{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:C7H663GZTRUDSUUY275Y6QGJCS","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":"156b5e80282102886002fbbae935440a70302b416bdcc92383bc23b7ffa12486","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-18T05:39:30Z","title_canon_sha256":"2cb687661584b4670bda496326726501cc84527f28acccdf6bd8859634d0a662"},"schema_version":"1.0","source":{"id":"2605.17877","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17877","created_at":"2026-05-20T00:05:03Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17877v1","created_at":"2026-05-20T00:05:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17877","created_at":"2026-05-20T00:05:03Z"},{"alias_kind":"pith_short_12","alias_value":"C7H663GZTRUD","created_at":"2026-05-20T00:05:03Z"},{"alias_kind":"pith_short_16","alias_value":"C7H663GZTRUDSUUY","created_at":"2026-05-20T00:05:03Z"},{"alias_kind":"pith_short_8","alias_value":"C7H663GZ","created_at":"2026-05-20T00:05:03Z"}],"graph_snapshots":[{"event_id":"sha256:5bcd141d7f6d2e1d13ac0cb93626dc689eab9d5ccea03c16c298309dba6743bc","target":"graph","created_at":"2026-05-20T00:05:03Z","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/2605.17877/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A significant hurdle for current LLMs is the execution of complex, multi-stage tasks. Group Relative Policy Optimization (GRPO) has been emerging as a leading choice, but its reliance on sparse outcome rewards severely limits credit assignment across intermediate steps. Existing remedies such as running full rollouts to assign step-level advantages, calling external LLM judges at each step, or computing intrinsic rewards that require ground-truth answers at every evaluation introduce significant costs or practical constraints. We hypothesize that internal correctness probing over LLM hidden st","authors_text":"Chanyoung Park, Dongha Lee, Sangwu Park, Wonjoong Kim, Yeonjun In","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-18T05:39:30Z","title":"PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17877","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":"sha256:8c9767df9b85453e9971b11e7c441e8706eb260f7f2100c63aad9a7816b2c504","target":"record","created_at":"2026-05-20T00:05:03Z","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":"156b5e80282102886002fbbae935440a70302b416bdcc92383bc23b7ffa12486","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-18T05:39:30Z","title_canon_sha256":"2cb687661584b4670bda496326726501cc84527f28acccdf6bd8859634d0a662"},"schema_version":"1.0","source":{"id":"2605.17877","kind":"arxiv","version":1}},"canonical_sha256":"17cfef6cd99c68395298d7fb8f40c914becf80d1c8b2cff68b117bdd7520bfea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"17cfef6cd99c68395298d7fb8f40c914becf80d1c8b2cff68b117bdd7520bfea","first_computed_at":"2026-05-20T00:05:03.085481Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:05:03.085481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WU++YNqSeredFAVVOS1L1JkCW6LPGW0I+02rYk4GFBcheXeuW10A0/bMZDLxR2OQCqLtp3ZXgNlpJohwGo9SCA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:05:03.086388Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.17877","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8c9767df9b85453e9971b11e7c441e8706eb260f7f2100c63aad9a7816b2c504","sha256:5bcd141d7f6d2e1d13ac0cb93626dc689eab9d5ccea03c16c298309dba6743bc"],"state_sha256":"99562de0e7d611ceb33035ceb29d1642ce657c6ec8e58f13d95b8b888fe8d831"}