{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QA4I7R64KAS7GMW6IKTZAIDM7P","short_pith_number":"pith:QA4I7R64","canonical_record":{"source":{"id":"2407.07053","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-09T17:18:27Z","cross_cats_sorted":[],"title_canon_sha256":"1ac82da1744016bae2f7bb511ec12dc1f04b309a7adbe3b70c1c289f6c847fdf","abstract_canon_sha256":"3340b7aca265cce48bdd99d455a9387ab46fd60eef767ebb392f2e7216cd97cd"},"schema_version":"1.0"},"canonical_sha256":"80388fc7dc5025f332de42a790206cfbf6dfd18cd3029599d289865b13fd2bdb","source":{"kind":"arxiv","id":"2407.07053","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.07053","created_at":"2026-07-05T09:15:12Z"},{"alias_kind":"arxiv_version","alias_value":"2407.07053v5","created_at":"2026-07-05T09:15:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.07053","created_at":"2026-07-05T09:15:12Z"},{"alias_kind":"pith_short_12","alias_value":"QA4I7R64KAS7","created_at":"2026-07-05T09:15:12Z"},{"alias_kind":"pith_short_16","alias_value":"QA4I7R64KAS7GMW6","created_at":"2026-07-05T09:15:12Z"},{"alias_kind":"pith_short_8","alias_value":"QA4I7R64","created_at":"2026-07-05T09:15:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QA4I7R64KAS7GMW6IKTZAIDM7P","target":"record","payload":{"canonical_record":{"source":{"id":"2407.07053","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-09T17:18:27Z","cross_cats_sorted":[],"title_canon_sha256":"1ac82da1744016bae2f7bb511ec12dc1f04b309a7adbe3b70c1c289f6c847fdf","abstract_canon_sha256":"3340b7aca265cce48bdd99d455a9387ab46fd60eef767ebb392f2e7216cd97cd"},"schema_version":"1.0"},"canonical_sha256":"80388fc7dc5025f332de42a790206cfbf6dfd18cd3029599d289865b13fd2bdb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:12.928206Z","signature_b64":"O3a5A8YwyUSSMo58AXO16R3dd7UBPI7/gaxCWheL4Q/VY6BOGOllCnsbhOBD01UiZQz8IwB7TyN1e25TsArOAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80388fc7dc5025f332de42a790206cfbf6dfd18cd3029599d289865b13fd2bdb","last_reissued_at":"2026-07-05T09:15:12.927743Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:12.927743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.07053","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:15:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DfqEA75xWE4KeR/Zy+9AjiRivdDyeKFZox4hTsvzBsAbuTu+s2DpgBfEdm/dhrQvlmAzye0ZTLJiNZST9OpTCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:26:46.563699Z"},"content_sha256":"1cc97fc1f3ab8a1795a5dae119fe84d9974721ff5d03e79cf1cddabd114b2d7c","schema_version":"1.0","event_id":"sha256:1cc97fc1f3ab8a1795a5dae119fe84d9974721ff5d03e79cf1cddabd114b2d7c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QA4I7R64KAS7GMW6IKTZAIDM7P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multimodal Self-Instruct: Synthetic Abstract Image and Visual Reasoning Instruction Using Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guiyang Hou, Mengna Wang, Mingqian He, Weiming Lu, Wenqi Zhang, Yanna Ma, Yongliang Shen, Yuanyu He, Yueting Zhuang, Zeqi Tan, Zhenglin Cheng","submitted_at":"2024-07-09T17:18:27Z","abstract_excerpt":"Although most current large multimodal models (LMMs) can already understand photos of natural scenes and portraits, their understanding of abstract images, e.g., charts, maps, or layouts, and visual reasoning capabilities remains quite rudimentary. They often struggle with simple daily tasks, such as reading time from a clock, understanding a flowchart, or planning a route using a road map. In light of this, we design a multi-modal self-instruct, utilizing large language models and their code capabilities to synthesize massive abstract images and visual reasoning instructions across daily scen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.07053","kind":"arxiv","version":5},"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/2407.07053/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":"2026-07-05T09:15:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mUIPvPlNDLvKwpRGpMLOCzqUNptTLRF7RMmNbJEDyBPytWXOfenues4NOsy+JHspX2yopgK8erA9I32hchFVDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:26:46.564070Z"},"content_sha256":"028e93e6f33b0c5ebba76895187f3647ef851fe5f2b665aa09bcb9772db2b3f0","schema_version":"1.0","event_id":"sha256:028e93e6f33b0c5ebba76895187f3647ef851fe5f2b665aa09bcb9772db2b3f0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QA4I7R64KAS7GMW6IKTZAIDM7P/bundle.json","state_url":"https://pith.science/pith/QA4I7R64KAS7GMW6IKTZAIDM7P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QA4I7R64KAS7GMW6IKTZAIDM7P/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":"2026-07-07T09:26:46Z","links":{"resolver":"https://pith.science/pith/QA4I7R64KAS7GMW6IKTZAIDM7P","bundle":"https://pith.science/pith/QA4I7R64KAS7GMW6IKTZAIDM7P/bundle.json","state":"https://pith.science/pith/QA4I7R64KAS7GMW6IKTZAIDM7P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QA4I7R64KAS7GMW6IKTZAIDM7P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QA4I7R64KAS7GMW6IKTZAIDM7P","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":"3340b7aca265cce48bdd99d455a9387ab46fd60eef767ebb392f2e7216cd97cd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-09T17:18:27Z","title_canon_sha256":"1ac82da1744016bae2f7bb511ec12dc1f04b309a7adbe3b70c1c289f6c847fdf"},"schema_version":"1.0","source":{"id":"2407.07053","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.07053","created_at":"2026-07-05T09:15:12Z"},{"alias_kind":"arxiv_version","alias_value":"2407.07053v5","created_at":"2026-07-05T09:15:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.07053","created_at":"2026-07-05T09:15:12Z"},{"alias_kind":"pith_short_12","alias_value":"QA4I7R64KAS7","created_at":"2026-07-05T09:15:12Z"},{"alias_kind":"pith_short_16","alias_value":"QA4I7R64KAS7GMW6","created_at":"2026-07-05T09:15:12Z"},{"alias_kind":"pith_short_8","alias_value":"QA4I7R64","created_at":"2026-07-05T09:15:12Z"}],"graph_snapshots":[{"event_id":"sha256:028e93e6f33b0c5ebba76895187f3647ef851fe5f2b665aa09bcb9772db2b3f0","target":"graph","created_at":"2026-07-05T09:15:12Z","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/2407.07053/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although most current large multimodal models (LMMs) can already understand photos of natural scenes and portraits, their understanding of abstract images, e.g., charts, maps, or layouts, and visual reasoning capabilities remains quite rudimentary. They often struggle with simple daily tasks, such as reading time from a clock, understanding a flowchart, or planning a route using a road map. In light of this, we design a multi-modal self-instruct, utilizing large language models and their code capabilities to synthesize massive abstract images and visual reasoning instructions across daily scen","authors_text":"Guiyang Hou, Mengna Wang, Mingqian He, Weiming Lu, Wenqi Zhang, Yanna Ma, Yongliang Shen, Yuanyu He, Yueting Zhuang, Zeqi Tan, Zhenglin Cheng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-09T17:18:27Z","title":"Multimodal Self-Instruct: Synthetic Abstract Image and Visual Reasoning Instruction Using Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.07053","kind":"arxiv","version":5},"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":"sha256:1cc97fc1f3ab8a1795a5dae119fe84d9974721ff5d03e79cf1cddabd114b2d7c","target":"record","created_at":"2026-07-05T09:15:12Z","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":"3340b7aca265cce48bdd99d455a9387ab46fd60eef767ebb392f2e7216cd97cd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-09T17:18:27Z","title_canon_sha256":"1ac82da1744016bae2f7bb511ec12dc1f04b309a7adbe3b70c1c289f6c847fdf"},"schema_version":"1.0","source":{"id":"2407.07053","kind":"arxiv","version":5}},"canonical_sha256":"80388fc7dc5025f332de42a790206cfbf6dfd18cd3029599d289865b13fd2bdb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80388fc7dc5025f332de42a790206cfbf6dfd18cd3029599d289865b13fd2bdb","first_computed_at":"2026-07-05T09:15:12.927743Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:15:12.927743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O3a5A8YwyUSSMo58AXO16R3dd7UBPI7/gaxCWheL4Q/VY6BOGOllCnsbhOBD01UiZQz8IwB7TyN1e25TsArOAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:15:12.928206Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.07053","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1cc97fc1f3ab8a1795a5dae119fe84d9974721ff5d03e79cf1cddabd114b2d7c","sha256:028e93e6f33b0c5ebba76895187f3647ef851fe5f2b665aa09bcb9772db2b3f0"],"state_sha256":"332a04b1dd00836f75f42b0230a3435520a01f23c84058c88d0ca13196a6c721"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t5Fj8VbLhpXNg4bjw1w3cIk9R1qAPyC9qVT8srb3FfWcoFRJ14kgdaWxOGcftafAw15CXvH6aDeksl2PZKqBAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T09:26:46.566042Z","bundle_sha256":"dd16cefdb07e6cdbd1e09753772d3aff07b379a8a1501e936845a5d42885e832"}}