQR65Z3KCEG4ULUKQFXU7X","target":"record","payload":{"canonical_record":{"source":{"id":"2412.16848","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-22T04:18:02Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"c96346afb469f62620ff383b7c2e62b03611ae03df91273854eb618f3de184ba","abstract_canon_sha256":"8f312d49edb565700b071f312f1268c1a21953e1b012502757ba5b342a7c79e4"},"schema_version":"1.0"},"canonical_sha256":"e782f2c23eee76a110dca2e8a816f4fde785c0253f7cc971bbd5c9e03c64ca46","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:32:36.056746Z","signature_b64":"dCb8bZdN6vaw+/SJtJmFyy+/8OSvhZ4JIY0fdpDJQ695trbqarqfo3f9WxJ+Y5qxXvd7ahIA5aiJu/e0fSFuBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e782f2c23eee76a110dca2e8a816f4fde785c0253f7cc971bbd5c9e03c64ca46","last_reissued_at":"2026-07-05T10:32:36.055773Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:32:36.055773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.16848","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":"2026-07-05T10:32:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"94MPO2Kh3ycyO3n6j+Sopv3gdYDTjEtzlnFPpoWMEPO6nEck6cvs43uzKrUnSlAoRUAbnEUhz7py6OLNJLGRAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T09:22:47.861073Z"},"content_sha256":"854bb722243dda640c866cbaab97ac20b7109c55d7c237f8a5418b875ac0e6b1","schema_version":"1.0","event_id":"sha256:854bb722243dda640c866cbaab97ac20b7109c55d7c237f8a5418b875ac0e6b1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:46BPFQR65Z3KCEG4ULUKQFXU7X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ACL-QL: Adaptive Conservative Level in Q-Learning for Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Chengxiang Yin, Chi Harold Liu, Feiferi Feng, Jian Tang, Kun Wu, Yinuo Zhao, Zhengping Che, Zhiyuan Xu","submitted_at":"2024-12-22T04:18:02Z","abstract_excerpt":"Offline Reinforcement Learning (RL), which operates solely on static datasets without further interactions with the environment, provides an appealing alternative to learning a safe and promising control policy. The prevailing methods typically learn a conservative policy to mitigate the problem of Q-value overestimation, but it is prone to overdo it, leading to an overly conservative policy. Moreover, they optimize all samples equally with fixed constraints, lacking the nuanced ability to control conservative levels in a fine-grained manner. Consequently, this limitation results in a performa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16848","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/2412.16848/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":"2026-07-05T10:32:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xnqog9Yd4uNTHGwszEVnHfZDz0U724HM1DoT9jwOJgUCI3rTsmqAZJ9LF9o3emxtaGRZAK4AuliyrVGnFSNqCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T09:22:47.861648Z"},"content_sha256":"64cd66fcea0e346c3839656bb4f900c35c6b8e2b5b6e7b59d6f0fbc68ca83610","schema_version":"1.0","event_id":"sha256:64cd66fcea0e346c3839656bb4f900c35c6b8e2b5b6e7b59d6f0fbc68ca83610"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/46BPFQR65Z3KCEG4ULUKQFXU7X/bundle.json","state_url":"https://pith.science/pith/46BPFQR65Z3KCEG4ULUKQFXU7X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/46BPFQR65Z3KCEG4ULUKQFXU7X/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":"2026-08-23T09:22:47Z","links":{"resolver":"https://pith.science/pith/46BPFQR65Z3KCEG4ULUKQFXU7X","bundle":"https://pith.science/pith/46BPFQR65Z3KCEG4ULUKQFXU7X/bundle.json","state":"https://pith.science/pith/46BPFQR65Z3KCEG4ULUKQFXU7X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/46BPFQR65Z3KCEG4ULUKQFXU7X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:46BPFQR65Z3KCEG4ULUKQFXU7X","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":"8f312d49edb565700b071f312f1268c1a21953e1b012502757ba5b342a7c79e4","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-22T04:18:02Z","title_canon_sha256":"c96346afb469f62620ff383b7c2e62b03611ae03df91273854eb618f3de184ba"},"schema_version":"1.0","source":{"id":"2412.16848","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.16848","created_at":"2026-07-05T10:32:36Z"},{"alias_kind":"arxiv_version","alias_value":"2412.16848v2","created_at":"2026-07-05T10:32:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16848","created_at":"2026-07-05T10:32:36Z"},{"alias_kind":"pith_short_12","alias_value":"46BPFQR65Z3K","created_at":"2026-07-05T10:32:36Z"},{"alias_kind":"pith_short_16","alias_value":"46BPFQR65Z3KCEG4","created_at":"2026-07-05T10:32:36Z"},{"alias_kind":"pith_short_8","alias_value":"46BPFQR6","created_at":"2026-07-05T10:32:36Z"}],"graph_snapshots":[{"event_id":"sha256:64cd66fcea0e346c3839656bb4f900c35c6b8e2b5b6e7b59d6f0fbc68ca83610","target":"graph","created_at":"2026-07-05T10:32:36Z","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/2412.16848/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline Reinforcement Learning (RL), which operates solely on static datasets without further interactions with the environment, provides an appealing alternative to learning a safe and promising control policy. The prevailing methods typically learn a conservative policy to mitigate the problem of Q-value overestimation, but it is prone to overdo it, leading to an overly conservative policy. Moreover, they optimize all samples equally with fixed constraints, lacking the nuanced ability to control conservative levels in a fine-grained manner. Consequently, this limitation results in a performa","authors_text":"Chengxiang Yin, Chi Harold Liu, Feiferi Feng, Jian Tang, Kun Wu, Yinuo Zhao, Zhengping Che, Zhiyuan Xu","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-22T04:18:02Z","title":"ACL-QL: Adaptive Conservative Level in Q-Learning for Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16848","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":"sha256:854bb722243dda640c866cbaab97ac20b7109c55d7c237f8a5418b875ac0e6b1","target":"record","created_at":"2026-07-05T10:32:36Z","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":"8f312d49edb565700b071f312f1268c1a21953e1b012502757ba5b342a7c79e4","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-22T04:18:02Z","title_canon_sha256":"c96346afb469f62620ff383b7c2e62b03611ae03df91273854eb618f3de184ba"},"schema_version":"1.0","source":{"id":"2412.16848","kind":"arxiv","version":2}},"canonical_sha256":"e782f2c23eee76a110dca2e8a816f4fde785c0253f7cc971bbd5c9e03c64ca46","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e782f2c23eee76a110dca2e8a816f4fde785c0253f7cc971bbd5c9e03c64ca46","first_computed_at":"2026-07-05T10:32:36.055773Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:32:36.055773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dCb8bZdN6vaw+/SJtJmFyy+/8OSvhZ4JIY0fdpDJQ695trbqarqfo3f9WxJ+Y5qxXvd7ahIA5aiJu/e0fSFuBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:32:36.056746Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.16848","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:854bb722243dda640c866cbaab97ac20b7109c55d7c237f8a5418b875ac0e6b1","sha256:64cd66fcea0e346c3839656bb4f900c35c6b8e2b5b6e7b59d6f0fbc68ca83610"],"state_sha256":"432f8ecb33152e1d888476d231afae94570747920afa83d4e1a5fd39adefe12a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MlamRzh4l0YJ1swKzrb7OSoRRmnmAU3oKyGktq+eZH3DNmMNhbqzYWdLSu/1wO206d1XgN1ME1kDdAn2jMc2Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T09:22:47.866949Z","bundle_sha256":"ed4ffd6f5d4ee1779ee95fe05af49a17bec5a4582c49e1dd3cd24429c2b6b8fe"}}