{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7FNC35AILXJ4C3QO75GZMKWYNT","short_pith_number":"pith:7FNC35AI","schema_version":"1.0","canonical_sha256":"f95a2df4085dd3c16e0eff4d962ad86cdf106df9efa908349a1cb721ba5afd6c","source":{"kind":"arxiv","id":"2401.03411","version":2},"attestation_state":"computed","paper":{"title":"GRAM: Global Reasoning for Multi-Page VQA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Alona Golts, Aviad Aberdam, Elad Ben Avraham, Roi Ronen, Ron Litman, Roy Ganz, Shahar Tsiper, Sharon Fogel, Tsachi Blau","submitted_at":"2024-01-07T08:03:06Z","abstract_excerpt":"The increasing use of transformer-based large language models brings forward the challenge of processing long sequences. In document visual question answering (DocVQA), leading methods focus on the single-page setting, while documents can span hundreds of pages. We present GRAM, a method that seamlessly extends pre-trained single-page models to the multi-page setting, without requiring computationally-heavy pretraining. To do so, we leverage a single-page encoder for local page-level understanding, and enhance it with document-level designated layers and learnable tokens, facilitating the flow"},"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":"2401.03411","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-07T08:03:06Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"e60792b56d4cbbef2706ae9271e52e6a2e3722ad089c424d36c895f3f7eebdd6","abstract_canon_sha256":"8762a3c2dcd843edbd3dbca61e41cd9c116b022ad52fc711d32dd2f11303a71b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:58.337644Z","signature_b64":"BAZsQdnLQk7bOvZXeDCUOgDkgKDrVTgeNG79pSiCBnkiqL3HRJDxucJbZKJT8CZanuPro4XS8eUqQ8HUE50XCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f95a2df4085dd3c16e0eff4d962ad86cdf106df9efa908349a1cb721ba5afd6c","last_reissued_at":"2026-07-05T07:56:58.337127Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:58.337127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GRAM: Global Reasoning for Multi-Page VQA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Alona Golts, Aviad Aberdam, Elad Ben Avraham, Roi Ronen, Ron Litman, Roy Ganz, Shahar Tsiper, Sharon Fogel, Tsachi Blau","submitted_at":"2024-01-07T08:03:06Z","abstract_excerpt":"The increasing use of transformer-based large language models brings forward the challenge of processing long sequences. In document visual question answering (DocVQA), leading methods focus on the single-page setting, while documents can span hundreds of pages. We present GRAM, a method that seamlessly extends pre-trained single-page models to the multi-page setting, without requiring computationally-heavy pretraining. To do so, we leverage a single-page encoder for local page-level understanding, and enhance it with document-level designated layers and learnable tokens, facilitating the flow"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.03411","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/2401.03411/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":"2401.03411","created_at":"2026-07-05T07:56:58.337195+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.03411v2","created_at":"2026-07-05T07:56:58.337195+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.03411","created_at":"2026-07-05T07:56:58.337195+00:00"},{"alias_kind":"pith_short_12","alias_value":"7FNC35AILXJ4","created_at":"2026-07-05T07:56:58.337195+00:00"},{"alias_kind":"pith_short_16","alias_value":"7FNC35AILXJ4C3QO","created_at":"2026-07-05T07:56:58.337195+00:00"},{"alias_kind":"pith_short_8","alias_value":"7FNC35AI","created_at":"2026-07-05T07:56:58.337195+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/7FNC35AILXJ4C3QO75GZMKWYNT","json":"https://pith.science/pith/7FNC35AILXJ4C3QO75GZMKWYNT.json","graph_json":"https://pith.science/api/pith-number/7FNC35AILXJ4C3QO75GZMKWYNT/graph.json","events_json":"https://pith.science/api/pith-number/7FNC35AILXJ4C3QO75GZMKWYNT/events.json","paper":"https://pith.science/paper/7FNC35AI"},"agent_actions":{"view_html":"https://pith.science/pith/7FNC35AILXJ4C3QO75GZMKWYNT","download_json":"https://pith.science/pith/7FNC35AILXJ4C3QO75GZMKWYNT.json","view_paper":"https://pith.science/paper/7FNC35AI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.03411&json=true","fetch_graph":"https://pith.science/api/pith-number/7FNC35AILXJ4C3QO75GZMKWYNT/graph.json","fetch_events":"https://pith.science/api/pith-number/7FNC35AILXJ4C3QO75GZMKWYNT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7FNC35AILXJ4C3QO75GZMKWYNT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7FNC35AILXJ4C3QO75GZMKWYNT/action/storage_attestation","attest_author":"https://pith.science/pith/7FNC35AILXJ4C3QO75GZMKWYNT/action/author_attestation","sign_citation":"https://pith.science/pith/7FNC35AILXJ4C3QO75GZMKWYNT/action/citation_signature","submit_replication":"https://pith.science/pith/7FNC35AILXJ4C3QO75GZMKWYNT/action/replication_record"}},"created_at":"2026-07-05T07:56:58.337195+00:00","updated_at":"2026-07-05T07:56:58.337195+00:00"}