{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:UPNJDIJ4EAQNECORFSPIKZN6SL","short_pith_number":"pith:UPNJDIJ4","canonical_record":{"source":{"id":"2311.01487","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-02T15:36:12Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"8f99e5762313ea8ec0ad32d7214e315c099438a24cd05e361d4d04ee0e305ffc","abstract_canon_sha256":"c245b0314e705f80dd2cd321e176d08719e122a922562ad534a21e0842593be3"},"schema_version":"1.0"},"canonical_sha256":"a3da91a13c2020d209d12c9e8565be92e617bcd6a27a93280b5cf0f5ea03266a","source":{"kind":"arxiv","id":"2311.01487","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.01487","created_at":"2026-07-05T10:09:41Z"},{"alias_kind":"arxiv_version","alias_value":"2311.01487v2","created_at":"2026-07-05T10:09:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.01487","created_at":"2026-07-05T10:09:41Z"},{"alias_kind":"pith_short_12","alias_value":"UPNJDIJ4EAQN","created_at":"2026-07-05T10:09:41Z"},{"alias_kind":"pith_short_16","alias_value":"UPNJDIJ4EAQNECOR","created_at":"2026-07-05T10:09:41Z"},{"alias_kind":"pith_short_8","alias_value":"UPNJDIJ4","created_at":"2026-07-05T10:09:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:UPNJDIJ4EAQNECORFSPIKZN6SL","target":"record","payload":{"canonical_record":{"source":{"id":"2311.01487","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-02T15:36:12Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"8f99e5762313ea8ec0ad32d7214e315c099438a24cd05e361d4d04ee0e305ffc","abstract_canon_sha256":"c245b0314e705f80dd2cd321e176d08719e122a922562ad534a21e0842593be3"},"schema_version":"1.0"},"canonical_sha256":"a3da91a13c2020d209d12c9e8565be92e617bcd6a27a93280b5cf0f5ea03266a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:41.101747Z","signature_b64":"oA03wC8Mcj7X4Pry7FAMXMkeu1Ho70l/phZ+KlrEzm0VDcXtbCYEq2ZCCTvWEkBx1gSbtBzff5AH1MpRPPdzBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3da91a13c2020d209d12c9e8565be92e617bcd6a27a93280b5cf0f5ea03266a","last_reissued_at":"2026-07-05T10:09:41.101278Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:41.101278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.01487","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":"2026-07-05T10:09:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j/3CGRettqvhsGixUkSa8ioD0GY8eX0KUJ9Cmm2alIKpzAM7u9cQ16g926FEIRLONQJKk+HMMP4CAU9IPNzmAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:32:48.935910Z"},"content_sha256":"f91bdeeba6a2f9f990cff337619e2730e4f67657c3300989d6b19a9db440a9cb","schema_version":"1.0","event_id":"sha256:f91bdeeba6a2f9f990cff337619e2730e4f67657c3300989d6b19a9db440a9cb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:UPNJDIJ4EAQNECORFSPIKZN6SL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What Makes for Good Visual Instructions? Synthesizing Complex Visual Reasoning Instructions for Visual Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chuyuan Wang, Hangyu Guo, Jinpeng Wang, Ji-Rong Wen, Kun Zhou, Mingchen Cai, Ruihua Song, Wayne Xin Zhao, Yifan Du","submitted_at":"2023-11-02T15:36:12Z","abstract_excerpt":"Visual instruction tuning is crucial for enhancing the zero-shot generalization capability of Multi-modal Large Language Models (MLLMs). In this paper, we aim to investigate a fundamental question: ''what makes for good visual instructions''. Through a comprehensive empirical study, we find that instructions focusing on complex visual reasoning tasks are particularly effective in improving the performance of MLLMs, with results correlating to instruction complexity. Based on this insight, we develop a systematic approach to automatically create high-quality complex visual reasoning instruction"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.01487","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/2311.01487/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":"2026-07-05T10:09:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"scbSa8pKEgbSPRV0qyaWJpb+ln2fiJYB495X5qiciif95NEn8SE0KitvML372y8+MJ12olrm1qPujaLMPgo0Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:32:48.938232Z"},"content_sha256":"40f0e63295d9f11cf7a79a8676bf5a3dd58f0cc25424de7901f9f3df2dbb1554","schema_version":"1.0","event_id":"sha256:40f0e63295d9f11cf7a79a8676bf5a3dd58f0cc25424de7901f9f3df2dbb1554"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UPNJDIJ4EAQNECORFSPIKZN6SL/bundle.json","state_url":"https://pith.science/pith/UPNJDIJ4EAQNECORFSPIKZN6SL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UPNJDIJ4EAQNECORFSPIKZN6SL/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":"2026-08-07T15:32:48Z","links":{"resolver":"https://pith.science/pith/UPNJDIJ4EAQNECORFSPIKZN6SL","bundle":"https://pith.science/pith/UPNJDIJ4EAQNECORFSPIKZN6SL/bundle.json","state":"https://pith.science/pith/UPNJDIJ4EAQNECORFSPIKZN6SL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UPNJDIJ4EAQNECORFSPIKZN6SL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UPNJDIJ4EAQNECORFSPIKZN6SL","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":"c245b0314e705f80dd2cd321e176d08719e122a922562ad534a21e0842593be3","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-02T15:36:12Z","title_canon_sha256":"8f99e5762313ea8ec0ad32d7214e315c099438a24cd05e361d4d04ee0e305ffc"},"schema_version":"1.0","source":{"id":"2311.01487","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.01487","created_at":"2026-07-05T10:09:41Z"},{"alias_kind":"arxiv_version","alias_value":"2311.01487v2","created_at":"2026-07-05T10:09:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.01487","created_at":"2026-07-05T10:09:41Z"},{"alias_kind":"pith_short_12","alias_value":"UPNJDIJ4EAQN","created_at":"2026-07-05T10:09:41Z"},{"alias_kind":"pith_short_16","alias_value":"UPNJDIJ4EAQNECOR","created_at":"2026-07-05T10:09:41Z"},{"alias_kind":"pith_short_8","alias_value":"UPNJDIJ4","created_at":"2026-07-05T10:09:41Z"}],"graph_snapshots":[{"event_id":"sha256:40f0e63295d9f11cf7a79a8676bf5a3dd58f0cc25424de7901f9f3df2dbb1554","target":"graph","created_at":"2026-07-05T10:09:41Z","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/2311.01487/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual instruction tuning is crucial for enhancing the zero-shot generalization capability of Multi-modal Large Language Models (MLLMs). In this paper, we aim to investigate a fundamental question: ''what makes for good visual instructions''. Through a comprehensive empirical study, we find that instructions focusing on complex visual reasoning tasks are particularly effective in improving the performance of MLLMs, with results correlating to instruction complexity. Based on this insight, we develop a systematic approach to automatically create high-quality complex visual reasoning instruction","authors_text":"Chuyuan Wang, Hangyu Guo, Jinpeng Wang, Ji-Rong Wen, Kun Zhou, Mingchen Cai, Ruihua Song, Wayne Xin Zhao, Yifan Du","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-02T15:36:12Z","title":"What Makes for Good Visual Instructions? Synthesizing Complex Visual Reasoning Instructions for Visual Instruction Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.01487","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:f91bdeeba6a2f9f990cff337619e2730e4f67657c3300989d6b19a9db440a9cb","target":"record","created_at":"2026-07-05T10:09:41Z","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":"c245b0314e705f80dd2cd321e176d08719e122a922562ad534a21e0842593be3","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-02T15:36:12Z","title_canon_sha256":"8f99e5762313ea8ec0ad32d7214e315c099438a24cd05e361d4d04ee0e305ffc"},"schema_version":"1.0","source":{"id":"2311.01487","kind":"arxiv","version":2}},"canonical_sha256":"a3da91a13c2020d209d12c9e8565be92e617bcd6a27a93280b5cf0f5ea03266a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a3da91a13c2020d209d12c9e8565be92e617bcd6a27a93280b5cf0f5ea03266a","first_computed_at":"2026-07-05T10:09:41.101278Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:09:41.101278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oA03wC8Mcj7X4Pry7FAMXMkeu1Ho70l/phZ+KlrEzm0VDcXtbCYEq2ZCCTvWEkBx1gSbtBzff5AH1MpRPPdzBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:09:41.101747Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.01487","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f91bdeeba6a2f9f990cff337619e2730e4f67657c3300989d6b19a9db440a9cb","sha256:40f0e63295d9f11cf7a79a8676bf5a3dd58f0cc25424de7901f9f3df2dbb1554"],"state_sha256":"f6075bedc30be3894036f4d6f678cedff6d7ce28d9f05a7ff369dfaeb7a35e06"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8vUBgFP+E9cOwjheBQVHoiEhL9+iyEoAQJmQvdxdkLb8dPVOW7QIJR1zkj/QmY288i+gJrdY+50uINWfsRU6Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T15:32:48.947482Z","bundle_sha256":"7eb3e72c5f50a268f93a7c024941099f0f61e45bfdff58ed583543ebb7974cab"}}