{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:5X5R6JM6G4THZHFIJ2YF4IWDCW","short_pith_number":"pith:5X5R6JM6","canonical_record":{"source":{"id":"2311.09612","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-16T06:50:26Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d511479d52f8c894a625813a82abf3c9a0cbdf96670d594f020c5b69534e4cff","abstract_canon_sha256":"b66d9469ae83691a9a17a4c8da661deee6830ca4fe34a3da3868b25986db8fcc"},"schema_version":"1.0"},"canonical_sha256":"edfb1f259e37267c9ca84eb05e22c315b86abf97b871dadcd65f7abc688ae69e","source":{"kind":"arxiv","id":"2311.09612","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.09612","created_at":"2026-07-05T08:03:08Z"},{"alias_kind":"arxiv_version","alias_value":"2311.09612v2","created_at":"2026-07-05T08:03:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09612","created_at":"2026-07-05T08:03:08Z"},{"alias_kind":"pith_short_12","alias_value":"5X5R6JM6G4TH","created_at":"2026-07-05T08:03:08Z"},{"alias_kind":"pith_short_16","alias_value":"5X5R6JM6G4THZHFI","created_at":"2026-07-05T08:03:08Z"},{"alias_kind":"pith_short_8","alias_value":"5X5R6JM6","created_at":"2026-07-05T08:03:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:5X5R6JM6G4THZHFIJ2YF4IWDCW","target":"record","payload":{"canonical_record":{"source":{"id":"2311.09612","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-16T06:50:26Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d511479d52f8c894a625813a82abf3c9a0cbdf96670d594f020c5b69534e4cff","abstract_canon_sha256":"b66d9469ae83691a9a17a4c8da661deee6830ca4fe34a3da3868b25986db8fcc"},"schema_version":"1.0"},"canonical_sha256":"edfb1f259e37267c9ca84eb05e22c315b86abf97b871dadcd65f7abc688ae69e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:08.647556Z","signature_b64":"iPBd1CVEG1rZeerj4o2vZGkv+/sy973Qrvbvvx+jHKAQ8cJT9zNKqg/SshPFbqsMUcqOXNWVA77CcPeY7iPmDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"edfb1f259e37267c9ca84eb05e22c315b86abf97b871dadcd65f7abc688ae69e","last_reissued_at":"2026-07-05T08:03:08.647062Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:08.647062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.09612","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:03:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jOXVwCf6mtAHf5wW8dsYuRTP8wy+NfZx5dTAcVKtyCMPJC0NKf7Xz3yL0Qr9YFt8vmZOyU+JS/5nWPUel3J7Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:52:54.045546Z"},"content_sha256":"0b1ad540264bbcf033efb18b34d886b311265b183f4a8ada12f63f6ad4317ae8","schema_version":"1.0","event_id":"sha256:0b1ad540264bbcf033efb18b34d886b311265b183f4a8ada12f63f6ad4317ae8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:5X5R6JM6G4THZHFIJ2YF4IWDCW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient End-to-End Visual Document Understanding with Rationale Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Alekh Agarwal, Jesse Thomason, Kristina Toutanova, Mandar Joshi, Robin Jia, Wang Zhu","submitted_at":"2023-11-16T06:50:26Z","abstract_excerpt":"Understanding visually situated language requires interpreting complex layouts of textual and visual elements. Pre-processing tools, such as optical character recognition (OCR), can map document image inputs to textual tokens, then large language models (LLMs) can reason over text. However, such methods have high computational and engineering complexity. Can small pretrained image-to-text models accurately understand visual documents through similar recognition and reasoning steps instead? We propose Rationale Distillation (RD), which incorporates the outputs of OCR tools, LLMs, and larger mul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09612","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/2311.09612/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":"2026-07-05T08:03:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gm+34deCayQM7v6Q3jKDMwPOWO/kfW0k3L4U3GGKTOcLew4VPQKhDns/xWPpeRBNEhPrTfCl4RywIkkdWjaGBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:52:54.046602Z"},"content_sha256":"7a86f7cc23a62373f1b0d373559257426b06f7ffa1092d830d6d7bde9068d26f","schema_version":"1.0","event_id":"sha256:7a86f7cc23a62373f1b0d373559257426b06f7ffa1092d830d6d7bde9068d26f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5X5R6JM6G4THZHFIJ2YF4IWDCW/bundle.json","state_url":"https://pith.science/pith/5X5R6JM6G4THZHFIJ2YF4IWDCW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5X5R6JM6G4THZHFIJ2YF4IWDCW/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":"2026-08-05T11:52:54Z","links":{"resolver":"https://pith.science/pith/5X5R6JM6G4THZHFIJ2YF4IWDCW","bundle":"https://pith.science/pith/5X5R6JM6G4THZHFIJ2YF4IWDCW/bundle.json","state":"https://pith.science/pith/5X5R6JM6G4THZHFIJ2YF4IWDCW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5X5R6JM6G4THZHFIJ2YF4IWDCW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5X5R6JM6G4THZHFIJ2YF4IWDCW","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":"b66d9469ae83691a9a17a4c8da661deee6830ca4fe34a3da3868b25986db8fcc","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-16T06:50:26Z","title_canon_sha256":"d511479d52f8c894a625813a82abf3c9a0cbdf96670d594f020c5b69534e4cff"},"schema_version":"1.0","source":{"id":"2311.09612","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.09612","created_at":"2026-07-05T08:03:08Z"},{"alias_kind":"arxiv_version","alias_value":"2311.09612v2","created_at":"2026-07-05T08:03:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09612","created_at":"2026-07-05T08:03:08Z"},{"alias_kind":"pith_short_12","alias_value":"5X5R6JM6G4TH","created_at":"2026-07-05T08:03:08Z"},{"alias_kind":"pith_short_16","alias_value":"5X5R6JM6G4THZHFI","created_at":"2026-07-05T08:03:08Z"},{"alias_kind":"pith_short_8","alias_value":"5X5R6JM6","created_at":"2026-07-05T08:03:08Z"}],"graph_snapshots":[{"event_id":"sha256:7a86f7cc23a62373f1b0d373559257426b06f7ffa1092d830d6d7bde9068d26f","target":"graph","created_at":"2026-07-05T08:03:08Z","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/2311.09612/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding visually situated language requires interpreting complex layouts of textual and visual elements. Pre-processing tools, such as optical character recognition (OCR), can map document image inputs to textual tokens, then large language models (LLMs) can reason over text. However, such methods have high computational and engineering complexity. Can small pretrained image-to-text models accurately understand visual documents through similar recognition and reasoning steps instead? We propose Rationale Distillation (RD), which incorporates the outputs of OCR tools, LLMs, and larger mul","authors_text":"Alekh Agarwal, Jesse Thomason, Kristina Toutanova, Mandar Joshi, Robin Jia, Wang Zhu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-16T06:50:26Z","title":"Efficient End-to-End Visual Document Understanding with Rationale Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09612","kind":"arxiv","version":2},"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":"sha256:0b1ad540264bbcf033efb18b34d886b311265b183f4a8ada12f63f6ad4317ae8","target":"record","created_at":"2026-07-05T08:03:08Z","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":"b66d9469ae83691a9a17a4c8da661deee6830ca4fe34a3da3868b25986db8fcc","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-16T06:50:26Z","title_canon_sha256":"d511479d52f8c894a625813a82abf3c9a0cbdf96670d594f020c5b69534e4cff"},"schema_version":"1.0","source":{"id":"2311.09612","kind":"arxiv","version":2}},"canonical_sha256":"edfb1f259e37267c9ca84eb05e22c315b86abf97b871dadcd65f7abc688ae69e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"edfb1f259e37267c9ca84eb05e22c315b86abf97b871dadcd65f7abc688ae69e","first_computed_at":"2026-07-05T08:03:08.647062Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:03:08.647062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iPBd1CVEG1rZeerj4o2vZGkv+/sy973Qrvbvvx+jHKAQ8cJT9zNKqg/SshPFbqsMUcqOXNWVA77CcPeY7iPmDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:03:08.647556Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.09612","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b1ad540264bbcf033efb18b34d886b311265b183f4a8ada12f63f6ad4317ae8","sha256:7a86f7cc23a62373f1b0d373559257426b06f7ffa1092d830d6d7bde9068d26f"],"state_sha256":"39bc19afe39d0c709b432f41b5ddf75eae0b80bc840974cdbff68ba5f28999d2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QRIVpUhAkeOJrgAl0ej4IMqTfZeNmkqGnFy2MTwjFnBXEfFo55CTss/9/KZsyHY26tCBjLKr+A75BEXzuQpZBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T11:52:54.056290Z","bundle_sha256":"e7495177ccee3bd825b34bc185020a358428cd22d2ee3afceae40accef13a8f0"}}