{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:TYLN5EKD4MBHTIELJVDFTVXWBW","short_pith_number":"pith:TYLN5EKD","canonical_record":{"source":{"id":"2607.26509","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-29T06:18:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d235f9572321387eac7b8dac38b58ad374d24a643ca5a5a9c4a42afd2b5503ae","abstract_canon_sha256":"528eac7726da8e19b882e8c1c73f04e95e76165d5cc940720064cb08cdbe01ee"},"schema_version":"1.0"},"canonical_sha256":"9e16de9143e30279a08b4d4659d6f60db66f59f79df9a819eae7cc40c5b1402a","source":{"kind":"arxiv","id":"2607.26509","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.26509","created_at":"2026-07-30T01:20:44Z"},{"alias_kind":"arxiv_version","alias_value":"2607.26509v1","created_at":"2026-07-30T01:20:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26509","created_at":"2026-07-30T01:20:44Z"},{"alias_kind":"pith_short_12","alias_value":"TYLN5EKD4MBH","created_at":"2026-07-30T01:20:44Z"},{"alias_kind":"pith_short_16","alias_value":"TYLN5EKD4MBHTIEL","created_at":"2026-07-30T01:20:44Z"},{"alias_kind":"pith_short_8","alias_value":"TYLN5EKD","created_at":"2026-07-30T01:20:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:TYLN5EKD4MBHTIELJVDFTVXWBW","target":"record","payload":{"canonical_record":{"source":{"id":"2607.26509","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-29T06:18:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d235f9572321387eac7b8dac38b58ad374d24a643ca5a5a9c4a42afd2b5503ae","abstract_canon_sha256":"528eac7726da8e19b882e8c1c73f04e95e76165d5cc940720064cb08cdbe01ee"},"schema_version":"1.0"},"canonical_sha256":"9e16de9143e30279a08b4d4659d6f60db66f59f79df9a819eae7cc40c5b1402a","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e16de9143e30279a08b4d4659d6f60db66f59f79df9a819eae7cc40c5b1402a","last_reissued_at":"2026-07-30T01:20:44.121382Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:20:44.121382Z"},"source_kind":"arxiv","source_id":"2607.26509","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":"2026-07-30T01:20:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CoWau/JE9OObdfSA9RhT8YE7xaQ+7P93H9kCOLz6PpQMzy3g9aFb2j9czn9EIsWLmxJzAWb+0piRTfuTOdSrDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T07:07:28.207088Z"},"content_sha256":"a0b5da036717f3788879e5ec655a632c93aaec70027cc62931109c190cdebdf0","schema_version":"1.0","event_id":"sha256:a0b5da036717f3788879e5ec655a632c93aaec70027cc62931109c190cdebdf0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:TYLN5EKD4MBHTIELJVDFTVXWBW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Collaborative Weighting with Pessimistic Critic for Mitigating Overestimation in Off-Policy Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Gong Gao, Guojie Chen, Weidong Zhao, Xianhui Liu, Xiao Lai, Ziqi Xie","submitted_at":"2026-07-29T06:18:19Z","abstract_excerpt":"Deep off-policy reinforcement learning algorithms for continuous control typically rely on neural value function approximation to guide policy improvement. However, temporal-difference (TD) learning introduces noisy targets, resulting in non-stationary optimization, while greedy policy updates amplify early-stage estimation errors. The recursive propagation of such errors leads to persistent overestimation bias and degraded training stability in actor-critic methods. Existing approaches attempt to alleviate this issue via prioritized sampling or modified value learning objectives, but often ov"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26509","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/2607.26509/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":"2026-07-30T01:20:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CCovuym4gLRDou/RyyX6+cfOvd5Bcuk+ElR1TSgA/2DasVTcuXcuxAX/toWH5HyNZRtVRMNhsZTAvbe25X0VCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T07:07:28.207637Z"},"content_sha256":"c8b72641228261f6288a769e796decb3ede43c8f4c6bc7a84f2b8a0d7449d1f8","schema_version":"1.0","event_id":"sha256:c8b72641228261f6288a769e796decb3ede43c8f4c6bc7a84f2b8a0d7449d1f8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TYLN5EKD4MBHTIELJVDFTVXWBW/bundle.json","state_url":"https://pith.science/pith/TYLN5EKD4MBHTIELJVDFTVXWBW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TYLN5EKD4MBHTIELJVDFTVXWBW/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":"2026-08-07T07:07:28Z","links":{"resolver":"https://pith.science/pith/TYLN5EKD4MBHTIELJVDFTVXWBW","bundle":"https://pith.science/pith/TYLN5EKD4MBHTIELJVDFTVXWBW/bundle.json","state":"https://pith.science/pith/TYLN5EKD4MBHTIELJVDFTVXWBW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TYLN5EKD4MBHTIELJVDFTVXWBW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TYLN5EKD4MBHTIELJVDFTVXWBW","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":"528eac7726da8e19b882e8c1c73f04e95e76165d5cc940720064cb08cdbe01ee","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-29T06:18:19Z","title_canon_sha256":"d235f9572321387eac7b8dac38b58ad374d24a643ca5a5a9c4a42afd2b5503ae"},"schema_version":"1.0","source":{"id":"2607.26509","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.26509","created_at":"2026-07-30T01:20:44Z"},{"alias_kind":"arxiv_version","alias_value":"2607.26509v1","created_at":"2026-07-30T01:20:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26509","created_at":"2026-07-30T01:20:44Z"},{"alias_kind":"pith_short_12","alias_value":"TYLN5EKD4MBH","created_at":"2026-07-30T01:20:44Z"},{"alias_kind":"pith_short_16","alias_value":"TYLN5EKD4MBHTIEL","created_at":"2026-07-30T01:20:44Z"},{"alias_kind":"pith_short_8","alias_value":"TYLN5EKD","created_at":"2026-07-30T01:20:44Z"}],"graph_snapshots":[{"event_id":"sha256:c8b72641228261f6288a769e796decb3ede43c8f4c6bc7a84f2b8a0d7449d1f8","target":"graph","created_at":"2026-07-30T01:20:44Z","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/2607.26509/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep off-policy reinforcement learning algorithms for continuous control typically rely on neural value function approximation to guide policy improvement. However, temporal-difference (TD) learning introduces noisy targets, resulting in non-stationary optimization, while greedy policy updates amplify early-stage estimation errors. The recursive propagation of such errors leads to persistent overestimation bias and degraded training stability in actor-critic methods. Existing approaches attempt to alleviate this issue via prioritized sampling or modified value learning objectives, but often ov","authors_text":"Gong Gao, Guojie Chen, Weidong Zhao, Xianhui Liu, Xiao Lai, Ziqi Xie","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-29T06:18:19Z","title":"Collaborative Weighting with Pessimistic Critic for Mitigating Overestimation in Off-Policy Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26509","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:a0b5da036717f3788879e5ec655a632c93aaec70027cc62931109c190cdebdf0","target":"record","created_at":"2026-07-30T01:20:44Z","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":"528eac7726da8e19b882e8c1c73f04e95e76165d5cc940720064cb08cdbe01ee","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-29T06:18:19Z","title_canon_sha256":"d235f9572321387eac7b8dac38b58ad374d24a643ca5a5a9c4a42afd2b5503ae"},"schema_version":"1.0","source":{"id":"2607.26509","kind":"arxiv","version":1}},"canonical_sha256":"9e16de9143e30279a08b4d4659d6f60db66f59f79df9a819eae7cc40c5b1402a","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e16de9143e30279a08b4d4659d6f60db66f59f79df9a819eae7cc40c5b1402a","first_computed_at":"2026-07-30T01:20:44.121382Z","kind":"pith_receipt","last_reissued_at":"2026-07-30T01:20:44.121382Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.26509","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0b5da036717f3788879e5ec655a632c93aaec70027cc62931109c190cdebdf0","sha256:c8b72641228261f6288a769e796decb3ede43c8f4c6bc7a84f2b8a0d7449d1f8"],"state_sha256":"d81f0560c2ce2dafe5df171cb8be30e8c1a0a1fa2bc1b5c59b219c8b727a1cdf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OxcvqlbtgjCMK4JIFNeKSjZKuI+rdwodKIIcOgc0Or6B2o8O1w+2JrMnjtamwX1kSpNUQURVdjp+OoNeTaLPCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T07:07:28.211299Z","bundle_sha256":"dfeb254489741afe36f035708eb64750369b1b88b21260f07da987f1c2a0c4f7"}}