{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7GCOPCZ7Q5PB74XQFFBDFAGIUB","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":"8cd260881596599a53c9b9b9d1bf0a48a0869ce035a426f454f5afd6b3d5c4be","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-12T03:06:55Z","title_canon_sha256":"ff5c805f3c44620371008bcea4b040df7fe5d4a6fa81e2619bbd3e90e775dc27"},"schema_version":"1.0","source":{"id":"2508.08589","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.08589","created_at":"2026-07-05T11:52:30Z"},{"alias_kind":"arxiv_version","alias_value":"2508.08589v1","created_at":"2026-07-05T11:52:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.08589","created_at":"2026-07-05T11:52:30Z"},{"alias_kind":"pith_short_12","alias_value":"7GCOPCZ7Q5PB","created_at":"2026-07-05T11:52:30Z"},{"alias_kind":"pith_short_16","alias_value":"7GCOPCZ7Q5PB74XQ","created_at":"2026-07-05T11:52:30Z"},{"alias_kind":"pith_short_8","alias_value":"7GCOPCZ7","created_at":"2026-07-05T11:52:30Z"}],"graph_snapshots":[{"event_id":"sha256:a44902e6db1cbd39c6105e5a1c59131e441d77d9a34629f2d98f92c3abae4761","target":"graph","created_at":"2026-07-05T11:52:30Z","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/2508.08589/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in document understanding. However, their reasoning processes remain largely black-box, making it difficult to ensure reliability and trustworthiness, especially in high-stakes domains such as legal, financial, and medical document analysis. Existing methods use fixed Chain-of-Thought (CoT) reasoning with supervised fine-tuning (SFT) but suffer from catastrophic forgetting, poor adaptability, and limited generalization across domain tasks. In this paper, we propose DocThinker, a rule-based Reinforcement Learning","authors_text":"Wenwen Yu, Xiang Bai, Yuliang Liu, Zhibo Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-12T03:06:55Z","title":"DocThinker: Explainable Multimodal Large Language Models with Rule-based Reinforcement Learning for Document Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.08589","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":"sha256:96da41f8e9938fd87fd92d5cca0972c6dfe5234557cee72633bbb1dea25aec13","target":"record","created_at":"2026-07-05T11:52:30Z","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":"8cd260881596599a53c9b9b9d1bf0a48a0869ce035a426f454f5afd6b3d5c4be","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-12T03:06:55Z","title_canon_sha256":"ff5c805f3c44620371008bcea4b040df7fe5d4a6fa81e2619bbd3e90e775dc27"},"schema_version":"1.0","source":{"id":"2508.08589","kind":"arxiv","version":1}},"canonical_sha256":"f984e78b3f875e1ff2f029423280c8a05746d3524a09ac99c083174604eba65f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f984e78b3f875e1ff2f029423280c8a05746d3524a09ac99c083174604eba65f","first_computed_at":"2026-07-05T11:52:30.920854Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:52:30.920854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6pFMhiLJBsM6k/1CaNAjRU4fxjK0xUNKVkaDVNc00oHC9c0iw4n+zNT3i5TTZ98aLmHaIpDJpqoHNj2GuUThAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:52:30.921348Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.08589","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:96da41f8e9938fd87fd92d5cca0972c6dfe5234557cee72633bbb1dea25aec13","sha256:a44902e6db1cbd39c6105e5a1c59131e441d77d9a34629f2d98f92c3abae4761"],"state_sha256":"7410e0e90ca3b5d0338e434f8b7dc4abc130bdf6bd7b523ab8903e9ed20bd071"}