{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XQYCD3ZNLJEUCWE2ZCP3BTEJWM","short_pith_number":"pith:XQYCD3ZN","canonical_record":{"source":{"id":"2402.07398","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-02-12T04:13:16Z","cross_cats_sorted":[],"title_canon_sha256":"fb887ebb38468038280103c67a45035ccaab01fcd7c38a8342302f335e8683af","abstract_canon_sha256":"d45783a6c2174f016f74b5e358d50335864c1fbde9f8126fc0af936563ba8c6e"},"schema_version":"1.0"},"canonical_sha256":"bc3021ef2d5a4941589ac89fb0cc89b33f7b15633b56ce47cf8f72c369c43383","source":{"kind":"arxiv","id":"2402.07398","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.07398","created_at":"2026-07-05T08:34:47Z"},{"alias_kind":"arxiv_version","alias_value":"2402.07398v3","created_at":"2026-07-05T08:34:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07398","created_at":"2026-07-05T08:34:47Z"},{"alias_kind":"pith_short_12","alias_value":"XQYCD3ZNLJEU","created_at":"2026-07-05T08:34:47Z"},{"alias_kind":"pith_short_16","alias_value":"XQYCD3ZNLJEUCWE2","created_at":"2026-07-05T08:34:47Z"},{"alias_kind":"pith_short_8","alias_value":"XQYCD3ZN","created_at":"2026-07-05T08:34:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XQYCD3ZNLJEUCWE2ZCP3BTEJWM","target":"record","payload":{"canonical_record":{"source":{"id":"2402.07398","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-02-12T04:13:16Z","cross_cats_sorted":[],"title_canon_sha256":"fb887ebb38468038280103c67a45035ccaab01fcd7c38a8342302f335e8683af","abstract_canon_sha256":"d45783a6c2174f016f74b5e358d50335864c1fbde9f8126fc0af936563ba8c6e"},"schema_version":"1.0"},"canonical_sha256":"bc3021ef2d5a4941589ac89fb0cc89b33f7b15633b56ce47cf8f72c369c43383","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:47.324946Z","signature_b64":"u8EEd86RlQ8iEpWAnv6M48/gXIM9vWhbVi25CAvqDiW0ArECEc7pBUhoOxVOUSXcYBNcyxxtwbVUsgBCymj1BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc3021ef2d5a4941589ac89fb0cc89b33f7b15633b56ce47cf8f72c369c43383","last_reissued_at":"2026-07-05T08:34:47.324483Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:47.324483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.07398","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:34:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PTWKBYRFeP54uIn0TLF8tFxAcjDoCt7dkA51CV33bYcuo1tTFrneKBEsNiOk8Nl2YwcYgowaxkvGl9W8baaoCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T03:36:55.947983Z"},"content_sha256":"b5820421cc692e770e142ec48bed7b6578d0be63d2a68e3f396d4dd7bb22cd5c","schema_version":"1.0","event_id":"sha256:b5820421cc692e770e142ec48bed7b6578d0be63d2a68e3f396d4dd7bb22cd5c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XQYCD3ZNLJEUCWE2ZCP3BTEJWM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VisLingInstruct: Elevating Zero-Shot Learning in Multi-Modal Language Models with Autonomous Instruction Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dawei Yin, Dongsheng Zhu, Guoliang Xing, Jinghui Lu, Junfeng Wang, Weidong Han, Xunzhu Tang, Yukun Zhao","submitted_at":"2024-02-12T04:13:16Z","abstract_excerpt":"This paper presents VisLingInstruct, a novel approach to advancing Multi-Modal Language Models (MMLMs) in zero-shot learning. Current MMLMs show impressive zero-shot abilities in multi-modal tasks, but their performance depends heavily on the quality of instructions. VisLingInstruct tackles this by autonomously evaluating and optimizing instructional texts through In-Context Learning, improving the synergy between visual perception and linguistic expression in MMLMs. Alongside this instructional advancement, we have also optimized the visual feature extraction modules in MMLMs, further augment"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07398","kind":"arxiv","version":3},"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/2402.07398/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":"2026-07-05T08:34:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iwuikbeMWd+TSZAvCKSg1tJlmcMhXabNhnVAYJfif5NKN38cEuHgEkT8bjfSFYXinT5uEtkFxq8IXALJ4c57DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T03:36:55.948533Z"},"content_sha256":"f733379aa8c6680d172bc58d2652f4f092d179301743c89c00009ccef9d91794","schema_version":"1.0","event_id":"sha256:f733379aa8c6680d172bc58d2652f4f092d179301743c89c00009ccef9d91794"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XQYCD3ZNLJEUCWE2ZCP3BTEJWM/bundle.json","state_url":"https://pith.science/pith/XQYCD3ZNLJEUCWE2ZCP3BTEJWM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XQYCD3ZNLJEUCWE2ZCP3BTEJWM/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":"2026-08-07T03:36:55Z","links":{"resolver":"https://pith.science/pith/XQYCD3ZNLJEUCWE2ZCP3BTEJWM","bundle":"https://pith.science/pith/XQYCD3ZNLJEUCWE2ZCP3BTEJWM/bundle.json","state":"https://pith.science/pith/XQYCD3ZNLJEUCWE2ZCP3BTEJWM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XQYCD3ZNLJEUCWE2ZCP3BTEJWM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XQYCD3ZNLJEUCWE2ZCP3BTEJWM","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":"d45783a6c2174f016f74b5e358d50335864c1fbde9f8126fc0af936563ba8c6e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-02-12T04:13:16Z","title_canon_sha256":"fb887ebb38468038280103c67a45035ccaab01fcd7c38a8342302f335e8683af"},"schema_version":"1.0","source":{"id":"2402.07398","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.07398","created_at":"2026-07-05T08:34:47Z"},{"alias_kind":"arxiv_version","alias_value":"2402.07398v3","created_at":"2026-07-05T08:34:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07398","created_at":"2026-07-05T08:34:47Z"},{"alias_kind":"pith_short_12","alias_value":"XQYCD3ZNLJEU","created_at":"2026-07-05T08:34:47Z"},{"alias_kind":"pith_short_16","alias_value":"XQYCD3ZNLJEUCWE2","created_at":"2026-07-05T08:34:47Z"},{"alias_kind":"pith_short_8","alias_value":"XQYCD3ZN","created_at":"2026-07-05T08:34:47Z"}],"graph_snapshots":[{"event_id":"sha256:f733379aa8c6680d172bc58d2652f4f092d179301743c89c00009ccef9d91794","target":"graph","created_at":"2026-07-05T08:34:47Z","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/2402.07398/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents VisLingInstruct, a novel approach to advancing Multi-Modal Language Models (MMLMs) in zero-shot learning. Current MMLMs show impressive zero-shot abilities in multi-modal tasks, but their performance depends heavily on the quality of instructions. VisLingInstruct tackles this by autonomously evaluating and optimizing instructional texts through In-Context Learning, improving the synergy between visual perception and linguistic expression in MMLMs. Alongside this instructional advancement, we have also optimized the visual feature extraction modules in MMLMs, further augment","authors_text":"Dawei Yin, Dongsheng Zhu, Guoliang Xing, Jinghui Lu, Junfeng Wang, Weidong Han, Xunzhu Tang, Yukun Zhao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-02-12T04:13:16Z","title":"VisLingInstruct: Elevating Zero-Shot Learning in Multi-Modal Language Models with Autonomous Instruction Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07398","kind":"arxiv","version":3},"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:b5820421cc692e770e142ec48bed7b6578d0be63d2a68e3f396d4dd7bb22cd5c","target":"record","created_at":"2026-07-05T08:34:47Z","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":"d45783a6c2174f016f74b5e358d50335864c1fbde9f8126fc0af936563ba8c6e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-02-12T04:13:16Z","title_canon_sha256":"fb887ebb38468038280103c67a45035ccaab01fcd7c38a8342302f335e8683af"},"schema_version":"1.0","source":{"id":"2402.07398","kind":"arxiv","version":3}},"canonical_sha256":"bc3021ef2d5a4941589ac89fb0cc89b33f7b15633b56ce47cf8f72c369c43383","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bc3021ef2d5a4941589ac89fb0cc89b33f7b15633b56ce47cf8f72c369c43383","first_computed_at":"2026-07-05T08:34:47.324483Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:34:47.324483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u8EEd86RlQ8iEpWAnv6M48/gXIM9vWhbVi25CAvqDiW0ArECEc7pBUhoOxVOUSXcYBNcyxxtwbVUsgBCymj1BA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:34:47.324946Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.07398","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5820421cc692e770e142ec48bed7b6578d0be63d2a68e3f396d4dd7bb22cd5c","sha256:f733379aa8c6680d172bc58d2652f4f092d179301743c89c00009ccef9d91794"],"state_sha256":"abd793d04c82df8875a5816e264519ff91461716c4c9f87c02329eccd48bce45"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vk8s5i9Mo0/4vOMig9oFpG6j0lzmTp/H6lhOvYbxB5jSRJg41SIM0idcKl7nbZxfhZZNK04pcKL8xMu4dwtdAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T03:36:55.954266Z","bundle_sha256":"fd00fd9cbdedafcf27d274ccb1f119eb18739b8c9a35cc4aa4f03b7e13ef4f40"}}