{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EZLI4UWJF5RYU232HLZ454A3FB","short_pith_number":"pith:EZLI4UWJ","schema_version":"1.0","canonical_sha256":"26568e52c92f638a6b7a3af3cef01b28534ee3c0dd2b2fcd6738c7c4d30e4593","source":{"kind":"arxiv","id":"2505.14059","version":1},"attestation_state":"computed","paper":{"title":"Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Binghong Wu, Can Huang, Chunhui Lin, Hao Feng, Hao Liu, Jinghui Lu, Jingqun Tang, Lei Liao, Qi Liu, Shu Wei, Wei Shi, Xiang Fei, Yingdong Han","submitted_at":"2025-05-20T08:03:59Z","abstract_excerpt":"Document image parsing is challenging due to its complexly intertwined elements such as text paragraphs, figures, formulas, and tables. Current approaches either assemble specialized expert models or directly generate page-level content autoregressively, facing integration overhead, efficiency bottlenecks, and layout structure degradation despite their decent performance. To address these limitations, we present \\textit{Dolphin} (\\textit{\\textbf{Do}cument Image \\textbf{P}arsing via \\textbf{H}eterogeneous Anchor Prompt\\textbf{in}g}), a novel multimodal document image parsing model following an "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2505.14059","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-20T08:03:59Z","cross_cats_sorted":[],"title_canon_sha256":"81a1d4152ac5daf92253a46b18519488f1824c84c641b0d6b196ee2f640876e1","abstract_canon_sha256":"21eb1765bfafcefde3fad1e32c8e960486306e67bf568519abc33b2eb632b41e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:55.421783Z","signature_b64":"ZYDzn8g/5Gg8FPJZzAc1aA1NqaLCkAx1q3iFueoMyUEoY65cim8RCerb9p51Gfy/RQv5iJKv4kvAelZQd9O5BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26568e52c92f638a6b7a3af3cef01b28534ee3c0dd2b2fcd6738c7c4d30e4593","last_reissued_at":"2026-07-05T11:05:55.421298Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:55.421298Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Binghong Wu, Can Huang, Chunhui Lin, Hao Feng, Hao Liu, Jinghui Lu, Jingqun Tang, Lei Liao, Qi Liu, Shu Wei, Wei Shi, Xiang Fei, Yingdong Han","submitted_at":"2025-05-20T08:03:59Z","abstract_excerpt":"Document image parsing is challenging due to its complexly intertwined elements such as text paragraphs, figures, formulas, and tables. Current approaches either assemble specialized expert models or directly generate page-level content autoregressively, facing integration overhead, efficiency bottlenecks, and layout structure degradation despite their decent performance. To address these limitations, we present \\textit{Dolphin} (\\textit{\\textbf{Do}cument Image \\textbf{P}arsing via \\textbf{H}eterogeneous Anchor Prompt\\textbf{in}g}), a novel multimodal document image parsing model following an "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14059","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.14059/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.14059","created_at":"2026-07-05T11:05:55.421379+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.14059v1","created_at":"2026-07-05T11:05:55.421379+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14059","created_at":"2026-07-05T11:05:55.421379+00:00"},{"alias_kind":"pith_short_12","alias_value":"EZLI4UWJF5RY","created_at":"2026-07-05T11:05:55.421379+00:00"},{"alias_kind":"pith_short_16","alias_value":"EZLI4UWJF5RYU232","created_at":"2026-07-05T11:05:55.421379+00:00"},{"alias_kind":"pith_short_8","alias_value":"EZLI4UWJ","created_at":"2026-07-05T11:05:55.421379+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24447","citing_title":"P-MTP: Efficient Document Parsing via Multi-Token Prediction with Progressive Depth Scaling","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23050","citing_title":"Unlimited OCR Works","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.15932","citing_title":"Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01602","citing_title":"ProWAFT: A ROMA-LPD Instance for Workload-Aware and Dynamic Fault Tolerance in FPGA-Based CNN Accelerators","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30189","citing_title":"DAIN: Dynamic Agent-Based Interaction Network for Efficient and Collaborative Multimodal Reasoning","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19866","citing_title":"Structured Layout Priors for Robust Out-of-Distribution Visual Document Understanding","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2509.22186","citing_title":"MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2601.21957","citing_title":"PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2603.09677","citing_title":"Logics-Parsing-Omni Technical Report","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2603.23885","citing_title":"Towards Real-World Document Parsing via Realistic Scene Synthesis and Document-Aware Training","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2603.24326","citing_title":"Boosting Document Parsing Efficiency and Performance with Coarse-to-Fine Visual Processing","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12812","citing_title":"DocSeeker: Structured Visual Reasoning with Evidence Grounding for Long Document Understanding","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2510.18234","citing_title":"DeepSeek-OCR: Contexts Optical Compression","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12812","citing_title":"DocSeeker: Structured Visual Reasoning with Evidence Grounding for Long Document Understanding","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16099","citing_title":"DenTab: A Dataset for Table Recognition and Visual QA on Real-World Dental Estimates","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EZLI4UWJF5RYU232HLZ454A3FB","json":"https://pith.science/pith/EZLI4UWJF5RYU232HLZ454A3FB.json","graph_json":"https://pith.science/api/pith-number/EZLI4UWJF5RYU232HLZ454A3FB/graph.json","events_json":"https://pith.science/api/pith-number/EZLI4UWJF5RYU232HLZ454A3FB/events.json","paper":"https://pith.science/paper/EZLI4UWJ"},"agent_actions":{"view_html":"https://pith.science/pith/EZLI4UWJF5RYU232HLZ454A3FB","download_json":"https://pith.science/pith/EZLI4UWJF5RYU232HLZ454A3FB.json","view_paper":"https://pith.science/paper/EZLI4UWJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.14059&json=true","fetch_graph":"https://pith.science/api/pith-number/EZLI4UWJF5RYU232HLZ454A3FB/graph.json","fetch_events":"https://pith.science/api/pith-number/EZLI4UWJF5RYU232HLZ454A3FB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EZLI4UWJF5RYU232HLZ454A3FB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EZLI4UWJF5RYU232HLZ454A3FB/action/storage_attestation","attest_author":"https://pith.science/pith/EZLI4UWJF5RYU232HLZ454A3FB/action/author_attestation","sign_citation":"https://pith.science/pith/EZLI4UWJF5RYU232HLZ454A3FB/action/citation_signature","submit_replication":"https://pith.science/pith/EZLI4UWJF5RYU232HLZ454A3FB/action/replication_record"}},"created_at":"2026-07-05T11:05:55.421379+00:00","updated_at":"2026-07-05T11:05:55.421379+00:00"}