{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6BC4KPK7VJFTLQ4YM2V5B5J4KB","short_pith_number":"pith:6BC4KPK7","schema_version":"1.0","canonical_sha256":"f045c53d5faa4b35c39866abd0f53c507762f9d80720a49420664151106a8d8a","source":{"kind":"arxiv","id":"2506.21316","version":2},"attestation_state":"computed","paper":{"title":"DRISHTIKON: Visual Grounding at Multiple Granularities in Documents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Badri Vishal Kasuba, Ganesh Ramakrishnan, Parag Chaudhuri","submitted_at":"2025-06-26T14:32:23Z","abstract_excerpt":"Visual grounding in text-rich document images is a critical yet underexplored challenge for Document Intelligence and Visual Question Answering (VQA) systems. We present DRISHTIKON, a multi-granular and multi-block visual grounding framework designed to enhance interpretability and trust in VQA for complex, multilingual documents. Our approach integrates multilingual OCR, large language models, and a novel region matching algorithm to localize answer spans at the block, line, word, and point levels. We introduce the Multi-Granular Visual Grounding (MGVG) benchmark, a curated test set of divers"},"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":"2506.21316","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-26T14:32:23Z","cross_cats_sorted":[],"title_canon_sha256":"17191336108b7854f814e9e0b4df9ffcee77e6c7de3bae78321c8c9754d6bdf1","abstract_canon_sha256":"4b79f811fec0d7a8ce12625a3bf55be86a6edf3bc2e229a31a80e8f2e1963216"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:37:45.189024Z","signature_b64":"pig5adogEqlhqa1p+y2hCr30vFb0Lyi7v5NNG590v9eZRFQlRBNCPmafmVshT+/ASeom83Fg+ZvJBGx8M78qDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f045c53d5faa4b35c39866abd0f53c507762f9d80720a49420664151106a8d8a","last_reissued_at":"2026-07-05T11:37:45.188408Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:37:45.188408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DRISHTIKON: Visual Grounding at Multiple Granularities in Documents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Badri Vishal Kasuba, Ganesh Ramakrishnan, Parag Chaudhuri","submitted_at":"2025-06-26T14:32:23Z","abstract_excerpt":"Visual grounding in text-rich document images is a critical yet underexplored challenge for Document Intelligence and Visual Question Answering (VQA) systems. We present DRISHTIKON, a multi-granular and multi-block visual grounding framework designed to enhance interpretability and trust in VQA for complex, multilingual documents. Our approach integrates multilingual OCR, large language models, and a novel region matching algorithm to localize answer spans at the block, line, word, and point levels. We introduce the Multi-Granular Visual Grounding (MGVG) benchmark, a curated test set of divers"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21316","kind":"arxiv","version":2},"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/2506.21316/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":"2506.21316","created_at":"2026-07-05T11:37:45.188474+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.21316v2","created_at":"2026-07-05T11:37:45.188474+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21316","created_at":"2026-07-05T11:37:45.188474+00:00"},{"alias_kind":"pith_short_12","alias_value":"6BC4KPK7VJFT","created_at":"2026-07-05T11:37:45.188474+00:00"},{"alias_kind":"pith_short_16","alias_value":"6BC4KPK7VJFTLQ4Y","created_at":"2026-07-05T11:37:45.188474+00:00"},{"alias_kind":"pith_short_8","alias_value":"6BC4KPK7","created_at":"2026-07-05T11:37:45.188474+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/6BC4KPK7VJFTLQ4YM2V5B5J4KB","json":"https://pith.science/pith/6BC4KPK7VJFTLQ4YM2V5B5J4KB.json","graph_json":"https://pith.science/api/pith-number/6BC4KPK7VJFTLQ4YM2V5B5J4KB/graph.json","events_json":"https://pith.science/api/pith-number/6BC4KPK7VJFTLQ4YM2V5B5J4KB/events.json","paper":"https://pith.science/paper/6BC4KPK7"},"agent_actions":{"view_html":"https://pith.science/pith/6BC4KPK7VJFTLQ4YM2V5B5J4KB","download_json":"https://pith.science/pith/6BC4KPK7VJFTLQ4YM2V5B5J4KB.json","view_paper":"https://pith.science/paper/6BC4KPK7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.21316&json=true","fetch_graph":"https://pith.science/api/pith-number/6BC4KPK7VJFTLQ4YM2V5B5J4KB/graph.json","fetch_events":"https://pith.science/api/pith-number/6BC4KPK7VJFTLQ4YM2V5B5J4KB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6BC4KPK7VJFTLQ4YM2V5B5J4KB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6BC4KPK7VJFTLQ4YM2V5B5J4KB/action/storage_attestation","attest_author":"https://pith.science/pith/6BC4KPK7VJFTLQ4YM2V5B5J4KB/action/author_attestation","sign_citation":"https://pith.science/pith/6BC4KPK7VJFTLQ4YM2V5B5J4KB/action/citation_signature","submit_replication":"https://pith.science/pith/6BC4KPK7VJFTLQ4YM2V5B5J4KB/action/replication_record"}},"created_at":"2026-07-05T11:37:45.188474+00:00","updated_at":"2026-07-05T11:37:45.188474+00:00"}