{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:QIJHMMIU7WIBIPJI5KXMXHCIXX","short_pith_number":"pith:QIJHMMIU","canonical_record":{"source":{"id":"2506.10406","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-12T06:59:35Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f2e9bcc801555309351daa46d2c058bc54005f1e1e3b7b03e39dd1fe91749451","abstract_canon_sha256":"2fb0f35ee56e3e2bf9349385c9dbd1bb5b6264ea0efc91c77499dd72860715dd"},"schema_version":"1.0"},"canonical_sha256":"8212763114fd90143d28eaaecb9c48bdf603ed0f57db8c36f39a4fa78f754446","source":{"kind":"arxiv","id":"2506.10406","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.10406","created_at":"2026-07-05T11:20:22Z"},{"alias_kind":"arxiv_version","alias_value":"2506.10406v1","created_at":"2026-07-05T11:20:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.10406","created_at":"2026-07-05T11:20:22Z"},{"alias_kind":"pith_short_12","alias_value":"QIJHMMIU7WIB","created_at":"2026-07-05T11:20:22Z"},{"alias_kind":"pith_short_16","alias_value":"QIJHMMIU7WIBIPJI","created_at":"2026-07-05T11:20:22Z"},{"alias_kind":"pith_short_8","alias_value":"QIJHMMIU","created_at":"2026-07-05T11:20:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:QIJHMMIU7WIBIPJI5KXMXHCIXX","target":"record","payload":{"canonical_record":{"source":{"id":"2506.10406","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-12T06:59:35Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f2e9bcc801555309351daa46d2c058bc54005f1e1e3b7b03e39dd1fe91749451","abstract_canon_sha256":"2fb0f35ee56e3e2bf9349385c9dbd1bb5b6264ea0efc91c77499dd72860715dd"},"schema_version":"1.0"},"canonical_sha256":"8212763114fd90143d28eaaecb9c48bdf603ed0f57db8c36f39a4fa78f754446","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:22.901537Z","signature_b64":"Gt4nALKMdvvDwcoigCRUqXg4uBNARJMlrIAhNuswGnwt35Vd6CYLT1c5+tqQGM6I7xgcbwBOEyY1FWGE8GSMDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8212763114fd90143d28eaaecb9c48bdf603ed0f57db8c36f39a4fa78f754446","last_reissued_at":"2026-07-05T11:20:22.901018Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:22.901018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.10406","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":"2026-07-05T11:20:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RHqDmIzpBQTNtfSCEKRE1l3tq5QFHfHBth5/RtPwUHTJ6/Sm8+IoAkikGEo3tluwqzVZ7Q6u7IH+AZkiVKMhCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:30:29.491897Z"},"content_sha256":"ea4d70866db0b5e2358440c3ac74e7297496af11a7206ac067c5cb91dcb7a4c5","schema_version":"1.0","event_id":"sha256:ea4d70866db0b5e2358440c3ac74e7297496af11a7206ac067c5cb91dcb7a4c5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:QIJHMMIU7WIBIPJI5KXMXHCIXX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PAG: Multi-Turn Reinforced LLM Self-Correction with Policy as Generative Verifier","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chao Xin, Lin Yan, Qianchuan Zhao, Wenyuan Xu, Yufeng Yuan, Yuhua Jiang, Yuwen Xiong, Yu Yue","submitted_at":"2025-06-12T06:59:35Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated impressive capabilities in complex reasoning tasks, yet they still struggle to reliably verify the correctness of their own outputs. Existing solutions to this verification challenge often depend on separate verifier models or require multi-stage self-correction training pipelines, which limit scalability. In this paper, we propose Policy as Generative Verifier (PAG), a simple and effective framework that empowers LLMs to self-correct by alternating between policy and verifier roles within a unified multi-turn reinforcement learning (RL) paradigm."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.10406","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/2506.10406/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":"2026-07-05T11:20:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Veg0mRh7rWj/3mkQpPlG6+Z+KMnWorP0o1pn+2YhjxbDl5NaCd04C78+9sRwObMh6Nan8ro2j/eWDo8iorOHCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:30:29.492546Z"},"content_sha256":"404b1148171382b01d5be1f187051cfec67fec93ca465636eab6acd1486ed167","schema_version":"1.0","event_id":"sha256:404b1148171382b01d5be1f187051cfec67fec93ca465636eab6acd1486ed167"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QIJHMMIU7WIBIPJI5KXMXHCIXX/bundle.json","state_url":"https://pith.science/pith/QIJHMMIU7WIBIPJI5KXMXHCIXX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QIJHMMIU7WIBIPJI5KXMXHCIXX/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":"2026-07-07T05:30:29Z","links":{"resolver":"https://pith.science/pith/QIJHMMIU7WIBIPJI5KXMXHCIXX","bundle":"https://pith.science/pith/QIJHMMIU7WIBIPJI5KXMXHCIXX/bundle.json","state":"https://pith.science/pith/QIJHMMIU7WIBIPJI5KXMXHCIXX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QIJHMMIU7WIBIPJI5KXMXHCIXX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QIJHMMIU7WIBIPJI5KXMXHCIXX","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":"2fb0f35ee56e3e2bf9349385c9dbd1bb5b6264ea0efc91c77499dd72860715dd","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-12T06:59:35Z","title_canon_sha256":"f2e9bcc801555309351daa46d2c058bc54005f1e1e3b7b03e39dd1fe91749451"},"schema_version":"1.0","source":{"id":"2506.10406","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.10406","created_at":"2026-07-05T11:20:22Z"},{"alias_kind":"arxiv_version","alias_value":"2506.10406v1","created_at":"2026-07-05T11:20:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.10406","created_at":"2026-07-05T11:20:22Z"},{"alias_kind":"pith_short_12","alias_value":"QIJHMMIU7WIB","created_at":"2026-07-05T11:20:22Z"},{"alias_kind":"pith_short_16","alias_value":"QIJHMMIU7WIBIPJI","created_at":"2026-07-05T11:20:22Z"},{"alias_kind":"pith_short_8","alias_value":"QIJHMMIU","created_at":"2026-07-05T11:20:22Z"}],"graph_snapshots":[{"event_id":"sha256:404b1148171382b01d5be1f187051cfec67fec93ca465636eab6acd1486ed167","target":"graph","created_at":"2026-07-05T11:20:22Z","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/2506.10406/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have demonstrated impressive capabilities in complex reasoning tasks, yet they still struggle to reliably verify the correctness of their own outputs. Existing solutions to this verification challenge often depend on separate verifier models or require multi-stage self-correction training pipelines, which limit scalability. In this paper, we propose Policy as Generative Verifier (PAG), a simple and effective framework that empowers LLMs to self-correct by alternating between policy and verifier roles within a unified multi-turn reinforcement learning (RL) paradigm.","authors_text":"Chao Xin, Lin Yan, Qianchuan Zhao, Wenyuan Xu, Yufeng Yuan, Yuhua Jiang, Yuwen Xiong, Yu Yue","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-12T06:59:35Z","title":"PAG: Multi-Turn Reinforced LLM Self-Correction with Policy as Generative Verifier"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.10406","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:ea4d70866db0b5e2358440c3ac74e7297496af11a7206ac067c5cb91dcb7a4c5","target":"record","created_at":"2026-07-05T11:20:22Z","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":"2fb0f35ee56e3e2bf9349385c9dbd1bb5b6264ea0efc91c77499dd72860715dd","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-12T06:59:35Z","title_canon_sha256":"f2e9bcc801555309351daa46d2c058bc54005f1e1e3b7b03e39dd1fe91749451"},"schema_version":"1.0","source":{"id":"2506.10406","kind":"arxiv","version":1}},"canonical_sha256":"8212763114fd90143d28eaaecb9c48bdf603ed0f57db8c36f39a4fa78f754446","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8212763114fd90143d28eaaecb9c48bdf603ed0f57db8c36f39a4fa78f754446","first_computed_at":"2026-07-05T11:20:22.901018Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:20:22.901018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Gt4nALKMdvvDwcoigCRUqXg4uBNARJMlrIAhNuswGnwt35Vd6CYLT1c5+tqQGM6I7xgcbwBOEyY1FWGE8GSMDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:20:22.901537Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.10406","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea4d70866db0b5e2358440c3ac74e7297496af11a7206ac067c5cb91dcb7a4c5","sha256:404b1148171382b01d5be1f187051cfec67fec93ca465636eab6acd1486ed167"],"state_sha256":"53bd23c2b0fa607d0e0a1744a811b99012f7072899c30893a25b8673cfd88a4a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2j6uRMwzaHiHRDSqmgq0cOS3kKdGz7I7mME9MOJGbZr2NmqYmW6tPy7iXta7gsx1F8LjYRD5HlAw0AebyUZGCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T05:30:29.495755Z","bundle_sha256":"f3e6cf112c0b18b45f4e4d36830c9eb8ffb5f4d9ad75b41bd77fdb1db86227ca"}}