{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3KYWDOKOMWZFNSDNZHBLZYKTMZ","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":"6173ba3298a470e9cdeb28af0ddff170fd895fa1e5a045d89ab4182a7fb7b4f4","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-02-26T01:17:50Z","title_canon_sha256":"c06378824bac7d60940bc840d0106c74bf80a588417e37a288e7900dcb099521"},"schema_version":"1.0","source":{"id":"2403.00816","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.00816","created_at":"2026-07-05T08:55:08Z"},{"alias_kind":"arxiv_version","alias_value":"2403.00816v3","created_at":"2026-07-05T08:55:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.00816","created_at":"2026-07-05T08:55:08Z"},{"alias_kind":"pith_short_12","alias_value":"3KYWDOKOMWZF","created_at":"2026-07-05T08:55:08Z"},{"alias_kind":"pith_short_16","alias_value":"3KYWDOKOMWZFNSDN","created_at":"2026-07-05T08:55:08Z"},{"alias_kind":"pith_short_8","alias_value":"3KYWDOKO","created_at":"2026-07-05T08:55:08Z"}],"graph_snapshots":[{"event_id":"sha256:5c2b0687a27ec105ed69798358465db5fa72bbf05d181fc508e44be569d9c37f","target":"graph","created_at":"2026-07-05T08:55:08Z","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/2403.00816/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding the contents of multimodal documents is essential to accurately extract relevant evidence and use it for reasoning. Existing document understanding models tend to generate answers with a single word or phrase directly, ignoring the source document's evidence and lacking interpretability. In this work, we address the lack of step-wise capabilities through data augmentation and extension. Specifically, We use Multi-modal Large Language Models (MLLMs), which have strong visual understanding and reasoning abilities, as data generators to generate step-wise question-and-answer pairs f","authors_text":"Jinxu Zhang","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-02-26T01:17:50Z","title":"Read and Think: An Efficient Step-wise Multimodal Language Model for Document Understanding and Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.00816","kind":"arxiv","version":3},"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":"sha256:767017bb980fca15a09074cd7fc27ef206c105329cb1c0f82d972d45dbbbe855","target":"record","created_at":"2026-07-05T08:55:08Z","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":"6173ba3298a470e9cdeb28af0ddff170fd895fa1e5a045d89ab4182a7fb7b4f4","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-02-26T01:17:50Z","title_canon_sha256":"c06378824bac7d60940bc840d0106c74bf80a588417e37a288e7900dcb099521"},"schema_version":"1.0","source":{"id":"2403.00816","kind":"arxiv","version":3}},"canonical_sha256":"dab161b94e65b256c86dc9c2bce1536657907d0b1f8ddeff51ec5a9fa607a302","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dab161b94e65b256c86dc9c2bce1536657907d0b1f8ddeff51ec5a9fa607a302","first_computed_at":"2026-07-05T08:55:08.112490Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:55:08.112490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PNahJ4yg8Z/KFzN9jG640djhT33Z9Y6D/1Bs2Abf3Vn1zoNxBVFvva65NMUXqdu1wKXGaHh8f8J4eseyqepVAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:55:08.112900Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.00816","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:767017bb980fca15a09074cd7fc27ef206c105329cb1c0f82d972d45dbbbe855","sha256:5c2b0687a27ec105ed69798358465db5fa72bbf05d181fc508e44be569d9c37f"],"state_sha256":"d317a0b26853d7d162990cd36afb93a27ad1fd4a0f04fe630cbb15f63dfb02af"}