{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:BXI4CWW37Q2LBIXEJVYQKSWDUW","short_pith_number":"pith:BXI4CWW3","canonical_record":{"source":{"id":"2308.10253","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-20T12:43:52Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"4e58076b6e9a3e5f3d8fdf4b85953781d5cffa8aefb25606e84da90da6c8d579","abstract_canon_sha256":"a46000093ed8611036d79a2d2bd3bc0ff20a158c07a10ccc042e1e10a46b81d4"},"schema_version":"1.0"},"canonical_sha256":"0dd1c15adbfc34b0a2e44d71054ac3a583fdcf264f687331c9b827da1073bd3a","source":{"kind":"arxiv","id":"2308.10253","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.10253","created_at":"2026-07-05T07:28:29Z"},{"alias_kind":"arxiv_version","alias_value":"2308.10253v2","created_at":"2026-07-05T07:28:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.10253","created_at":"2026-07-05T07:28:29Z"},{"alias_kind":"pith_short_12","alias_value":"BXI4CWW37Q2L","created_at":"2026-07-05T07:28:29Z"},{"alias_kind":"pith_short_16","alias_value":"BXI4CWW37Q2LBIXE","created_at":"2026-07-05T07:28:29Z"},{"alias_kind":"pith_short_8","alias_value":"BXI4CWW3","created_at":"2026-07-05T07:28:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:BXI4CWW37Q2LBIXEJVYQKSWDUW","target":"record","payload":{"canonical_record":{"source":{"id":"2308.10253","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-20T12:43:52Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"4e58076b6e9a3e5f3d8fdf4b85953781d5cffa8aefb25606e84da90da6c8d579","abstract_canon_sha256":"a46000093ed8611036d79a2d2bd3bc0ff20a158c07a10ccc042e1e10a46b81d4"},"schema_version":"1.0"},"canonical_sha256":"0dd1c15adbfc34b0a2e44d71054ac3a583fdcf264f687331c9b827da1073bd3a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:28:29.419089Z","signature_b64":"B0naXva9tePHXC4lzLQLvMkuoLJcJJ/YhaTTkatgIO6AnLG8+wDSSjaxTtXsmLog0EXRW+3i/7+dEVW5lGHfDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0dd1c15adbfc34b0a2e44d71054ac3a583fdcf264f687331c9b827da1073bd3a","last_reissued_at":"2026-07-05T07:28:29.418559Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:28:29.418559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.10253","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":"2026-07-05T07:28:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FRNTtufQQ0ZqkJaSXBOYM/34ZAdgaA+1ZDh58/QnhEyJpUG3TeBhANKalvBitahqNJan4b5Ibst/uw1w4MVtDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T12:11:48.475153Z"},"content_sha256":"bd8a54b35ae715331a00da32a98004392c7168e4c7a03f211e6f9508c5ad4c5a","schema_version":"1.0","event_id":"sha256:bd8a54b35ae715331a00da32a98004392c7168e4c7a03f211e6f9508c5ad4c5a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:BXI4CWW37Q2LBIXEJVYQKSWDUW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"StableLLaVA: Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bin Fu, Chi Zhang, Chunhua Shen, Gang Yu, Guosheng Lin, Ling Chen, Yanda Li, Yunchao Wei, Zhibin Wang","submitted_at":"2023-08-20T12:43:52Z","abstract_excerpt":"The remarkable multimodal capabilities demonstrated by OpenAI's GPT-4 have sparked significant interest in the development of multimodal Large Language Models (LLMs). A primary research objective of such models is to align visual and textual modalities effectively while comprehending human instructions. Current methodologies often rely on annotations derived from benchmark datasets to construct image-dialogue datasets for training purposes, akin to instruction tuning in LLMs. However, these datasets often exhibit domain bias, potentially constraining the generative capabilities of the models. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.10253","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/2308.10253/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":"2026-07-05T07:28:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1p5Ti4jmLhWWQQ+W3EYJACMrAVRUChF9SjoTOxGyaioIo7FRaigiSCb5BIQ9UUs2qfUTbbRrfZwTZZFgC2cDAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T12:11:48.475737Z"},"content_sha256":"b24427d615989caccf29185b75847dc8cdf9283bfd0cfb78f1fc4c14e2f63b6f","schema_version":"1.0","event_id":"sha256:b24427d615989caccf29185b75847dc8cdf9283bfd0cfb78f1fc4c14e2f63b6f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BXI4CWW37Q2LBIXEJVYQKSWDUW/bundle.json","state_url":"https://pith.science/pith/BXI4CWW37Q2LBIXEJVYQKSWDUW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BXI4CWW37Q2LBIXEJVYQKSWDUW/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":"2026-08-06T12:11:48Z","links":{"resolver":"https://pith.science/pith/BXI4CWW37Q2LBIXEJVYQKSWDUW","bundle":"https://pith.science/pith/BXI4CWW37Q2LBIXEJVYQKSWDUW/bundle.json","state":"https://pith.science/pith/BXI4CWW37Q2LBIXEJVYQKSWDUW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BXI4CWW37Q2LBIXEJVYQKSWDUW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BXI4CWW37Q2LBIXEJVYQKSWDUW","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":"a46000093ed8611036d79a2d2bd3bc0ff20a158c07a10ccc042e1e10a46b81d4","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-20T12:43:52Z","title_canon_sha256":"4e58076b6e9a3e5f3d8fdf4b85953781d5cffa8aefb25606e84da90da6c8d579"},"schema_version":"1.0","source":{"id":"2308.10253","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.10253","created_at":"2026-07-05T07:28:29Z"},{"alias_kind":"arxiv_version","alias_value":"2308.10253v2","created_at":"2026-07-05T07:28:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.10253","created_at":"2026-07-05T07:28:29Z"},{"alias_kind":"pith_short_12","alias_value":"BXI4CWW37Q2L","created_at":"2026-07-05T07:28:29Z"},{"alias_kind":"pith_short_16","alias_value":"BXI4CWW37Q2LBIXE","created_at":"2026-07-05T07:28:29Z"},{"alias_kind":"pith_short_8","alias_value":"BXI4CWW3","created_at":"2026-07-05T07:28:29Z"}],"graph_snapshots":[{"event_id":"sha256:b24427d615989caccf29185b75847dc8cdf9283bfd0cfb78f1fc4c14e2f63b6f","target":"graph","created_at":"2026-07-05T07:28:29Z","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/2308.10253/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The remarkable multimodal capabilities demonstrated by OpenAI's GPT-4 have sparked significant interest in the development of multimodal Large Language Models (LLMs). A primary research objective of such models is to align visual and textual modalities effectively while comprehending human instructions. Current methodologies often rely on annotations derived from benchmark datasets to construct image-dialogue datasets for training purposes, akin to instruction tuning in LLMs. However, these datasets often exhibit domain bias, potentially constraining the generative capabilities of the models. ","authors_text":"Bin Fu, Chi Zhang, Chunhua Shen, Gang Yu, Guosheng Lin, Ling Chen, Yanda Li, Yunchao Wei, Zhibin Wang","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-20T12:43:52Z","title":"StableLLaVA: Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.10253","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:bd8a54b35ae715331a00da32a98004392c7168e4c7a03f211e6f9508c5ad4c5a","target":"record","created_at":"2026-07-05T07:28:29Z","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":"a46000093ed8611036d79a2d2bd3bc0ff20a158c07a10ccc042e1e10a46b81d4","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-20T12:43:52Z","title_canon_sha256":"4e58076b6e9a3e5f3d8fdf4b85953781d5cffa8aefb25606e84da90da6c8d579"},"schema_version":"1.0","source":{"id":"2308.10253","kind":"arxiv","version":2}},"canonical_sha256":"0dd1c15adbfc34b0a2e44d71054ac3a583fdcf264f687331c9b827da1073bd3a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0dd1c15adbfc34b0a2e44d71054ac3a583fdcf264f687331c9b827da1073bd3a","first_computed_at":"2026-07-05T07:28:29.418559Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:28:29.418559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B0naXva9tePHXC4lzLQLvMkuoLJcJJ/YhaTTkatgIO6AnLG8+wDSSjaxTtXsmLog0EXRW+3i/7+dEVW5lGHfDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:28:29.419089Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.10253","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd8a54b35ae715331a00da32a98004392c7168e4c7a03f211e6f9508c5ad4c5a","sha256:b24427d615989caccf29185b75847dc8cdf9283bfd0cfb78f1fc4c14e2f63b6f"],"state_sha256":"dc1df36f17bb1fbd75e641162b1959788ede516be15d100b513349842e9be655"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q5dVemNA6IdDs6yKdEbSfbCN6inW75I8ml1GlxaNlRokG9oGAN+Q2kDxZ39BjdUx28ykmMXqGBVw01o2+L0GAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T12:11:48.481117Z","bundle_sha256":"a9c944f4905a6a7615fa47cf3ab27e6b575be70fd6044b617e4f0d4f74d8450d"}}