{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GG7EXLYFYYPGNR6K3W4GJMK5DF","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":"3127b259872b6d7da069039e871200bb4b053027232f7f22fa911000c35f10b3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-01T08:45:41Z","title_canon_sha256":"fc869ea23afbf901399bb20c9565ef6479049be3c149739666e87b95e1a6d79e"},"schema_version":"1.0","source":{"id":"2608.00536","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.00536","created_at":"2026-08-04T00:37:23Z"},{"alias_kind":"arxiv_version","alias_value":"2608.00536v1","created_at":"2026-08-04T00:37:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00536","created_at":"2026-08-04T00:37:23Z"},{"alias_kind":"pith_short_12","alias_value":"GG7EXLYFYYPG","created_at":"2026-08-04T00:37:23Z"},{"alias_kind":"pith_short_16","alias_value":"GG7EXLYFYYPGNR6K","created_at":"2026-08-04T00:37:23Z"},{"alias_kind":"pith_short_8","alias_value":"GG7EXLYF","created_at":"2026-08-04T00:37:23Z"}],"graph_snapshots":[{"event_id":"sha256:6fcef3a76b8406ff571725bd8ba2cb5cbc18f6ae77fb82fecba463060ad1ef21","target":"graph","created_at":"2026-08-04T00:37:23Z","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/2608.00536/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) for document parsing often relies on reference-based rewards rooted in edit distance (e.g., tree edit distance), yet it remains hard to optimize in the high-accuracy regime because such rewards become weakly discriminative: near-correct outputs receive very similar scores, providing limited learning signal for hard cases. We propose Step-Aware Annealing (SAA), a plug-and-play reward sharpening mechanism that progressively increases reward curvature during training, amplifying subtle quality differences among high-scoring samples while preserving stability in early l","authors_text":"Binghong Wu, Feng Zhang, Jiacheng Shi, Shuo Huang, Tinghao Yu, Yunhao Wang, Zhenyu Huang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-01T08:45:41Z","title":"DocPO: Advancing Document Policy Optimization via Tailored Step-Aware Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00536","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":"sha256:08837f3c16c12009fc91704f877c9e8ee0815ebaa0387c201a9dc3665068cf2a","target":"record","created_at":"2026-08-04T00:37:23Z","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":"3127b259872b6d7da069039e871200bb4b053027232f7f22fa911000c35f10b3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-01T08:45:41Z","title_canon_sha256":"fc869ea23afbf901399bb20c9565ef6479049be3c149739666e87b95e1a6d79e"},"schema_version":"1.0","source":{"id":"2608.00536","kind":"arxiv","version":1}},"canonical_sha256":"31be4baf05c61e66c7caddb864b15d1973ce72ce53526c62073166150922c10c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31be4baf05c61e66c7caddb864b15d1973ce72ce53526c62073166150922c10c","first_computed_at":"2026-08-04T00:37:23.763786Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T00:37:23.763786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L0OnQtT7tIntWO94/YdfOBmuBx7XtKsihj9UVbP1+JTwAuTXFLHpFbjFz2G0KfbeAhuQROUVl5+skv2LxZeQDw==","signature_status":"signed_v1","signed_at":"2026-08-04T00:37:23.765255Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.00536","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08837f3c16c12009fc91704f877c9e8ee0815ebaa0387c201a9dc3665068cf2a","sha256:6fcef3a76b8406ff571725bd8ba2cb5cbc18f6ae77fb82fecba463060ad1ef21"],"state_sha256":"7c69c45b3beb25146b3470b8487f4ba165e12b0875f562c2332954a40ed67056"}