{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ES62HFF6G5GHRXHZBYEFTJQKRN","short_pith_number":"pith:ES62HFF6","canonical_record":{"source":{"id":"2309.14389","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-25T07:01:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ff9bee36c2cb1c6f66ed5ce2cba2370149561985048081024dccf8c8b50b6567","abstract_canon_sha256":"c8b6db26c408af6749544f0fed5c7e87023caa870e7311379ad78d395b3eb6ba"},"schema_version":"1.0"},"canonical_sha256":"24bda394be374c78dcf90e0859a60a8b62aeb9c8f10620ac6dd6a940d87766b1","source":{"kind":"arxiv","id":"2309.14389","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.14389","created_at":"2026-07-05T06:54:24Z"},{"alias_kind":"arxiv_version","alias_value":"2309.14389v1","created_at":"2026-07-05T06:54:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.14389","created_at":"2026-07-05T06:54:24Z"},{"alias_kind":"pith_short_12","alias_value":"ES62HFF6G5GH","created_at":"2026-07-05T06:54:24Z"},{"alias_kind":"pith_short_16","alias_value":"ES62HFF6G5GHRXHZ","created_at":"2026-07-05T06:54:24Z"},{"alias_kind":"pith_short_8","alias_value":"ES62HFF6","created_at":"2026-07-05T06:54:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ES62HFF6G5GHRXHZBYEFTJQKRN","target":"record","payload":{"canonical_record":{"source":{"id":"2309.14389","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-25T07:01:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ff9bee36c2cb1c6f66ed5ce2cba2370149561985048081024dccf8c8b50b6567","abstract_canon_sha256":"c8b6db26c408af6749544f0fed5c7e87023caa870e7311379ad78d395b3eb6ba"},"schema_version":"1.0"},"canonical_sha256":"24bda394be374c78dcf90e0859a60a8b62aeb9c8f10620ac6dd6a940d87766b1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:54:24.942645Z","signature_b64":"WEIp5bWV2o4o0NToKcq9adFdNG83PIqUDLE+54/2/eb78LC/0ecfT1lF7T33pC4laIHnf24HYFAwscnwma88BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24bda394be374c78dcf90e0859a60a8b62aeb9c8f10620ac6dd6a940d87766b1","last_reissued_at":"2026-07-05T06:54:24.942106Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:54:24.942106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.14389","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":"2026-07-05T06:54:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gNVwA306nfetnj1+bfYtmPTlBjqlrRvVZld4UMXDsgThsV0MXZzIo7BQgE5pO0Xnn1xiFYa7QOzmyZMavM8XAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T08:23:34.609407Z"},"content_sha256":"918ee16c5c73aee553f1b6e60055f1ba461d41c2032e3e14034a24d5aca7d303","schema_version":"1.0","event_id":"sha256:918ee16c5c73aee553f1b6e60055f1ba461d41c2032e3e14034a24d5aca7d303"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ES62HFF6G5GHRXHZBYEFTJQKRN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Analyzing the Efficacy of an LLM-Only Approach for Image-based Document Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Gagan Madan, Gaurav Aggarwal, Nidhi Hegde, Sujoy Paul","submitted_at":"2023-09-25T07:01:16Z","abstract_excerpt":"Recent document question answering models consist of two key components: the vision encoder, which captures layout and visual elements in images, and a Large Language Model (LLM) that helps contextualize questions to the image and supplements them with external world knowledge to generate accurate answers. However, the relative contributions of the vision encoder and the language model in these tasks remain unclear. This is especially interesting given the effectiveness of instruction-tuned LLMs, which exhibit remarkable adaptability to new tasks. To this end, we explore the following aspects "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.14389","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/2309.14389/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":"2026-07-05T06:54:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7tpFKg0euiSFUclS1df3NBKA25uqWO1zOlOwANcd7YZZXUpn4/D7mNVR0b7YXeVcVC+yzOvffSeHPxwWW2vuDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T08:23:34.609972Z"},"content_sha256":"d763e68533a9ed140294f139d947d19dfc7ea4960538f6dcdf4982e6f378f5f7","schema_version":"1.0","event_id":"sha256:d763e68533a9ed140294f139d947d19dfc7ea4960538f6dcdf4982e6f378f5f7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ES62HFF6G5GHRXHZBYEFTJQKRN/bundle.json","state_url":"https://pith.science/pith/ES62HFF6G5GHRXHZBYEFTJQKRN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ES62HFF6G5GHRXHZBYEFTJQKRN/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":"2026-08-14T08:23:34Z","links":{"resolver":"https://pith.science/pith/ES62HFF6G5GHRXHZBYEFTJQKRN","bundle":"https://pith.science/pith/ES62HFF6G5GHRXHZBYEFTJQKRN/bundle.json","state":"https://pith.science/pith/ES62HFF6G5GHRXHZBYEFTJQKRN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ES62HFF6G5GHRXHZBYEFTJQKRN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ES62HFF6G5GHRXHZBYEFTJQKRN","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":"c8b6db26c408af6749544f0fed5c7e87023caa870e7311379ad78d395b3eb6ba","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-25T07:01:16Z","title_canon_sha256":"ff9bee36c2cb1c6f66ed5ce2cba2370149561985048081024dccf8c8b50b6567"},"schema_version":"1.0","source":{"id":"2309.14389","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.14389","created_at":"2026-07-05T06:54:24Z"},{"alias_kind":"arxiv_version","alias_value":"2309.14389v1","created_at":"2026-07-05T06:54:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.14389","created_at":"2026-07-05T06:54:24Z"},{"alias_kind":"pith_short_12","alias_value":"ES62HFF6G5GH","created_at":"2026-07-05T06:54:24Z"},{"alias_kind":"pith_short_16","alias_value":"ES62HFF6G5GHRXHZ","created_at":"2026-07-05T06:54:24Z"},{"alias_kind":"pith_short_8","alias_value":"ES62HFF6","created_at":"2026-07-05T06:54:24Z"}],"graph_snapshots":[{"event_id":"sha256:d763e68533a9ed140294f139d947d19dfc7ea4960538f6dcdf4982e6f378f5f7","target":"graph","created_at":"2026-07-05T06:54:24Z","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/2309.14389/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent document question answering models consist of two key components: the vision encoder, which captures layout and visual elements in images, and a Large Language Model (LLM) that helps contextualize questions to the image and supplements them with external world knowledge to generate accurate answers. However, the relative contributions of the vision encoder and the language model in these tasks remain unclear. This is especially interesting given the effectiveness of instruction-tuned LLMs, which exhibit remarkable adaptability to new tasks. To this end, we explore the following aspects ","authors_text":"Gagan Madan, Gaurav Aggarwal, Nidhi Hegde, Sujoy Paul","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-25T07:01:16Z","title":"Analyzing the Efficacy of an LLM-Only Approach for Image-based Document Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.14389","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":"sha256:918ee16c5c73aee553f1b6e60055f1ba461d41c2032e3e14034a24d5aca7d303","target":"record","created_at":"2026-07-05T06:54:24Z","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":"c8b6db26c408af6749544f0fed5c7e87023caa870e7311379ad78d395b3eb6ba","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-25T07:01:16Z","title_canon_sha256":"ff9bee36c2cb1c6f66ed5ce2cba2370149561985048081024dccf8c8b50b6567"},"schema_version":"1.0","source":{"id":"2309.14389","kind":"arxiv","version":1}},"canonical_sha256":"24bda394be374c78dcf90e0859a60a8b62aeb9c8f10620ac6dd6a940d87766b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24bda394be374c78dcf90e0859a60a8b62aeb9c8f10620ac6dd6a940d87766b1","first_computed_at":"2026-07-05T06:54:24.942106Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:54:24.942106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WEIp5bWV2o4o0NToKcq9adFdNG83PIqUDLE+54/2/eb78LC/0ecfT1lF7T33pC4laIHnf24HYFAwscnwma88BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:54:24.942645Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.14389","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:918ee16c5c73aee553f1b6e60055f1ba461d41c2032e3e14034a24d5aca7d303","sha256:d763e68533a9ed140294f139d947d19dfc7ea4960538f6dcdf4982e6f378f5f7"],"state_sha256":"a707251df29d48c57e9049a2b6160f9728c3b183dab5453d8adf49ec37c00317"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qOSd4HUxXvnlejoxzF9i9mfeBId3WFyPBLLG0D4ko2aW2dMqxH6fAXxoSiyQ/eXmG6BhY/NfsG5RFlDsB5WOAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T08:23:34.613590Z","bundle_sha256":"ba719c9a4beb3e7cfc92c271b48084942b45b19fd1659e4c4a3a6ec59edf7b5c"}}