{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:I4BSZR7QJMFDJCOCKL2BLXYUI3","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":"39817771c4d921fa85b2ea18023e7244ba6b552a5073920f0d1c2a04988b99c1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-07T11:54:01Z","title_canon_sha256":"a43bf68f22ca226eda02b375ba48911134ca8ebec0eca1926a30fb5e670e6f3a"},"schema_version":"1.0","source":{"id":"2411.04642","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.04642","created_at":"2026-07-05T09:32:23Z"},{"alias_kind":"arxiv_version","alias_value":"2411.04642v1","created_at":"2026-07-05T09:32:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04642","created_at":"2026-07-05T09:32:23Z"},{"alias_kind":"pith_short_12","alias_value":"I4BSZR7QJMFD","created_at":"2026-07-05T09:32:23Z"},{"alias_kind":"pith_short_16","alias_value":"I4BSZR7QJMFDJCOC","created_at":"2026-07-05T09:32:23Z"},{"alias_kind":"pith_short_8","alias_value":"I4BSZR7Q","created_at":"2026-07-05T09:32:23Z"}],"graph_snapshots":[{"event_id":"sha256:c5bc93d5eee64129023444663a2acbd9c59b90f4a4bb204d53cc58e430c3d4d2","target":"graph","created_at":"2026-07-05T09:32:23Z","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/2411.04642/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language (VL) models have garnered considerable research interest; however, they still face challenges in effectively handling text within images. To address this limitation, researchers have developed two approaches. The first method involves utilizing external Optical Character Recognition (OCR) tools to extract textual information from images, which is then prepended to other textual inputs. The second strategy focuses on employing extremely high-resolution images to improve text recognition capabilities. In this paper, we focus on enhancing the first strategy by introducing a novel ","authors_text":"Aviad Aberdam, Elad Ben Avraham, Jonathan Fhima, Oren Nuriel, Ron Litman, Roy Ganz, Yair Kittenplon","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-07T11:54:01Z","title":"TAP-VL: Text Layout-Aware Pre-training for Enriched Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.04642","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":"sha256:39518c7d641790a93a3d8eb62320b4e56ad36315174614b8b80d8038caccf53c","target":"record","created_at":"2026-07-05T09:32:23Z","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":"39817771c4d921fa85b2ea18023e7244ba6b552a5073920f0d1c2a04988b99c1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-07T11:54:01Z","title_canon_sha256":"a43bf68f22ca226eda02b375ba48911134ca8ebec0eca1926a30fb5e670e6f3a"},"schema_version":"1.0","source":{"id":"2411.04642","kind":"arxiv","version":1}},"canonical_sha256":"47032cc7f04b0a3489c252f415df1446fe2c7c40735ed49cd42e337a77c88c01","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"47032cc7f04b0a3489c252f415df1446fe2c7c40735ed49cd42e337a77c88c01","first_computed_at":"2026-07-05T09:32:23.272221Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:32:23.272221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/K8r8y/lH348fJY4Gcxg/51UEytpmPeCRTHiTf2dIuvls44AdrHWvZtd8pFOVLZn3o6PSry8ksgaNwAZcxX3DA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:32:23.272727Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.04642","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:39518c7d641790a93a3d8eb62320b4e56ad36315174614b8b80d8038caccf53c","sha256:c5bc93d5eee64129023444663a2acbd9c59b90f4a4bb204d53cc58e430c3d4d2"],"state_sha256":"9fc4aa3006f0c7c2f57718c095231e95828967730d563de516f2ed1ee803263f"}