{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:TVTN2SYNWL45527Z53A3UKXBPB","short_pith_number":"pith:TVTN2SYN","canonical_record":{"source":{"id":"2312.16602","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-27T14:54:37Z","cross_cats_sorted":[],"title_canon_sha256":"3461984ebbff57adb60e8e2d75373324b3cf121943032c2edcd2936aaa257128","abstract_canon_sha256":"de8f3369ae86b212dc6e26636bc5ee5c0780266cc4ccd7d3632b9dd8b167c2af"},"schema_version":"1.0"},"canonical_sha256":"9d66dd4b0db2f9deebf9eec1ba2ae1784fce3d9f104793444ffc15dfc0b01362","source":{"kind":"arxiv","id":"2312.16602","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.16602","created_at":"2026-07-05T07:28:19Z"},{"alias_kind":"arxiv_version","alias_value":"2312.16602v1","created_at":"2026-07-05T07:28:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.16602","created_at":"2026-07-05T07:28:19Z"},{"alias_kind":"pith_short_12","alias_value":"TVTN2SYNWL45","created_at":"2026-07-05T07:28:19Z"},{"alias_kind":"pith_short_16","alias_value":"TVTN2SYNWL45527Z","created_at":"2026-07-05T07:28:19Z"},{"alias_kind":"pith_short_8","alias_value":"TVTN2SYN","created_at":"2026-07-05T07:28:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:TVTN2SYNWL45527Z53A3UKXBPB","target":"record","payload":{"canonical_record":{"source":{"id":"2312.16602","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-27T14:54:37Z","cross_cats_sorted":[],"title_canon_sha256":"3461984ebbff57adb60e8e2d75373324b3cf121943032c2edcd2936aaa257128","abstract_canon_sha256":"de8f3369ae86b212dc6e26636bc5ee5c0780266cc4ccd7d3632b9dd8b167c2af"},"schema_version":"1.0"},"canonical_sha256":"9d66dd4b0db2f9deebf9eec1ba2ae1784fce3d9f104793444ffc15dfc0b01362","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:28:19.719540Z","signature_b64":"bVkMtmoUq3Cx+nNKyZFIOqcacnYGabpDofgU7Z7RmAZ5u+nIQJ/bBVAXLCbQINXVq3PNR/eSEi2CeHJg+E0yAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d66dd4b0db2f9deebf9eec1ba2ae1784fce3d9f104793444ffc15dfc0b01362","last_reissued_at":"2026-07-05T07:28:19.718970Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:28:19.718970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.16602","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:28:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HY8FI5b8XyRGgMYfpOXo+JMmmNL9ddQVYb2S51JghdntbS4OTAwRHoPbQ2PY5plIUXXkJKgCIjvSztSeRLjrBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T06:22:09.970677Z"},"content_sha256":"5a1d94676154ab02716942252f4ecca0f1800e01bdf5e2087cc10763284f33ff","schema_version":"1.0","event_id":"sha256:5a1d94676154ab02716942252f4ecca0f1800e01bdf5e2087cc10763284f33ff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:TVTN2SYNWL45527Z53A3UKXBPB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Visual Instruction Tuning towards General-Purpose Multimodal Model: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Han Qiu, Jiaxing Huang, Jingyi Zhang, Kai Jiang, Shijian Lu","submitted_at":"2023-12-27T14:54:37Z","abstract_excerpt":"Traditional computer vision generally solves each single task independently by a dedicated model with the task instruction implicitly designed in the model architecture, arising two limitations: (1) it leads to task-specific models, which require multiple models for different tasks and restrict the potential synergies from diverse tasks; (2) it leads to a pre-defined and fixed model interface that has limited interactivity and adaptability in following user' task instructions. To address them, Visual Instruction Tuning (VIT) has been intensively studied recently, which finetunes a large vision"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.16602","kind":"arxiv","version":1},"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/2312.16602/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":"2026-07-05T07:28:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zFzwUOS4/RXQbOUKxZXnXx0dpiEnKIgxPvVOMD8ikvrr3mp6N871Wlaa0EtiA/FwRtXT4yxZj/0p7ZTqNkTWBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T06:22:09.971266Z"},"content_sha256":"a31a3355c441fc5e0c3f70bdb9757a0b6a8699f2aba17c4ac5f81579a15f4919","schema_version":"1.0","event_id":"sha256:a31a3355c441fc5e0c3f70bdb9757a0b6a8699f2aba17c4ac5f81579a15f4919"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TVTN2SYNWL45527Z53A3UKXBPB/bundle.json","state_url":"https://pith.science/pith/TVTN2SYNWL45527Z53A3UKXBPB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TVTN2SYNWL45527Z53A3UKXBPB/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":"2026-08-12T06:22:09Z","links":{"resolver":"https://pith.science/pith/TVTN2SYNWL45527Z53A3UKXBPB","bundle":"https://pith.science/pith/TVTN2SYNWL45527Z53A3UKXBPB/bundle.json","state":"https://pith.science/pith/TVTN2SYNWL45527Z53A3UKXBPB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TVTN2SYNWL45527Z53A3UKXBPB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TVTN2SYNWL45527Z53A3UKXBPB","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":"de8f3369ae86b212dc6e26636bc5ee5c0780266cc4ccd7d3632b9dd8b167c2af","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-27T14:54:37Z","title_canon_sha256":"3461984ebbff57adb60e8e2d75373324b3cf121943032c2edcd2936aaa257128"},"schema_version":"1.0","source":{"id":"2312.16602","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.16602","created_at":"2026-07-05T07:28:19Z"},{"alias_kind":"arxiv_version","alias_value":"2312.16602v1","created_at":"2026-07-05T07:28:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.16602","created_at":"2026-07-05T07:28:19Z"},{"alias_kind":"pith_short_12","alias_value":"TVTN2SYNWL45","created_at":"2026-07-05T07:28:19Z"},{"alias_kind":"pith_short_16","alias_value":"TVTN2SYNWL45527Z","created_at":"2026-07-05T07:28:19Z"},{"alias_kind":"pith_short_8","alias_value":"TVTN2SYN","created_at":"2026-07-05T07:28:19Z"}],"graph_snapshots":[{"event_id":"sha256:a31a3355c441fc5e0c3f70bdb9757a0b6a8699f2aba17c4ac5f81579a15f4919","target":"graph","created_at":"2026-07-05T07:28:19Z","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/2312.16602/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Traditional computer vision generally solves each single task independently by a dedicated model with the task instruction implicitly designed in the model architecture, arising two limitations: (1) it leads to task-specific models, which require multiple models for different tasks and restrict the potential synergies from diverse tasks; (2) it leads to a pre-defined and fixed model interface that has limited interactivity and adaptability in following user' task instructions. To address them, Visual Instruction Tuning (VIT) has been intensively studied recently, which finetunes a large vision","authors_text":"Han Qiu, Jiaxing Huang, Jingyi Zhang, Kai Jiang, Shijian Lu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-27T14:54:37Z","title":"Visual Instruction Tuning towards General-Purpose Multimodal Model: A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.16602","kind":"arxiv","version":1},"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":"sha256:5a1d94676154ab02716942252f4ecca0f1800e01bdf5e2087cc10763284f33ff","target":"record","created_at":"2026-07-05T07:28:19Z","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":"de8f3369ae86b212dc6e26636bc5ee5c0780266cc4ccd7d3632b9dd8b167c2af","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-27T14:54:37Z","title_canon_sha256":"3461984ebbff57adb60e8e2d75373324b3cf121943032c2edcd2936aaa257128"},"schema_version":"1.0","source":{"id":"2312.16602","kind":"arxiv","version":1}},"canonical_sha256":"9d66dd4b0db2f9deebf9eec1ba2ae1784fce3d9f104793444ffc15dfc0b01362","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d66dd4b0db2f9deebf9eec1ba2ae1784fce3d9f104793444ffc15dfc0b01362","first_computed_at":"2026-07-05T07:28:19.718970Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:28:19.718970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bVkMtmoUq3Cx+nNKyZFIOqcacnYGabpDofgU7Z7RmAZ5u+nIQJ/bBVAXLCbQINXVq3PNR/eSEi2CeHJg+E0yAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:28:19.719540Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.16602","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a1d94676154ab02716942252f4ecca0f1800e01bdf5e2087cc10763284f33ff","sha256:a31a3355c441fc5e0c3f70bdb9757a0b6a8699f2aba17c4ac5f81579a15f4919"],"state_sha256":"d0e19b9b36f8f3ed6a622f251b67d7afa38fe1518dc213883c645209e7abb2ca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pjCytWzcrDkfGyIRSKjXqEy++czQJ9eysylYJm7U523TFn38AW3YygVqgHwnVg41b2VhYez+X9+9pAButI8vDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T06:22:09.975012Z","bundle_sha256":"9621f57c2ad23c0b304c082e7bb11ea42ccfa623aa3e9e05f25d573c3109815d"}}