{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:UPPGNIWXQASJV3LW2USQ22WCNA","short_pith_number":"pith:UPPGNIWX","canonical_record":{"source":{"id":"2607.21302","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-23T13:26:57Z","cross_cats_sorted":[],"title_canon_sha256":"9bf16fe2b346de5fb4f6f3f33c753505db0e972975b3001682b30fae629bb3e5","abstract_canon_sha256":"e8fe2c0e8ecea0ef4efbe397ae7616f142bdf1e8e443f5aa6f674174bdd867bb"},"schema_version":"1.0"},"canonical_sha256":"a3de66a2d780249aed76d5250d6ac2680fce3d19eb0bdffc93997574d21fc056","source":{"kind":"arxiv","id":"2607.21302","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.21302","created_at":"2026-07-24T01:24:24Z"},{"alias_kind":"arxiv_version","alias_value":"2607.21302v1","created_at":"2026-07-24T01:24:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21302","created_at":"2026-07-24T01:24:24Z"},{"alias_kind":"pith_short_12","alias_value":"UPPGNIWXQASJ","created_at":"2026-07-24T01:24:24Z"},{"alias_kind":"pith_short_16","alias_value":"UPPGNIWXQASJV3LW","created_at":"2026-07-24T01:24:24Z"},{"alias_kind":"pith_short_8","alias_value":"UPPGNIWX","created_at":"2026-07-24T01:24:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:UPPGNIWXQASJV3LW2USQ22WCNA","target":"record","payload":{"canonical_record":{"source":{"id":"2607.21302","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-23T13:26:57Z","cross_cats_sorted":[],"title_canon_sha256":"9bf16fe2b346de5fb4f6f3f33c753505db0e972975b3001682b30fae629bb3e5","abstract_canon_sha256":"e8fe2c0e8ecea0ef4efbe397ae7616f142bdf1e8e443f5aa6f674174bdd867bb"},"schema_version":"1.0"},"canonical_sha256":"a3de66a2d780249aed76d5250d6ac2680fce3d19eb0bdffc93997574d21fc056","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-24T01:24:24.533263Z","signature_b64":"AIebYniV69GeRCj7NBBo5vawlTpAYmbTsbNZohHzen0FcDCoqmcrQpA6qxTaunIXZlH71Idt7qa1dBMQFxMaCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3de66a2d780249aed76d5250d6ac2680fce3d19eb0bdffc93997574d21fc056","last_reissued_at":"2026-07-24T01:24:24.532379Z","signature_status":"signed_v1","first_computed_at":"2026-07-24T01:24:24.532379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.21302","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":"2026-07-24T01:24:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KIlcfAdywAGPPtcsMTVODbapZQ+L7WEU5+XJSnZ+sUbG/Jn7sYBplrBGl79g1CHV6cT5fVQFVcruR7ar3Wg/Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:27:00.477432Z"},"content_sha256":"6b4e9b994be71cce351bb97075d192d8967b643bbbbbc6a718f7cadef64d0c90","schema_version":"1.0","event_id":"sha256:6b4e9b994be71cce351bb97075d192d8967b643bbbbbc6a718f7cadef64d0c90"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:UPPGNIWXQASJV3LW2USQ22WCNA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Expert Behavior Prior Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Gong Gao, Ning Jia, Weidong Zhao, Xianhui Liu","submitted_at":"2026-07-23T13:26:57Z","abstract_excerpt":"Behavior prior reinforcement learning (BPRL) has emerged as a promising paradigm to improve sample efficiency in online reinforcement learning (RL) by leveraging policy priors derived from offline demonstrations. However, most existing BPRL methods rely on static offline datasets, which often suffer from low data diversity and suboptimal trajectory quality. This reliance restricts the effectiveness of policy priors, hindering both policy exploitation and stability during online training. Consequently, agents are prone to inefficient exploration and unstable learning dynamics. To address these "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21302","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/2607.21302/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":"2026-07-24T01:24:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xcoBDPo+xkbr9Wm3TVb/OomI7oOM4gc4UUbKTq1WXaiNj9ZO0aSSztRjLBw5QsW68cDHdut6DFbnqF7HJLePDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:27:00.478270Z"},"content_sha256":"9b975dfbf3e0ff9aed235def4c6583821f23eb63f5a33e9fb32898361f3fe070","schema_version":"1.0","event_id":"sha256:9b975dfbf3e0ff9aed235def4c6583821f23eb63f5a33e9fb32898361f3fe070"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UPPGNIWXQASJV3LW2USQ22WCNA/bundle.json","state_url":"https://pith.science/pith/UPPGNIWXQASJV3LW2USQ22WCNA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UPPGNIWXQASJV3LW2USQ22WCNA/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":"2026-08-06T05:27:00Z","links":{"resolver":"https://pith.science/pith/UPPGNIWXQASJV3LW2USQ22WCNA","bundle":"https://pith.science/pith/UPPGNIWXQASJV3LW2USQ22WCNA/bundle.json","state":"https://pith.science/pith/UPPGNIWXQASJV3LW2USQ22WCNA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UPPGNIWXQASJV3LW2USQ22WCNA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UPPGNIWXQASJV3LW2USQ22WCNA","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":"e8fe2c0e8ecea0ef4efbe397ae7616f142bdf1e8e443f5aa6f674174bdd867bb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-23T13:26:57Z","title_canon_sha256":"9bf16fe2b346de5fb4f6f3f33c753505db0e972975b3001682b30fae629bb3e5"},"schema_version":"1.0","source":{"id":"2607.21302","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.21302","created_at":"2026-07-24T01:24:24Z"},{"alias_kind":"arxiv_version","alias_value":"2607.21302v1","created_at":"2026-07-24T01:24:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21302","created_at":"2026-07-24T01:24:24Z"},{"alias_kind":"pith_short_12","alias_value":"UPPGNIWXQASJ","created_at":"2026-07-24T01:24:24Z"},{"alias_kind":"pith_short_16","alias_value":"UPPGNIWXQASJV3LW","created_at":"2026-07-24T01:24:24Z"},{"alias_kind":"pith_short_8","alias_value":"UPPGNIWX","created_at":"2026-07-24T01:24:24Z"}],"graph_snapshots":[{"event_id":"sha256:9b975dfbf3e0ff9aed235def4c6583821f23eb63f5a33e9fb32898361f3fe070","target":"graph","created_at":"2026-07-24T01:24:24Z","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/2607.21302/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Behavior prior reinforcement learning (BPRL) has emerged as a promising paradigm to improve sample efficiency in online reinforcement learning (RL) by leveraging policy priors derived from offline demonstrations. However, most existing BPRL methods rely on static offline datasets, which often suffer from low data diversity and suboptimal trajectory quality. This reliance restricts the effectiveness of policy priors, hindering both policy exploitation and stability during online training. Consequently, agents are prone to inefficient exploration and unstable learning dynamics. To address these ","authors_text":"Gong Gao, Ning Jia, Weidong Zhao, Xianhui Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-23T13:26:57Z","title":"Expert Behavior Prior Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21302","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":"sha256:6b4e9b994be71cce351bb97075d192d8967b643bbbbbc6a718f7cadef64d0c90","target":"record","created_at":"2026-07-24T01:24:24Z","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":"e8fe2c0e8ecea0ef4efbe397ae7616f142bdf1e8e443f5aa6f674174bdd867bb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-23T13:26:57Z","title_canon_sha256":"9bf16fe2b346de5fb4f6f3f33c753505db0e972975b3001682b30fae629bb3e5"},"schema_version":"1.0","source":{"id":"2607.21302","kind":"arxiv","version":1}},"canonical_sha256":"a3de66a2d780249aed76d5250d6ac2680fce3d19eb0bdffc93997574d21fc056","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a3de66a2d780249aed76d5250d6ac2680fce3d19eb0bdffc93997574d21fc056","first_computed_at":"2026-07-24T01:24:24.532379Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-24T01:24:24.532379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AIebYniV69GeRCj7NBBo5vawlTpAYmbTsbNZohHzen0FcDCoqmcrQpA6qxTaunIXZlH71Idt7qa1dBMQFxMaCQ==","signature_status":"signed_v1","signed_at":"2026-07-24T01:24:24.533263Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.21302","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6b4e9b994be71cce351bb97075d192d8967b643bbbbbc6a718f7cadef64d0c90","sha256:9b975dfbf3e0ff9aed235def4c6583821f23eb63f5a33e9fb32898361f3fe070"],"state_sha256":"19a670fb6b7fc6f26d15227a7c0f7060c01076e7bd66c4ab5f5526278855d36b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VJMEeiYzsoUKee+zciv9wSxnVIeZe0FRN/Qa/hCN/63ZAb6RhO00Or4UQNDOn5BWe6nHIXx3BBU5oAATK4kcCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T05:27:00.484871Z","bundle_sha256":"efb2326b7356ec0816638f405ce8f419dbe4bbdfe24db4e74dae126d25e3b355"}}