{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:V7KIAFY6ABDXU3FTXORK22BB7D","short_pith_number":"pith:V7KIAFY6","canonical_record":{"source":{"id":"2412.08746","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-11T19:35:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f55e0d748d59ea8fe1e4153b1caea9bb26f0d5b5822007405bced2699ff0d2f8","abstract_canon_sha256":"fd96093cfb3b58fa40fad4621b859d5692c93344ed4e7602c7b537b18ba4df58"},"schema_version":"1.0"},"canonical_sha256":"afd480171e00477a6cb3bba2ad6821f8cb15f0ea88b661df0f71b9f856ed8375","source":{"kind":"arxiv","id":"2412.08746","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.08746","created_at":"2026-07-05T09:47:59Z"},{"alias_kind":"arxiv_version","alias_value":"2412.08746v1","created_at":"2026-07-05T09:47:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08746","created_at":"2026-07-05T09:47:59Z"},{"alias_kind":"pith_short_12","alias_value":"V7KIAFY6ABDX","created_at":"2026-07-05T09:47:59Z"},{"alias_kind":"pith_short_16","alias_value":"V7KIAFY6ABDXU3FT","created_at":"2026-07-05T09:47:59Z"},{"alias_kind":"pith_short_8","alias_value":"V7KIAFY6","created_at":"2026-07-05T09:47:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:V7KIAFY6ABDXU3FTXORK22BB7D","target":"record","payload":{"canonical_record":{"source":{"id":"2412.08746","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-11T19:35:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f55e0d748d59ea8fe1e4153b1caea9bb26f0d5b5822007405bced2699ff0d2f8","abstract_canon_sha256":"fd96093cfb3b58fa40fad4621b859d5692c93344ed4e7602c7b537b18ba4df58"},"schema_version":"1.0"},"canonical_sha256":"afd480171e00477a6cb3bba2ad6821f8cb15f0ea88b661df0f71b9f856ed8375","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:59.809545Z","signature_b64":"n7bI7KMQ12OocQ8AmYrUQnOWv+19wjXWAIWE4am/t9ZptYVbi0Fso5w8GNfMqlW98bIJW1L5eDc9vWHNT/hvBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"afd480171e00477a6cb3bba2ad6821f8cb15f0ea88b661df0f71b9f856ed8375","last_reissued_at":"2026-07-05T09:47:59.809061Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:59.809061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.08746","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":"2026-07-05T09:47:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D1iu4uXa99mcBH4dE6V7xAhgGrr2+/rQFqpRkS/F4BepAX6SuSZznuPBVKOZ/hjpONm9SaXfvAwn9kzgszCdAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T01:56:09.400628Z"},"content_sha256":"ebfdbc380ec7b068945cc8ac2ef16e3b78b6ae4ab7bc5fb24d87d828a1c23b81","schema_version":"1.0","event_id":"sha256:ebfdbc380ec7b068945cc8ac2ef16e3b78b6ae4ab7bc5fb24d87d828a1c23b81"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:V7KIAFY6ABDXU3FTXORK22BB7D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DocVLM: Make Your VLM an Efficient Reader","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alona Golts, Aviad Aberdam, Elad Ben Avraham, Mor Shpigel Nacson, Ron Litman, Roy Ganz, Shai Mazor, Yair Kittenplon","submitted_at":"2024-12-11T19:35:06Z","abstract_excerpt":"Vision-Language Models (VLMs) excel in diverse visual tasks but face challenges in document understanding, which requires fine-grained text processing. While typical visual tasks perform well with low-resolution inputs, reading-intensive applications demand high-resolution, resulting in significant computational overhead. Using OCR-extracted text in VLM prompts partially addresses this issue but underperforms compared to full-resolution counterpart, as it lacks the complete visual context needed for optimal performance. We introduce DocVLM, a method that integrates an OCR-based modality into V"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08746","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/2412.08746/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":"2026-07-05T09:47:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CUKyOML8ULiO484plN/KLFLTwggBaboRFWYoF9B5ZJkHRgirVr7teWF65/e5KN3JUNKcVmZYnLVwxxc2jWaJDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T01:56:09.400980Z"},"content_sha256":"3d8d9dbb1f8c132fa980c3a8927b1609f34aa3b618046de65ad086b28ec38ba5","schema_version":"1.0","event_id":"sha256:3d8d9dbb1f8c132fa980c3a8927b1609f34aa3b618046de65ad086b28ec38ba5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V7KIAFY6ABDXU3FTXORK22BB7D/bundle.json","state_url":"https://pith.science/pith/V7KIAFY6ABDXU3FTXORK22BB7D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V7KIAFY6ABDXU3FTXORK22BB7D/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":"2026-08-14T01:56:09Z","links":{"resolver":"https://pith.science/pith/V7KIAFY6ABDXU3FTXORK22BB7D","bundle":"https://pith.science/pith/V7KIAFY6ABDXU3FTXORK22BB7D/bundle.json","state":"https://pith.science/pith/V7KIAFY6ABDXU3FTXORK22BB7D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V7KIAFY6ABDXU3FTXORK22BB7D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:V7KIAFY6ABDXU3FTXORK22BB7D","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":"fd96093cfb3b58fa40fad4621b859d5692c93344ed4e7602c7b537b18ba4df58","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-11T19:35:06Z","title_canon_sha256":"f55e0d748d59ea8fe1e4153b1caea9bb26f0d5b5822007405bced2699ff0d2f8"},"schema_version":"1.0","source":{"id":"2412.08746","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.08746","created_at":"2026-07-05T09:47:59Z"},{"alias_kind":"arxiv_version","alias_value":"2412.08746v1","created_at":"2026-07-05T09:47:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08746","created_at":"2026-07-05T09:47:59Z"},{"alias_kind":"pith_short_12","alias_value":"V7KIAFY6ABDX","created_at":"2026-07-05T09:47:59Z"},{"alias_kind":"pith_short_16","alias_value":"V7KIAFY6ABDXU3FT","created_at":"2026-07-05T09:47:59Z"},{"alias_kind":"pith_short_8","alias_value":"V7KIAFY6","created_at":"2026-07-05T09:47:59Z"}],"graph_snapshots":[{"event_id":"sha256:3d8d9dbb1f8c132fa980c3a8927b1609f34aa3b618046de65ad086b28ec38ba5","target":"graph","created_at":"2026-07-05T09:47:59Z","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/2412.08746/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Models (VLMs) excel in diverse visual tasks but face challenges in document understanding, which requires fine-grained text processing. While typical visual tasks perform well with low-resolution inputs, reading-intensive applications demand high-resolution, resulting in significant computational overhead. Using OCR-extracted text in VLM prompts partially addresses this issue but underperforms compared to full-resolution counterpart, as it lacks the complete visual context needed for optimal performance. We introduce DocVLM, a method that integrates an OCR-based modality into V","authors_text":"Alona Golts, Aviad Aberdam, Elad Ben Avraham, Mor Shpigel Nacson, Ron Litman, Roy Ganz, Shai Mazor, Yair Kittenplon","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-11T19:35:06Z","title":"DocVLM: Make Your VLM an Efficient Reader"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08746","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:ebfdbc380ec7b068945cc8ac2ef16e3b78b6ae4ab7bc5fb24d87d828a1c23b81","target":"record","created_at":"2026-07-05T09:47:59Z","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":"fd96093cfb3b58fa40fad4621b859d5692c93344ed4e7602c7b537b18ba4df58","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-11T19:35:06Z","title_canon_sha256":"f55e0d748d59ea8fe1e4153b1caea9bb26f0d5b5822007405bced2699ff0d2f8"},"schema_version":"1.0","source":{"id":"2412.08746","kind":"arxiv","version":1}},"canonical_sha256":"afd480171e00477a6cb3bba2ad6821f8cb15f0ea88b661df0f71b9f856ed8375","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"afd480171e00477a6cb3bba2ad6821f8cb15f0ea88b661df0f71b9f856ed8375","first_computed_at":"2026-07-05T09:47:59.809061Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:47:59.809061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n7bI7KMQ12OocQ8AmYrUQnOWv+19wjXWAIWE4am/t9ZptYVbi0Fso5w8GNfMqlW98bIJW1L5eDc9vWHNT/hvBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:47:59.809545Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.08746","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ebfdbc380ec7b068945cc8ac2ef16e3b78b6ae4ab7bc5fb24d87d828a1c23b81","sha256:3d8d9dbb1f8c132fa980c3a8927b1609f34aa3b618046de65ad086b28ec38ba5"],"state_sha256":"092483a4d25863a045ad5021de9ece7bb0bc377c027d8136e92132b06a660330"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"izo9SKf0HJD6ki7QRgV32t5PQYPkNkvve9OWztnAtC5uKWzu3AFPMVg4siwDGZAE0i1039/eN8ksSlA0LjQADA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T01:56:09.404175Z","bundle_sha256":"562784cdc89f4403400fcf5c0a093bd7ed7d53f00884f57c99285b5688174ca6"}}