{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GUIW2FNGEZSO3QV5G3P7WW6KHD","short_pith_number":"pith:GUIW2FNG","canonical_record":{"source":{"id":"2402.19014","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-29T10:17:27Z","cross_cats_sorted":[],"title_canon_sha256":"81d273afc34c76bb311a25fbd44d81e84d385f50bff3683976bc1cd180fe19b9","abstract_canon_sha256":"95365a156ac60a804acb0a45d5a16aa93f66e1834cf490689fb559ac6a6291a4"},"schema_version":"1.0"},"canonical_sha256":"35116d15a62664edc2bd36dffb5bca38e48f2491fe77cd33d2a2f3f30fcc7412","source":{"kind":"arxiv","id":"2402.19014","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.19014","created_at":"2026-07-05T07:50:31Z"},{"alias_kind":"arxiv_version","alias_value":"2402.19014v1","created_at":"2026-07-05T07:50:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.19014","created_at":"2026-07-05T07:50:31Z"},{"alias_kind":"pith_short_12","alias_value":"GUIW2FNGEZSO","created_at":"2026-07-05T07:50:31Z"},{"alias_kind":"pith_short_16","alias_value":"GUIW2FNGEZSO3QV5","created_at":"2026-07-05T07:50:31Z"},{"alias_kind":"pith_short_8","alias_value":"GUIW2FNG","created_at":"2026-07-05T07:50:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GUIW2FNGEZSO3QV5G3P7WW6KHD","target":"record","payload":{"canonical_record":{"source":{"id":"2402.19014","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-29T10:17:27Z","cross_cats_sorted":[],"title_canon_sha256":"81d273afc34c76bb311a25fbd44d81e84d385f50bff3683976bc1cd180fe19b9","abstract_canon_sha256":"95365a156ac60a804acb0a45d5a16aa93f66e1834cf490689fb559ac6a6291a4"},"schema_version":"1.0"},"canonical_sha256":"35116d15a62664edc2bd36dffb5bca38e48f2491fe77cd33d2a2f3f30fcc7412","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:50:31.266849Z","signature_b64":"d6/PdzoqGbxOLaRypdGdAQjO6J2zts3+BVQdik0+hL1YABERZTePKzzyCBPgHzjoMDypm7yi9HVar3aqg2hDBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35116d15a62664edc2bd36dffb5bca38e48f2491fe77cd33d2a2f3f30fcc7412","last_reissued_at":"2026-07-05T07:50:31.266375Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:50:31.266375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.19014","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":"2026-07-05T07:50:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5xRk3q5vApjrqTPelSYzXBXKTAfTcdIkUXn/qwQJXOuBwp65GgjgYUhweOVttdhHCt/Vqzn4YY9dN9q8nkd0Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:45:14.915936Z"},"content_sha256":"a5fcca394da0c37bf18e46852b5334bf87c7b69c2ad9acb7b1375480bc81bd45","schema_version":"1.0","event_id":"sha256:a5fcca394da0c37bf18e46852b5334bf87c7b69c2ad9acb7b1375480bc81bd45"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GUIW2FNGEZSO3QV5G3P7WW6KHD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing Visual Document Understanding with Contrastive Learning in Large Visual-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deqiang Jiang, Haoyu Cao, Mingming Gong, Xinghua Jiang, Xing Sun, Xin Li, Yinsong Liu, Yunfei Wu, Zhihao Guo","submitted_at":"2024-02-29T10:17:27Z","abstract_excerpt":"Recently, the advent of Large Visual-Language Models (LVLMs) has received increasing attention across various domains, particularly in the field of visual document understanding (VDU). Different from conventional vision-language tasks, VDU is specifically concerned with text-rich scenarios containing abundant document elements. Nevertheless, the importance of fine-grained features remains largely unexplored within the community of LVLMs, leading to suboptimal performance in text-rich scenarios. In this paper, we abbreviate it as the fine-grained feature collapse issue. With the aim of filling "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.19014","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/2402.19014/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":"2026-07-05T07:50:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jj5T27CTcULuImtqK6oNW+WswehQb6U1y661ImTEP5mr5ggew+igsGWFRZn66F3+K3+P/a1GVRJUpW7Di0FqAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:45:14.916342Z"},"content_sha256":"e8439a3ae39345fac1d8d684c15936e362e7d38ba605ca81f7827e682c665f4b","schema_version":"1.0","event_id":"sha256:e8439a3ae39345fac1d8d684c15936e362e7d38ba605ca81f7827e682c665f4b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GUIW2FNGEZSO3QV5G3P7WW6KHD/bundle.json","state_url":"https://pith.science/pith/GUIW2FNGEZSO3QV5G3P7WW6KHD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GUIW2FNGEZSO3QV5G3P7WW6KHD/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":"2026-07-09T05:45:14Z","links":{"resolver":"https://pith.science/pith/GUIW2FNGEZSO3QV5G3P7WW6KHD","bundle":"https://pith.science/pith/GUIW2FNGEZSO3QV5G3P7WW6KHD/bundle.json","state":"https://pith.science/pith/GUIW2FNGEZSO3QV5G3P7WW6KHD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GUIW2FNGEZSO3QV5G3P7WW6KHD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GUIW2FNGEZSO3QV5G3P7WW6KHD","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":"95365a156ac60a804acb0a45d5a16aa93f66e1834cf490689fb559ac6a6291a4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-29T10:17:27Z","title_canon_sha256":"81d273afc34c76bb311a25fbd44d81e84d385f50bff3683976bc1cd180fe19b9"},"schema_version":"1.0","source":{"id":"2402.19014","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.19014","created_at":"2026-07-05T07:50:31Z"},{"alias_kind":"arxiv_version","alias_value":"2402.19014v1","created_at":"2026-07-05T07:50:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.19014","created_at":"2026-07-05T07:50:31Z"},{"alias_kind":"pith_short_12","alias_value":"GUIW2FNGEZSO","created_at":"2026-07-05T07:50:31Z"},{"alias_kind":"pith_short_16","alias_value":"GUIW2FNGEZSO3QV5","created_at":"2026-07-05T07:50:31Z"},{"alias_kind":"pith_short_8","alias_value":"GUIW2FNG","created_at":"2026-07-05T07:50:31Z"}],"graph_snapshots":[{"event_id":"sha256:e8439a3ae39345fac1d8d684c15936e362e7d38ba605ca81f7827e682c665f4b","target":"graph","created_at":"2026-07-05T07:50:31Z","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/2402.19014/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, the advent of Large Visual-Language Models (LVLMs) has received increasing attention across various domains, particularly in the field of visual document understanding (VDU). Different from conventional vision-language tasks, VDU is specifically concerned with text-rich scenarios containing abundant document elements. Nevertheless, the importance of fine-grained features remains largely unexplored within the community of LVLMs, leading to suboptimal performance in text-rich scenarios. In this paper, we abbreviate it as the fine-grained feature collapse issue. With the aim of filling ","authors_text":"Deqiang Jiang, Haoyu Cao, Mingming Gong, Xinghua Jiang, Xing Sun, Xin Li, Yinsong Liu, Yunfei Wu, Zhihao Guo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-29T10:17:27Z","title":"Enhancing Visual Document Understanding with Contrastive Learning in Large Visual-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.19014","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:a5fcca394da0c37bf18e46852b5334bf87c7b69c2ad9acb7b1375480bc81bd45","target":"record","created_at":"2026-07-05T07:50:31Z","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":"95365a156ac60a804acb0a45d5a16aa93f66e1834cf490689fb559ac6a6291a4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-29T10:17:27Z","title_canon_sha256":"81d273afc34c76bb311a25fbd44d81e84d385f50bff3683976bc1cd180fe19b9"},"schema_version":"1.0","source":{"id":"2402.19014","kind":"arxiv","version":1}},"canonical_sha256":"35116d15a62664edc2bd36dffb5bca38e48f2491fe77cd33d2a2f3f30fcc7412","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"35116d15a62664edc2bd36dffb5bca38e48f2491fe77cd33d2a2f3f30fcc7412","first_computed_at":"2026-07-05T07:50:31.266375Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:50:31.266375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d6/PdzoqGbxOLaRypdGdAQjO6J2zts3+BVQdik0+hL1YABERZTePKzzyCBPgHzjoMDypm7yi9HVar3aqg2hDBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:50:31.266849Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.19014","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a5fcca394da0c37bf18e46852b5334bf87c7b69c2ad9acb7b1375480bc81bd45","sha256:e8439a3ae39345fac1d8d684c15936e362e7d38ba605ca81f7827e682c665f4b"],"state_sha256":"139c8ccdcf3f6b36b9e7b72e1485e2495f600850a5f1ec26d7361230edbf00ba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6NRWy/USyDZP8CsB4IifB1kyDsGbNuPgAYXFVlrC4jnI1bfWHzUfaT/ll3oQ3zjEI/+Md7NiQrGjVnVtE29ICw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T05:45:14.919489Z","bundle_sha256":"e92cc027a53a92c53df057ca1770fd84f263cc8f8eecbb8f209cda69ba13928e"}}