{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:U5BGOZWALWEG72AAW672F5XTMA","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":"b1930039963c7305819850320afa3617b73e86047e3ccfbb0e8f972c68e31703","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-24T17:54:08Z","title_canon_sha256":"73bab3b48aae39d4b7bd05b36c27b0358b2484f3ed7a23ad9ba1df076203c2c5"},"schema_version":"1.0","source":{"id":"2606.26080","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.26080","created_at":"2026-06-25T01:18:48Z"},{"alias_kind":"arxiv_version","alias_value":"2606.26080v1","created_at":"2026-06-25T01:18:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26080","created_at":"2026-06-25T01:18:48Z"},{"alias_kind":"pith_short_12","alias_value":"U5BGOZWALWEG","created_at":"2026-06-25T01:18:48Z"},{"alias_kind":"pith_short_16","alias_value":"U5BGOZWALWEG72AA","created_at":"2026-06-25T01:18:48Z"},{"alias_kind":"pith_short_8","alias_value":"U5BGOZWA","created_at":"2026-06-25T01:18:48Z"}],"graph_snapshots":[{"event_id":"sha256:2f12fce4f885077ac6e6a6f8c1f6ac0f31d51b696c3ce8949e8c6f26294a94f4","target":"graph","created_at":"2026-06-25T01:18:48Z","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/2606.26080/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Process reward models enable fine-grained, step-level evaluation of LLMs, yet building them for agentic settings remains prohibitively difficult: long-horizon interactions, irreversible actions, and stochastic environment feedback make both human annotation and Monte Carlo estimation infeasible at scale. In this work, we show that reinforcement learning (RL) post-training already provides the ingredients for effective step-level scoring, eliminating the need for dedicated reward model training altogether. Concretely, we derive an implicit advantage under a general stochastic Markov decision pr","authors_text":"Changdae Oh, Samuel Yeh, Seongheon Park, Sharon Li, Tanwi Mallick, Wendi Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-24T17:54:08Z","title":"Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26080","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:c9df17d6aba2dfb384075496cab419fbc24e5280751a48affa3311ba9805a58d","target":"record","created_at":"2026-06-25T01:18:48Z","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":"b1930039963c7305819850320afa3617b73e86047e3ccfbb0e8f972c68e31703","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-24T17:54:08Z","title_canon_sha256":"73bab3b48aae39d4b7bd05b36c27b0358b2484f3ed7a23ad9ba1df076203c2c5"},"schema_version":"1.0","source":{"id":"2606.26080","kind":"arxiv","version":1}},"canonical_sha256":"a7426766c05d886fe800b7bfa2f6f3601dd5f3a58ff1ad08f5e2fdea1c9eff20","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a7426766c05d886fe800b7bfa2f6f3601dd5f3a58ff1ad08f5e2fdea1c9eff20","first_computed_at":"2026-06-25T01:18:48.013122Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-25T01:18:48.013122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PpD7WcNmg3EaHbw64njDK3qH9Pmnhzz4JJ4pcn7S7h6c6xFbzkvLKTVJFxNZBK1Xd/1FkM+6Z0iafjAxAWGAAg==","signature_status":"signed_v1","signed_at":"2026-06-25T01:18:48.013530Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.26080","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c9df17d6aba2dfb384075496cab419fbc24e5280751a48affa3311ba9805a58d","sha256:2f12fce4f885077ac6e6a6f8c1f6ac0f31d51b696c3ce8949e8c6f26294a94f4"],"state_sha256":"8bb5b996970449bfd0e38b742e033f8d407c1588f2948f10d28008483b649135"}