{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DIG4MUSCDVUJ2QR3MSIFLCYYJE","short_pith_number":"pith:DIG4MUSC","schema_version":"1.0","canonical_sha256":"1a0dc652421d689d423b6490558b18490205a59eb511978f12f0e7dbd56f51ec","source":{"kind":"arxiv","id":"2607.10400","version":1},"attestation_state":"computed","paper":{"title":"SynthDocBench: Controlled Benchmark for Long-Context Visual Document Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Abhigya Verma, Amit Kumar Saha, Khyati Mahajan, Sagar Davasam, Sai Rajeswar Mudumba, Shruthan Radhakrishna, Vikas Yadav","submitted_at":"2026-07-11T17:02:49Z","abstract_excerpt":"Vision language models (VLMs) have achieved strong performance on visual document understanding benchmarks such as DocVQA, ChartQA, and MMLongBench-Doc. However, real-world documents combine multiple factors such as length, layout complexity, modality, and question difficulty, which makes it difficult to attribute model failures to specific causes. We introduce SynthDocBench, a fully synthetic benchmark for long-context visual document understanding that systematically controls factors including document length, layout structure, modality composition, and question type. The benchmark is constr"},"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":"2607.10400","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-11T17:02:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"24196bb9854bf29d2e65077900819de8e842f8f853f6f6d0d76311b61f942f36","abstract_canon_sha256":"0b273e90e77673223212ccab042ab4425fd36f1fcbf2b1d2e469aa9cccb49171"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:21:14.222934Z","signature_b64":"e3ykQ6bIkoFHq3KyZjYUl2oqTaCi9CZM5enedCapyfp9ytBztoaF3cnqwRQliPe1pPhInJTsVPjKkKFvovhiAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a0dc652421d689d423b6490558b18490205a59eb511978f12f0e7dbd56f51ec","last_reissued_at":"2026-07-14T01:21:14.222134Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:21:14.222134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SynthDocBench: Controlled Benchmark for Long-Context Visual Document Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Abhigya Verma, Amit Kumar Saha, Khyati Mahajan, Sagar Davasam, Sai Rajeswar Mudumba, Shruthan Radhakrishna, Vikas Yadav","submitted_at":"2026-07-11T17:02:49Z","abstract_excerpt":"Vision language models (VLMs) have achieved strong performance on visual document understanding benchmarks such as DocVQA, ChartQA, and MMLongBench-Doc. However, real-world documents combine multiple factors such as length, layout complexity, modality, and question difficulty, which makes it difficult to attribute model failures to specific causes. We introduce SynthDocBench, a fully synthetic benchmark for long-context visual document understanding that systematically controls factors including document length, layout structure, modality composition, and question type. The benchmark is constr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.10400","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/2607.10400/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":"2607.10400","created_at":"2026-07-14T01:21:14.222561+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.10400v1","created_at":"2026-07-14T01:21:14.222561+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.10400","created_at":"2026-07-14T01:21:14.222561+00:00"},{"alias_kind":"pith_short_12","alias_value":"DIG4MUSCDVUJ","created_at":"2026-07-14T01:21:14.222561+00:00"},{"alias_kind":"pith_short_16","alias_value":"DIG4MUSCDVUJ2QR3","created_at":"2026-07-14T01:21:14.222561+00:00"},{"alias_kind":"pith_short_8","alias_value":"DIG4MUSC","created_at":"2026-07-14T01:21:14.222561+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DIG4MUSCDVUJ2QR3MSIFLCYYJE","json":"https://pith.science/pith/DIG4MUSCDVUJ2QR3MSIFLCYYJE.json","graph_json":"https://pith.science/api/pith-number/DIG4MUSCDVUJ2QR3MSIFLCYYJE/graph.json","events_json":"https://pith.science/api/pith-number/DIG4MUSCDVUJ2QR3MSIFLCYYJE/events.json","paper":"https://pith.science/paper/DIG4MUSC"},"agent_actions":{"view_html":"https://pith.science/pith/DIG4MUSCDVUJ2QR3MSIFLCYYJE","download_json":"https://pith.science/pith/DIG4MUSCDVUJ2QR3MSIFLCYYJE.json","view_paper":"https://pith.science/paper/DIG4MUSC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.10400&json=true","fetch_graph":"https://pith.science/api/pith-number/DIG4MUSCDVUJ2QR3MSIFLCYYJE/graph.json","fetch_events":"https://pith.science/api/pith-number/DIG4MUSCDVUJ2QR3MSIFLCYYJE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DIG4MUSCDVUJ2QR3MSIFLCYYJE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DIG4MUSCDVUJ2QR3MSIFLCYYJE/action/storage_attestation","attest_author":"https://pith.science/pith/DIG4MUSCDVUJ2QR3MSIFLCYYJE/action/author_attestation","sign_citation":"https://pith.science/pith/DIG4MUSCDVUJ2QR3MSIFLCYYJE/action/citation_signature","submit_replication":"https://pith.science/pith/DIG4MUSCDVUJ2QR3MSIFLCYYJE/action/replication_record"}},"created_at":"2026-07-14T01:21:14.222561+00:00","updated_at":"2026-07-14T01:21:14.222561+00:00"}