{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IMNA4ZR6UJZ766CSMO2VK326VH","short_pith_number":"pith:IMNA4ZR6","canonical_record":{"source":{"id":"2507.14675","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-19T16:03:34Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"399fb45f40b67c3b08e37dd19211344f64f7984bef5a2c3886f57ce11561195e","abstract_canon_sha256":"3370c0795f8589b31482f222fd9d1c407ac740d26cdf18ad859af9ed73053e0b"},"schema_version":"1.0"},"canonical_sha256":"431a0e663ea273ff785263b5556f5ea9c4bdf996d5a576908bb6778eb59ab33f","source":{"kind":"arxiv","id":"2507.14675","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.14675","created_at":"2026-07-05T11:40:11Z"},{"alias_kind":"arxiv_version","alias_value":"2507.14675v1","created_at":"2026-07-05T11:40:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.14675","created_at":"2026-07-05T11:40:11Z"},{"alias_kind":"pith_short_12","alias_value":"IMNA4ZR6UJZ7","created_at":"2026-07-05T11:40:11Z"},{"alias_kind":"pith_short_16","alias_value":"IMNA4ZR6UJZ766CS","created_at":"2026-07-05T11:40:11Z"},{"alias_kind":"pith_short_8","alias_value":"IMNA4ZR6","created_at":"2026-07-05T11:40:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IMNA4ZR6UJZ766CSMO2VK326VH","target":"record","payload":{"canonical_record":{"source":{"id":"2507.14675","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-19T16:03:34Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"399fb45f40b67c3b08e37dd19211344f64f7984bef5a2c3886f57ce11561195e","abstract_canon_sha256":"3370c0795f8589b31482f222fd9d1c407ac740d26cdf18ad859af9ed73053e0b"},"schema_version":"1.0"},"canonical_sha256":"431a0e663ea273ff785263b5556f5ea9c4bdf996d5a576908bb6778eb59ab33f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:11.548442Z","signature_b64":"b9KlA4yqs/9g4gao75l0G/Gpfkuu0x5xx4d/7CUNZOFMRK2NaK9l2zgxYCaAxuRPpWKDhG2LMtidoFEZZqYUBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"431a0e663ea273ff785263b5556f5ea9c4bdf996d5a576908bb6778eb59ab33f","last_reissued_at":"2026-07-05T11:40:11.547950Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:11.547950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.14675","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:40:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rihEmMXqR7cokrYrkvKoV7IwsVYvFxJbYmIH5LkChp7pp+MpfLRlj90lxAAk2ji6iCFqxtstXC7e46ZJMyLGBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:40:59.440522Z"},"content_sha256":"3debf79b2a99cca527388df636a167d6cb43cca73d453698fb14eb40bc5e8a38","schema_version":"1.0","event_id":"sha256:3debf79b2a99cca527388df636a167d6cb43cca73d453698fb14eb40bc5e8a38"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IMNA4ZR6UJZ766CSMO2VK326VH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Docopilot: Improving Multimodal Models for Document-Level Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Botian Shi, Hongsheng Li, Jifeng Dai, Lewei Lu, Qibin Hou, Shenglong Ye, Tong Lu, Weiyun Wang, Wenhai Wang, Yuchen Duan, Yusong Hu, Zhe Chen","submitted_at":"2025-07-19T16:03:34Z","abstract_excerpt":"Despite significant progress in multimodal large language models (MLLMs), their performance on complex, multi-page document comprehension remains inadequate, largely due to the lack of high-quality, document-level datasets. While current retrieval-augmented generation (RAG) methods offer partial solutions, they suffer from issues, such as fragmented retrieval contexts, multi-stage error accumulation, and extra time costs of retrieval. In this work, we present a high-quality document-level dataset, Doc-750K, designed to support in-depth understanding of multimodal documents. This dataset includ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.14675","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/2507.14675/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:40:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E1cmvs2c3hYX4Q+7iF85gvQBZR/JYmtVwGbkatnoT+ccatLn9ln4q5+xZ8NQMb5qeJuyk6luM9Go/yHyVOBkBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:40:59.440916Z"},"content_sha256":"c3f0889a189a8df0c3a74bb5dc44be021a7c2d7d9f214e2164a15f91c121bdd7","schema_version":"1.0","event_id":"sha256:c3f0889a189a8df0c3a74bb5dc44be021a7c2d7d9f214e2164a15f91c121bdd7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IMNA4ZR6UJZ766CSMO2VK326VH/bundle.json","state_url":"https://pith.science/pith/IMNA4ZR6UJZ766CSMO2VK326VH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IMNA4ZR6UJZ766CSMO2VK326VH/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T15:40:59Z","links":{"resolver":"https://pith.science/pith/IMNA4ZR6UJZ766CSMO2VK326VH","bundle":"https://pith.science/pith/IMNA4ZR6UJZ766CSMO2VK326VH/bundle.json","state":"https://pith.science/pith/IMNA4ZR6UJZ766CSMO2VK326VH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IMNA4ZR6UJZ766CSMO2VK326VH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IMNA4ZR6UJZ766CSMO2VK326VH","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":"3370c0795f8589b31482f222fd9d1c407ac740d26cdf18ad859af9ed73053e0b","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-19T16:03:34Z","title_canon_sha256":"399fb45f40b67c3b08e37dd19211344f64f7984bef5a2c3886f57ce11561195e"},"schema_version":"1.0","source":{"id":"2507.14675","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.14675","created_at":"2026-07-05T11:40:11Z"},{"alias_kind":"arxiv_version","alias_value":"2507.14675v1","created_at":"2026-07-05T11:40:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.14675","created_at":"2026-07-05T11:40:11Z"},{"alias_kind":"pith_short_12","alias_value":"IMNA4ZR6UJZ7","created_at":"2026-07-05T11:40:11Z"},{"alias_kind":"pith_short_16","alias_value":"IMNA4ZR6UJZ766CS","created_at":"2026-07-05T11:40:11Z"},{"alias_kind":"pith_short_8","alias_value":"IMNA4ZR6","created_at":"2026-07-05T11:40:11Z"}],"graph_snapshots":[{"event_id":"sha256:c3f0889a189a8df0c3a74bb5dc44be021a7c2d7d9f214e2164a15f91c121bdd7","target":"graph","created_at":"2026-07-05T11:40:11Z","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/2507.14675/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite significant progress in multimodal large language models (MLLMs), their performance on complex, multi-page document comprehension remains inadequate, largely due to the lack of high-quality, document-level datasets. While current retrieval-augmented generation (RAG) methods offer partial solutions, they suffer from issues, such as fragmented retrieval contexts, multi-stage error accumulation, and extra time costs of retrieval. In this work, we present a high-quality document-level dataset, Doc-750K, designed to support in-depth understanding of multimodal documents. This dataset includ","authors_text":"Botian Shi, Hongsheng Li, Jifeng Dai, Lewei Lu, Qibin Hou, Shenglong Ye, Tong Lu, Weiyun Wang, Wenhai Wang, Yuchen Duan, Yusong Hu, Zhe Chen","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-19T16:03:34Z","title":"Docopilot: Improving Multimodal Models for Document-Level Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.14675","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":"sha256:3debf79b2a99cca527388df636a167d6cb43cca73d453698fb14eb40bc5e8a38","target":"record","created_at":"2026-07-05T11:40:11Z","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":"3370c0795f8589b31482f222fd9d1c407ac740d26cdf18ad859af9ed73053e0b","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-19T16:03:34Z","title_canon_sha256":"399fb45f40b67c3b08e37dd19211344f64f7984bef5a2c3886f57ce11561195e"},"schema_version":"1.0","source":{"id":"2507.14675","kind":"arxiv","version":1}},"canonical_sha256":"431a0e663ea273ff785263b5556f5ea9c4bdf996d5a576908bb6778eb59ab33f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"431a0e663ea273ff785263b5556f5ea9c4bdf996d5a576908bb6778eb59ab33f","first_computed_at":"2026-07-05T11:40:11.547950Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:40:11.547950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b9KlA4yqs/9g4gao75l0G/Gpfkuu0x5xx4d/7CUNZOFMRK2NaK9l2zgxYCaAxuRPpWKDhG2LMtidoFEZZqYUBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:40:11.548442Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.14675","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3debf79b2a99cca527388df636a167d6cb43cca73d453698fb14eb40bc5e8a38","sha256:c3f0889a189a8df0c3a74bb5dc44be021a7c2d7d9f214e2164a15f91c121bdd7"],"state_sha256":"82395d266208d5b571945b610fcda62eeee067ef04bdfd5328690117b27cd767"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x25JTCEB8kejoeu4d0nSKdxZPbeHhYTl3GluAXY+d/FSN3A76GCeQ2WytBp4cy6w9weX1W1cajMfO8n2F160Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T15:40:59.443192Z","bundle_sha256":"dcb44f95060a3e17a98d516ad8f98c686e7c80b8a1689f0206b48b88ce924626"}}