{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:57DIOOZHQ5H75U5MV2QNBGHDZT","short_pith_number":"pith:57DIOOZH","canonical_record":{"source":{"id":"2311.08172","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.MM","submitted_at":"2023-11-14T14:02:32Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"13b422ba8496b8cff46b393bf3aaa677e96218ece8e2d7a7fd5971fdde64d083","abstract_canon_sha256":"b87ff86dbe637a688693e10564c6d8395a92f1daccfc9c20a7c26f910441d977"},"schema_version":"1.0"},"canonical_sha256":"efc6873b27874ffed3acaea0d098e3cccea53afc330de5b43f2c037665f0eede","source":{"kind":"arxiv","id":"2311.08172","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.08172","created_at":"2026-07-05T07:16:49Z"},{"alias_kind":"arxiv_version","alias_value":"2311.08172v2","created_at":"2026-07-05T07:16:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.08172","created_at":"2026-07-05T07:16:49Z"},{"alias_kind":"pith_short_12","alias_value":"57DIOOZHQ5H7","created_at":"2026-07-05T07:16:49Z"},{"alias_kind":"pith_short_16","alias_value":"57DIOOZHQ5H75U5M","created_at":"2026-07-05T07:16:49Z"},{"alias_kind":"pith_short_8","alias_value":"57DIOOZH","created_at":"2026-07-05T07:16:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:57DIOOZHQ5H75U5MV2QNBGHDZT","target":"record","payload":{"canonical_record":{"source":{"id":"2311.08172","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.MM","submitted_at":"2023-11-14T14:02:32Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"13b422ba8496b8cff46b393bf3aaa677e96218ece8e2d7a7fd5971fdde64d083","abstract_canon_sha256":"b87ff86dbe637a688693e10564c6d8395a92f1daccfc9c20a7c26f910441d977"},"schema_version":"1.0"},"canonical_sha256":"efc6873b27874ffed3acaea0d098e3cccea53afc330de5b43f2c037665f0eede","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:16:49.542807Z","signature_b64":"awn2OaldnvvS/xmgld9pTXdrjeGnBd3RaJScG+KRNbf5RONp0dWfcJVCiJLTqg6I+jEQsTKhzZ+RXZvEwNBEBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efc6873b27874ffed3acaea0d098e3cccea53afc330de5b43f2c037665f0eede","last_reissued_at":"2026-07-05T07:16:49.542351Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:16:49.542351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.08172","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":"2026-07-05T07:16:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cyoRIDMYZzU1WgR5XRvlmXEvwlePMQPYUVp8mqKFS/5jekDjwSA3+o1/xPlxqVeHwFJ9HiIN9JiCko1/gnVwDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:39:00.963467Z"},"content_sha256":"0c02e40c4863dc2b90cd5e1f971a186b9a627107a39887e51baf7c7640653dd1","schema_version":"1.0","event_id":"sha256:0c02e40c4863dc2b90cd5e1f971a186b9a627107a39887e51baf7c7640653dd1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:57DIOOZHQ5H75U5MV2QNBGHDZT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Vision-Language Instruction Tuning: A Review and Analysis","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.MM","authors_text":"Chen Li, Dian Li, Ying Shan, Yixiao Ge","submitted_at":"2023-11-14T14:02:32Z","abstract_excerpt":"Instruction tuning is a crucial supervised training phase in Large Language Models (LLMs), aiming to enhance the LLM's ability to generalize instruction execution and adapt to user preferences. With the increasing integration of multi-modal data into LLMs, there is growing interest in Vision-Language Instruction Tuning (VLIT), which presents more complex characteristics compared to pure text instruction tuning. In this paper, we systematically review the latest VLIT settings and corresponding datasets in multi-modal LLMs and provide insights into the intrinsic motivations behind their design. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.08172","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/2311.08172/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":"2026-07-05T07:16:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rm+wZQEtRr5eiWzLFUkz4gqPaiY+UZwUZGMSEceO6e9OAlsep/EkHXZWPlmOsWERj9VtRAIbkEfEt6VLdQ/4Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:39:00.964385Z"},"content_sha256":"10a10e01328edd863ad5dcdd1da8aa48ea8f115e76a539f47d8e59a950745325","schema_version":"1.0","event_id":"sha256:10a10e01328edd863ad5dcdd1da8aa48ea8f115e76a539f47d8e59a950745325"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/57DIOOZHQ5H75U5MV2QNBGHDZT/bundle.json","state_url":"https://pith.science/pith/57DIOOZHQ5H75U5MV2QNBGHDZT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/57DIOOZHQ5H75U5MV2QNBGHDZT/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":"2026-08-03T21:39:00Z","links":{"resolver":"https://pith.science/pith/57DIOOZHQ5H75U5MV2QNBGHDZT","bundle":"https://pith.science/pith/57DIOOZHQ5H75U5MV2QNBGHDZT/bundle.json","state":"https://pith.science/pith/57DIOOZHQ5H75U5MV2QNBGHDZT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/57DIOOZHQ5H75U5MV2QNBGHDZT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:57DIOOZHQ5H75U5MV2QNBGHDZT","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":"b87ff86dbe637a688693e10564c6d8395a92f1daccfc9c20a7c26f910441d977","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.MM","submitted_at":"2023-11-14T14:02:32Z","title_canon_sha256":"13b422ba8496b8cff46b393bf3aaa677e96218ece8e2d7a7fd5971fdde64d083"},"schema_version":"1.0","source":{"id":"2311.08172","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.08172","created_at":"2026-07-05T07:16:49Z"},{"alias_kind":"arxiv_version","alias_value":"2311.08172v2","created_at":"2026-07-05T07:16:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.08172","created_at":"2026-07-05T07:16:49Z"},{"alias_kind":"pith_short_12","alias_value":"57DIOOZHQ5H7","created_at":"2026-07-05T07:16:49Z"},{"alias_kind":"pith_short_16","alias_value":"57DIOOZHQ5H75U5M","created_at":"2026-07-05T07:16:49Z"},{"alias_kind":"pith_short_8","alias_value":"57DIOOZH","created_at":"2026-07-05T07:16:49Z"}],"graph_snapshots":[{"event_id":"sha256:10a10e01328edd863ad5dcdd1da8aa48ea8f115e76a539f47d8e59a950745325","target":"graph","created_at":"2026-07-05T07:16:49Z","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/2311.08172/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction tuning is a crucial supervised training phase in Large Language Models (LLMs), aiming to enhance the LLM's ability to generalize instruction execution and adapt to user preferences. With the increasing integration of multi-modal data into LLMs, there is growing interest in Vision-Language Instruction Tuning (VLIT), which presents more complex characteristics compared to pure text instruction tuning. In this paper, we systematically review the latest VLIT settings and corresponding datasets in multi-modal LLMs and provide insights into the intrinsic motivations behind their design. ","authors_text":"Chen Li, Dian Li, Ying Shan, Yixiao Ge","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.MM","submitted_at":"2023-11-14T14:02:32Z","title":"Vision-Language Instruction Tuning: A Review and Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.08172","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":"sha256:0c02e40c4863dc2b90cd5e1f971a186b9a627107a39887e51baf7c7640653dd1","target":"record","created_at":"2026-07-05T07:16:49Z","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":"b87ff86dbe637a688693e10564c6d8395a92f1daccfc9c20a7c26f910441d977","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.MM","submitted_at":"2023-11-14T14:02:32Z","title_canon_sha256":"13b422ba8496b8cff46b393bf3aaa677e96218ece8e2d7a7fd5971fdde64d083"},"schema_version":"1.0","source":{"id":"2311.08172","kind":"arxiv","version":2}},"canonical_sha256":"efc6873b27874ffed3acaea0d098e3cccea53afc330de5b43f2c037665f0eede","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"efc6873b27874ffed3acaea0d098e3cccea53afc330de5b43f2c037665f0eede","first_computed_at":"2026-07-05T07:16:49.542351Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:16:49.542351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"awn2OaldnvvS/xmgld9pTXdrjeGnBd3RaJScG+KRNbf5RONp0dWfcJVCiJLTqg6I+jEQsTKhzZ+RXZvEwNBEBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:16:49.542807Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.08172","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0c02e40c4863dc2b90cd5e1f971a186b9a627107a39887e51baf7c7640653dd1","sha256:10a10e01328edd863ad5dcdd1da8aa48ea8f115e76a539f47d8e59a950745325"],"state_sha256":"af3ee39b11c4d9eede3e07706724bb04a951a724b2bc982a1b37f9ee868b0dea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hXAaF3muYE6hLCv8XUDmWHdpOHPvXmx8pgQAvmhZ9wxpnEMJSVfjFJnaFTwuG+Pl3xod4yZZpkDcUKFNiHhODg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T21:39:00.969935Z","bundle_sha256":"774f485880efb2cc4a7cfcb74bc2e2df66674b05b690478b15429b63d353af1a"}}