{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NDY2FZUNFRY36DVNYA5KHH6EYK","short_pith_number":"pith:NDY2FZUN","canonical_record":{"source":{"id":"2404.12803","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-19T11:38:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bb35a22a3703a26447d479b6c56b02921b27a7a7829bb63accf918bd0f98adf3","abstract_canon_sha256":"986188194bc553236b21edf4a285ea38e9bd45897a6899fb2928830ad6addeb5"},"schema_version":"1.0"},"canonical_sha256":"68f1a2e68d2c71bf0eadc03aa39fc4c2b363d734550636e57e835bb829466100","source":{"kind":"arxiv","id":"2404.12803","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.12803","created_at":"2026-07-05T11:19:19Z"},{"alias_kind":"arxiv_version","alias_value":"2404.12803v3","created_at":"2026-07-05T11:19:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.12803","created_at":"2026-07-05T11:19:19Z"},{"alias_kind":"pith_short_12","alias_value":"NDY2FZUNFRY3","created_at":"2026-07-05T11:19:19Z"},{"alias_kind":"pith_short_16","alias_value":"NDY2FZUNFRY36DVN","created_at":"2026-07-05T11:19:19Z"},{"alias_kind":"pith_short_8","alias_value":"NDY2FZUN","created_at":"2026-07-05T11:19:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NDY2FZUNFRY36DVNYA5KHH6EYK","target":"record","payload":{"canonical_record":{"source":{"id":"2404.12803","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-19T11:38:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bb35a22a3703a26447d479b6c56b02921b27a7a7829bb63accf918bd0f98adf3","abstract_canon_sha256":"986188194bc553236b21edf4a285ea38e9bd45897a6899fb2928830ad6addeb5"},"schema_version":"1.0"},"canonical_sha256":"68f1a2e68d2c71bf0eadc03aa39fc4c2b363d734550636e57e835bb829466100","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:19.057862Z","signature_b64":"Ktk4xba9fKdx9pZN5td2NpkLDmSMu+GJWS3cw1Yc11FJeyhCFCZsxyCY2yC3XkiB3zjZpK3n/o5+ZBUSSNPzCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68f1a2e68d2c71bf0eadc03aa39fc4c2b363d734550636e57e835bb829466100","last_reissued_at":"2026-07-05T11:19:19.057334Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:19.057334Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.12803","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:19:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O3DjJk+wsAgujWcXa+oMCAk0tcxfXTvfMPOEsjRypm4duJ48KTKspsQsQtO0cUL/tSVOjTqLkXKJhcbCGzdNAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T11:03:34.426149Z"},"content_sha256":"a4ecef98cef21854a31c7ebed78cc5b855ea1201f6f58e0e3a135c64b4af0931","schema_version":"1.0","event_id":"sha256:a4ecef98cef21854a31c7ebed78cc5b855ea1201f6f58e0e3a135c64b4af0931"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NDY2FZUNFRY36DVNYA5KHH6EYK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TextSquare: Scaling up Text-Centric Visual Instruction Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Binghong Wu, Can Huang, Chunhui Lin, Hao Feng, Hao Liu, Jingqun Tang, Kuan Lu, Lei Liao, Qi Liu, Shu Wei, Siqi Wang, Wei Shi, Xiang Bai, Yangfan He, Yang Li, Yuan Xie, Yuliang Liu, Zhen Zhao","submitted_at":"2024-04-19T11:38:08Z","abstract_excerpt":"Text-centric visual question answering (VQA) has made great strides with the development of Multimodal Large Language Models (MLLMs), yet open-source models still fall short of leading models like GPT4V and Gemini, partly due to a lack of extensive, high-quality instruction tuning data. To this end, we introduce a new approach for creating a massive, high-quality instruction-tuning dataset, Square-10M, which is generated using closed-source MLLMs. The data construction process, termed Square, consists of four steps: Self-Questioning, Answering, Reasoning, and Evaluation. Our experiments with S"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.12803","kind":"arxiv","version":3},"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/2404.12803/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":"2026-07-05T11:19:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OZnBPglUCz+SXwAAZIVrVsdhEVxFoLJGuO6P7vaXtqviJwlabVROkm/pRpgnxDTewTIy0nZMmL0fX+xbQ6M4Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T11:03:34.427145Z"},"content_sha256":"69d13fdf5446a246b27cdea473ae77c61f050cebcaab4569a60928a851a08cf0","schema_version":"1.0","event_id":"sha256:69d13fdf5446a246b27cdea473ae77c61f050cebcaab4569a60928a851a08cf0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NDY2FZUNFRY36DVNYA5KHH6EYK/bundle.json","state_url":"https://pith.science/pith/NDY2FZUNFRY36DVNYA5KHH6EYK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NDY2FZUNFRY36DVNYA5KHH6EYK/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":"2026-08-12T11:03:34Z","links":{"resolver":"https://pith.science/pith/NDY2FZUNFRY36DVNYA5KHH6EYK","bundle":"https://pith.science/pith/NDY2FZUNFRY36DVNYA5KHH6EYK/bundle.json","state":"https://pith.science/pith/NDY2FZUNFRY36DVNYA5KHH6EYK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NDY2FZUNFRY36DVNYA5KHH6EYK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NDY2FZUNFRY36DVNYA5KHH6EYK","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":"986188194bc553236b21edf4a285ea38e9bd45897a6899fb2928830ad6addeb5","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-19T11:38:08Z","title_canon_sha256":"bb35a22a3703a26447d479b6c56b02921b27a7a7829bb63accf918bd0f98adf3"},"schema_version":"1.0","source":{"id":"2404.12803","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.12803","created_at":"2026-07-05T11:19:19Z"},{"alias_kind":"arxiv_version","alias_value":"2404.12803v3","created_at":"2026-07-05T11:19:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.12803","created_at":"2026-07-05T11:19:19Z"},{"alias_kind":"pith_short_12","alias_value":"NDY2FZUNFRY3","created_at":"2026-07-05T11:19:19Z"},{"alias_kind":"pith_short_16","alias_value":"NDY2FZUNFRY36DVN","created_at":"2026-07-05T11:19:19Z"},{"alias_kind":"pith_short_8","alias_value":"NDY2FZUN","created_at":"2026-07-05T11:19:19Z"}],"graph_snapshots":[{"event_id":"sha256:69d13fdf5446a246b27cdea473ae77c61f050cebcaab4569a60928a851a08cf0","target":"graph","created_at":"2026-07-05T11:19:19Z","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/2404.12803/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-centric visual question answering (VQA) has made great strides with the development of Multimodal Large Language Models (MLLMs), yet open-source models still fall short of leading models like GPT4V and Gemini, partly due to a lack of extensive, high-quality instruction tuning data. To this end, we introduce a new approach for creating a massive, high-quality instruction-tuning dataset, Square-10M, which is generated using closed-source MLLMs. The data construction process, termed Square, consists of four steps: Self-Questioning, Answering, Reasoning, and Evaluation. Our experiments with S","authors_text":"Binghong Wu, Can Huang, Chunhui Lin, Hao Feng, Hao Liu, Jingqun Tang, Kuan Lu, Lei Liao, Qi Liu, Shu Wei, Siqi Wang, Wei Shi, Xiang Bai, Yangfan He, Yang Li, Yuan Xie, Yuliang Liu, Zhen Zhao","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-19T11:38:08Z","title":"TextSquare: Scaling up Text-Centric Visual Instruction Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.12803","kind":"arxiv","version":3},"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:a4ecef98cef21854a31c7ebed78cc5b855ea1201f6f58e0e3a135c64b4af0931","target":"record","created_at":"2026-07-05T11:19:19Z","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":"986188194bc553236b21edf4a285ea38e9bd45897a6899fb2928830ad6addeb5","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-19T11:38:08Z","title_canon_sha256":"bb35a22a3703a26447d479b6c56b02921b27a7a7829bb63accf918bd0f98adf3"},"schema_version":"1.0","source":{"id":"2404.12803","kind":"arxiv","version":3}},"canonical_sha256":"68f1a2e68d2c71bf0eadc03aa39fc4c2b363d734550636e57e835bb829466100","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"68f1a2e68d2c71bf0eadc03aa39fc4c2b363d734550636e57e835bb829466100","first_computed_at":"2026-07-05T11:19:19.057334Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:19.057334Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ktk4xba9fKdx9pZN5td2NpkLDmSMu+GJWS3cw1Yc11FJeyhCFCZsxyCY2yC3XkiB3zjZpK3n/o5+ZBUSSNPzCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:19.057862Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.12803","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a4ecef98cef21854a31c7ebed78cc5b855ea1201f6f58e0e3a135c64b4af0931","sha256:69d13fdf5446a246b27cdea473ae77c61f050cebcaab4569a60928a851a08cf0"],"state_sha256":"498cf4b46fb676f7febc824e5d617d6e2ce024aef7eb2304f3e3bafbbecc51e8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DGMDtgVTTwrkQ8nWFV3vuJOqHnc0L7DfZqhInfQA82fc5a/P49NaU+kiTzEjB71KMRhVe+2VpDsocgBzjJrtCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T11:03:34.432810Z","bundle_sha256":"dd366626464e565cfed4d3f3757f50d3bea7104222de2823b1d17954b6d620fe"}}