{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:4KCCKS2E2ZEVH67AF2OY4SRFRC","short_pith_number":"pith:4KCCKS2E","canonical_record":{"source":{"id":"2608.01837","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-03T07:47:59Z","cross_cats_sorted":[],"title_canon_sha256":"6fc5d80109d348855a552b7d94199c766cd515598eaedbc829b18d8c9884ee28","abstract_canon_sha256":"749bc90f7d127f4d1083aa0aac19fff2910daa003394d13324351e6f2fc03414"},"schema_version":"1.0"},"canonical_sha256":"e284254b44d64953fbe02e9d8e4a25889376140cb5cee5d4d2742d5e60cc5c6d","source":{"kind":"arxiv","id":"2608.01837","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.01837","created_at":"2026-08-04T02:07:22Z"},{"alias_kind":"arxiv_version","alias_value":"2608.01837v1","created_at":"2026-08-04T02:07:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01837","created_at":"2026-08-04T02:07:22Z"},{"alias_kind":"pith_short_12","alias_value":"4KCCKS2E2ZEV","created_at":"2026-08-04T02:07:22Z"},{"alias_kind":"pith_short_16","alias_value":"4KCCKS2E2ZEVH67A","created_at":"2026-08-04T02:07:22Z"},{"alias_kind":"pith_short_8","alias_value":"4KCCKS2E","created_at":"2026-08-04T02:07:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:4KCCKS2E2ZEVH67AF2OY4SRFRC","target":"record","payload":{"canonical_record":{"source":{"id":"2608.01837","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-03T07:47:59Z","cross_cats_sorted":[],"title_canon_sha256":"6fc5d80109d348855a552b7d94199c766cd515598eaedbc829b18d8c9884ee28","abstract_canon_sha256":"749bc90f7d127f4d1083aa0aac19fff2910daa003394d13324351e6f2fc03414"},"schema_version":"1.0"},"canonical_sha256":"e284254b44d64953fbe02e9d8e4a25889376140cb5cee5d4d2742d5e60cc5c6d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:07:22.096058Z","signature_b64":"aAmS9mXWIaUZL/omHw5hNzg+//Jy9IK4S4DXGudP+tC3il0VB5ZzTkGxd1qgZPSbsJmxVNP2+ZSXIybcRFOMAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e284254b44d64953fbe02e9d8e4a25889376140cb5cee5d4d2742d5e60cc5c6d","last_reissued_at":"2026-08-04T02:07:22.094216Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:07:22.094216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.01837","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":"2026-08-04T02:07:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xfay3lx82H8qslMYgzaTR4RJX/LE2xFDHrUrEBodjs/mQaNeQMREBsrh7zBuzo3rtM8kQDPnjH1Sf4KdOnFcBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:34:08.106590Z"},"content_sha256":"54d4c1eb01953bf8914abbb4de0aea7bff4fc05cb9d8912773d2d41708550f64","schema_version":"1.0","event_id":"sha256:54d4c1eb01953bf8914abbb4de0aea7bff4fc05cb9d8912773d2d41708550f64"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:4KCCKS2E2ZEVH67AF2OY4SRFRC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PCSD: Persistent Consistency for Self-Distillation in Agentic Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Changsheng Li, Chunji Lv, Guoren Wang, Jinyang Wu, Junlin Liu, Ming Liu, Xinming Wang, Yang Gao, Yangguang Wei","submitted_at":"2026-08-03T07:47:59Z","abstract_excerpt":"Large language model agents have shown strong potential in complex interactive tasks, yet their reinforcement learning (RL) is often hindered by sparse rewards, as a long multi-turn trajectory may receive only a single outcome-level signal. On-policy self-distillation (OPSD) provides dense token-level supervision from a privileged teacher, but the teacher may not be reliable at every position. Existing methods commonly rely on isolated token-level discrepancies, which can be sensitive to noise, or assign a shared step-level weight that may overlook positional variation. We propose Persistent C"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01837","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/2608.01837/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":"2026-08-04T02:07:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6+tqnCZ7ff/hw4L/7iPlvNT5ICPtJIYA8xlwtNkmEpZEOUT/GJPE9ETg3Jr+yhe547wuKgU7coWumjhVXt99AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:34:08.107081Z"},"content_sha256":"6851b7b1d087f3fe799c1175469da03e8602ded4f91a61ed393f24af9f407989","schema_version":"1.0","event_id":"sha256:6851b7b1d087f3fe799c1175469da03e8602ded4f91a61ed393f24af9f407989"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4KCCKS2E2ZEVH67AF2OY4SRFRC/bundle.json","state_url":"https://pith.science/pith/4KCCKS2E2ZEVH67AF2OY4SRFRC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4KCCKS2E2ZEVH67AF2OY4SRFRC/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":"2026-08-05T17:34:08Z","links":{"resolver":"https://pith.science/pith/4KCCKS2E2ZEVH67AF2OY4SRFRC","bundle":"https://pith.science/pith/4KCCKS2E2ZEVH67AF2OY4SRFRC/bundle.json","state":"https://pith.science/pith/4KCCKS2E2ZEVH67AF2OY4SRFRC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4KCCKS2E2ZEVH67AF2OY4SRFRC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4KCCKS2E2ZEVH67AF2OY4SRFRC","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":"749bc90f7d127f4d1083aa0aac19fff2910daa003394d13324351e6f2fc03414","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-03T07:47:59Z","title_canon_sha256":"6fc5d80109d348855a552b7d94199c766cd515598eaedbc829b18d8c9884ee28"},"schema_version":"1.0","source":{"id":"2608.01837","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.01837","created_at":"2026-08-04T02:07:22Z"},{"alias_kind":"arxiv_version","alias_value":"2608.01837v1","created_at":"2026-08-04T02:07:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01837","created_at":"2026-08-04T02:07:22Z"},{"alias_kind":"pith_short_12","alias_value":"4KCCKS2E2ZEV","created_at":"2026-08-04T02:07:22Z"},{"alias_kind":"pith_short_16","alias_value":"4KCCKS2E2ZEVH67A","created_at":"2026-08-04T02:07:22Z"},{"alias_kind":"pith_short_8","alias_value":"4KCCKS2E","created_at":"2026-08-04T02:07:22Z"}],"graph_snapshots":[{"event_id":"sha256:6851b7b1d087f3fe799c1175469da03e8602ded4f91a61ed393f24af9f407989","target":"graph","created_at":"2026-08-04T02:07:22Z","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/2608.01837/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language model agents have shown strong potential in complex interactive tasks, yet their reinforcement learning (RL) is often hindered by sparse rewards, as a long multi-turn trajectory may receive only a single outcome-level signal. On-policy self-distillation (OPSD) provides dense token-level supervision from a privileged teacher, but the teacher may not be reliable at every position. Existing methods commonly rely on isolated token-level discrepancies, which can be sensitive to noise, or assign a shared step-level weight that may overlook positional variation. We propose Persistent C","authors_text":"Changsheng Li, Chunji Lv, Guoren Wang, Jinyang Wu, Junlin Liu, Ming Liu, Xinming Wang, Yang Gao, Yangguang Wei","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-03T07:47:59Z","title":"PCSD: Persistent Consistency for Self-Distillation in Agentic Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01837","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":"sha256:54d4c1eb01953bf8914abbb4de0aea7bff4fc05cb9d8912773d2d41708550f64","target":"record","created_at":"2026-08-04T02:07:22Z","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":"749bc90f7d127f4d1083aa0aac19fff2910daa003394d13324351e6f2fc03414","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-03T07:47:59Z","title_canon_sha256":"6fc5d80109d348855a552b7d94199c766cd515598eaedbc829b18d8c9884ee28"},"schema_version":"1.0","source":{"id":"2608.01837","kind":"arxiv","version":1}},"canonical_sha256":"e284254b44d64953fbe02e9d8e4a25889376140cb5cee5d4d2742d5e60cc5c6d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e284254b44d64953fbe02e9d8e4a25889376140cb5cee5d4d2742d5e60cc5c6d","first_computed_at":"2026-08-04T02:07:22.094216Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T02:07:22.094216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aAmS9mXWIaUZL/omHw5hNzg+//Jy9IK4S4DXGudP+tC3il0VB5ZzTkGxd1qgZPSbsJmxVNP2+ZSXIybcRFOMAQ==","signature_status":"signed_v1","signed_at":"2026-08-04T02:07:22.096058Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.01837","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:54d4c1eb01953bf8914abbb4de0aea7bff4fc05cb9d8912773d2d41708550f64","sha256:6851b7b1d087f3fe799c1175469da03e8602ded4f91a61ed393f24af9f407989"],"state_sha256":"f2f8612eb66d7be165d8ffa4ef1317670bfaba076db0b613bdb3550d9bd04ec5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CEHW9iPPWrM77t8EX8eDnARp28ZcNwBB08iyJc+jOzLVmxmALM46pKJO3JTRFr27MVYuIr4aBu1x6h9AhqYpBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T17:34:08.110756Z","bundle_sha256":"6d16fa5233ddd776ef3771b677d331f2a438813fd9c4eaf015f522c8dbdca389"}}