{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VWLSVLZI5AVIF32KTJD2ZOSZIF","short_pith_number":"pith:VWLSVLZI","canonical_record":{"source":{"id":"2412.04626","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-05T21:41:20Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"5e18c0313a0f2621cd6f9bd3c909d1f59b184ce8de18082c83eb07c91425a955","abstract_canon_sha256":"32288d787bff0db1ee81e7ec617a84f203490e6fa19e9abfc48019e534511156"},"schema_version":"1.0"},"canonical_sha256":"ad972aaf28e82a82ef4a9a47acba59415081eb0fea4b361eb2a5b2a0795c281a","source":{"kind":"arxiv","id":"2412.04626","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.04626","created_at":"2026-07-05T10:32:35Z"},{"alias_kind":"arxiv_version","alias_value":"2412.04626v2","created_at":"2026-07-05T10:32:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04626","created_at":"2026-07-05T10:32:35Z"},{"alias_kind":"pith_short_12","alias_value":"VWLSVLZI5AVI","created_at":"2026-07-05T10:32:35Z"},{"alias_kind":"pith_short_16","alias_value":"VWLSVLZI5AVIF32K","created_at":"2026-07-05T10:32:35Z"},{"alias_kind":"pith_short_8","alias_value":"VWLSVLZI","created_at":"2026-07-05T10:32:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VWLSVLZI5AVIF32KTJD2ZOSZIF","target":"record","payload":{"canonical_record":{"source":{"id":"2412.04626","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-05T21:41:20Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"5e18c0313a0f2621cd6f9bd3c909d1f59b184ce8de18082c83eb07c91425a955","abstract_canon_sha256":"32288d787bff0db1ee81e7ec617a84f203490e6fa19e9abfc48019e534511156"},"schema_version":"1.0"},"canonical_sha256":"ad972aaf28e82a82ef4a9a47acba59415081eb0fea4b361eb2a5b2a0795c281a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:32:35.159465Z","signature_b64":"HlaAxUcdYMpOum7SBjyqxRHQqDx0oLMU90cHgghjUSYN/kaD37zFNJCcLwNrnN8zrusz8DbtezaeHwWNyfxTAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad972aaf28e82a82ef4a9a47acba59415081eb0fea4b361eb2a5b2a0795c281a","last_reissued_at":"2026-07-05T10:32:35.158824Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:32:35.158824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.04626","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":"2026-07-05T10:32:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QwQ9CBhEBzqpMt4c5DMq9tXD5czTpRsDxnqwo4CiG/iw4fSs4ivWLkljCXy/v7Lw6NNxi3dklLbflB8zJbnRCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T23:12:57.420290Z"},"content_sha256":"d571d03e03363738e5e7a967ec40648a5ce67cbe7000f629c75d0a8903f3af76","schema_version":"1.0","event_id":"sha256:d571d03e03363738e5e7a967ec40648a5ce67cbe7000f629c75d0a8903f3af76"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VWLSVLZI5AVIF32KTJD2ZOSZIF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BigDocs: An Open Dataset for Training Multimodal Models on Document and Code Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Aarash Feizi, Abhay Puri, Ahmed Masry, Akshay Kalkunte, Amirhossein Abaskohi, Christopher Pal, David Vazquez, Fran\\c{c}ois Savard, Issam Laradji, Joao Monteiro, Juan Rodriguez, Krishnamurthy Dj Dvijotham, Kurt MacDonald, Mahsa Massoud, Marco Pedersoli, Mats Leon Richter, M. \\\"Ozsu, Nicolas Chapados, Noah Bolger, Perouz Taslakian, Pierre-Andr\\'e No\\\"el, Rabiul Awal, Sai Rajeswar, Sanket Biswas, Sara Shanian, Sathwik Tejaswi, Saverio Vadacchino, Sean Hughes, Sepideh Kharagani, Shravan Nayak, Shubham Agarwal, Siba Smarak Panigrahi, Simon Fauvel, Siva Reddy, Spandana Gella, Srinivas Sunkara, Suyuchen Wang, Tianyu Zhang, Torsten Scholak, Xiangru Jian, Ying Zhang, Yoshua Bengio, Zichao Li","submitted_at":"2024-12-05T21:41:20Z","abstract_excerpt":"Multimodal AI has the potential to significantly enhance document-understanding tasks, such as processing receipts, understanding workflows, extracting data from documents, and summarizing reports. Code generation tasks that require long-structured outputs can also be enhanced by multimodality. Despite this, their use in commercial applications is often limited due to limited access to training data and restrictive licensing, which hinders open access. To address these limitations, we introduce BigDocs-7.5M, a high-quality, open-access dataset comprising 7.5 million multimodal documents across"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04626","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/2412.04626/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":"2026-07-05T10:32:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tKx2574uI7V7VLvbpkthQ2Hst8UMdiGeX/1mJkHSxUpMGBU/4jcngYxrRHh/Q+CFw6BxrGFo6Lb6OVD5AivZBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T23:12:57.420697Z"},"content_sha256":"e9721be6742218317a1be9ee5c316dcbbd345ffe6b5bbad95e8e030408ca20f1","schema_version":"1.0","event_id":"sha256:e9721be6742218317a1be9ee5c316dcbbd345ffe6b5bbad95e8e030408ca20f1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VWLSVLZI5AVIF32KTJD2ZOSZIF/bundle.json","state_url":"https://pith.science/pith/VWLSVLZI5AVIF32KTJD2ZOSZIF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VWLSVLZI5AVIF32KTJD2ZOSZIF/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":"2026-07-09T23:12:57Z","links":{"resolver":"https://pith.science/pith/VWLSVLZI5AVIF32KTJD2ZOSZIF","bundle":"https://pith.science/pith/VWLSVLZI5AVIF32KTJD2ZOSZIF/bundle.json","state":"https://pith.science/pith/VWLSVLZI5AVIF32KTJD2ZOSZIF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VWLSVLZI5AVIF32KTJD2ZOSZIF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VWLSVLZI5AVIF32KTJD2ZOSZIF","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":"32288d787bff0db1ee81e7ec617a84f203490e6fa19e9abfc48019e534511156","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-05T21:41:20Z","title_canon_sha256":"5e18c0313a0f2621cd6f9bd3c909d1f59b184ce8de18082c83eb07c91425a955"},"schema_version":"1.0","source":{"id":"2412.04626","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.04626","created_at":"2026-07-05T10:32:35Z"},{"alias_kind":"arxiv_version","alias_value":"2412.04626v2","created_at":"2026-07-05T10:32:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04626","created_at":"2026-07-05T10:32:35Z"},{"alias_kind":"pith_short_12","alias_value":"VWLSVLZI5AVI","created_at":"2026-07-05T10:32:35Z"},{"alias_kind":"pith_short_16","alias_value":"VWLSVLZI5AVIF32K","created_at":"2026-07-05T10:32:35Z"},{"alias_kind":"pith_short_8","alias_value":"VWLSVLZI","created_at":"2026-07-05T10:32:35Z"}],"graph_snapshots":[{"event_id":"sha256:e9721be6742218317a1be9ee5c316dcbbd345ffe6b5bbad95e8e030408ca20f1","target":"graph","created_at":"2026-07-05T10:32:35Z","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/2412.04626/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal AI has the potential to significantly enhance document-understanding tasks, such as processing receipts, understanding workflows, extracting data from documents, and summarizing reports. Code generation tasks that require long-structured outputs can also be enhanced by multimodality. Despite this, their use in commercial applications is often limited due to limited access to training data and restrictive licensing, which hinders open access. To address these limitations, we introduce BigDocs-7.5M, a high-quality, open-access dataset comprising 7.5 million multimodal documents across","authors_text":"Aarash Feizi, Abhay Puri, Ahmed Masry, Akshay Kalkunte, Amirhossein Abaskohi, Christopher Pal, David Vazquez, Fran\\c{c}ois Savard, Issam Laradji, Joao Monteiro, Juan Rodriguez, Krishnamurthy Dj Dvijotham, Kurt MacDonald, Mahsa Massoud, Marco Pedersoli, Mats Leon Richter, M. \\\"Ozsu, Nicolas Chapados, Noah Bolger, Perouz Taslakian, Pierre-Andr\\'e No\\\"el, Rabiul Awal, Sai Rajeswar, Sanket Biswas, Sara Shanian, Sathwik Tejaswi, Saverio Vadacchino, Sean Hughes, Sepideh Kharagani, Shravan Nayak, Shubham Agarwal, Siba Smarak Panigrahi, Simon Fauvel, Siva Reddy, Spandana Gella, Srinivas Sunkara, Suyuchen Wang, Tianyu Zhang, Torsten Scholak, Xiangru Jian, Ying Zhang, Yoshua Bengio, Zichao Li","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-05T21:41:20Z","title":"BigDocs: An Open Dataset for Training Multimodal Models on Document and Code Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04626","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:d571d03e03363738e5e7a967ec40648a5ce67cbe7000f629c75d0a8903f3af76","target":"record","created_at":"2026-07-05T10:32:35Z","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":"32288d787bff0db1ee81e7ec617a84f203490e6fa19e9abfc48019e534511156","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-05T21:41:20Z","title_canon_sha256":"5e18c0313a0f2621cd6f9bd3c909d1f59b184ce8de18082c83eb07c91425a955"},"schema_version":"1.0","source":{"id":"2412.04626","kind":"arxiv","version":2}},"canonical_sha256":"ad972aaf28e82a82ef4a9a47acba59415081eb0fea4b361eb2a5b2a0795c281a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad972aaf28e82a82ef4a9a47acba59415081eb0fea4b361eb2a5b2a0795c281a","first_computed_at":"2026-07-05T10:32:35.158824Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:32:35.158824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HlaAxUcdYMpOum7SBjyqxRHQqDx0oLMU90cHgghjUSYN/kaD37zFNJCcLwNrnN8zrusz8DbtezaeHwWNyfxTAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:32:35.159465Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.04626","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d571d03e03363738e5e7a967ec40648a5ce67cbe7000f629c75d0a8903f3af76","sha256:e9721be6742218317a1be9ee5c316dcbbd345ffe6b5bbad95e8e030408ca20f1"],"state_sha256":"bd1e24dfd72933103bc541982f982d885a6aa3bd934f373cd1d3fd21ccc33fb6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"noP2rJh/F/cvUiXPFvJfjmg70W/1CS8ya8dKAe+wtn3DXrid9UtXtHMQJEIH+E+cI+UHHtso5xTAVaZV7kplBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T23:12:57.422660Z","bundle_sha256":"6c3ae4e28d103a6fc0a41c6b697706efd1cfec2423532c046276f69a7c8769e6"}}