{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:SNBYB3WC5EP232EWCRF2UJX3BO","short_pith_number":"pith:SNBYB3WC","canonical_record":{"source":{"id":"2305.00201","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-29T08:59:12Z","cross_cats_sorted":[],"title_canon_sha256":"beefe2e817ceeb687aa4a2e580287c7017b0262157cc0eeb1d4d32f6cfc5e87d","abstract_canon_sha256":"4eccb75e8928dbf8ae0b3b1a52a6021eb4bae8b8891d773e1789f9509726a469"},"schema_version":"1.0"},"canonical_sha256":"934380eec2e91fade896144baa26fb0b8e3c0a7db9c24421cfbb0eb0bf329a6f","source":{"kind":"arxiv","id":"2305.00201","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.00201","created_at":"2026-07-05T06:05:38Z"},{"alias_kind":"arxiv_version","alias_value":"2305.00201v1","created_at":"2026-07-05T06:05:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.00201","created_at":"2026-07-05T06:05:38Z"},{"alias_kind":"pith_short_12","alias_value":"SNBYB3WC5EP2","created_at":"2026-07-05T06:05:38Z"},{"alias_kind":"pith_short_16","alias_value":"SNBYB3WC5EP232EW","created_at":"2026-07-05T06:05:38Z"},{"alias_kind":"pith_short_8","alias_value":"SNBYB3WC","created_at":"2026-07-05T06:05:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:SNBYB3WC5EP232EWCRF2UJX3BO","target":"record","payload":{"canonical_record":{"source":{"id":"2305.00201","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-29T08:59:12Z","cross_cats_sorted":[],"title_canon_sha256":"beefe2e817ceeb687aa4a2e580287c7017b0262157cc0eeb1d4d32f6cfc5e87d","abstract_canon_sha256":"4eccb75e8928dbf8ae0b3b1a52a6021eb4bae8b8891d773e1789f9509726a469"},"schema_version":"1.0"},"canonical_sha256":"934380eec2e91fade896144baa26fb0b8e3c0a7db9c24421cfbb0eb0bf329a6f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:05:38.477565Z","signature_b64":"7aw/pnY8cXVFsDiClmbVPRXGnhdGsXT9xXlHsn/GHy3wTlVte7YpOpFurv2n4sBDhmy8LcUVaNdQJ8b12DZwAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"934380eec2e91fade896144baa26fb0b8e3c0a7db9c24421cfbb0eb0bf329a6f","last_reissued_at":"2026-07-05T06:05:38.477160Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:05:38.477160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.00201","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":"2026-07-05T06:05:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8PmzltX0HQbBThXhId7FDTyOY2TkeOdH7CW5Q58yfcey8UPWzptj4MTp6RgiPeuzZiUFZ1aKY8N3FwKbpIcrBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:21:20.522004Z"},"content_sha256":"f3bff1935031b41d83ba17c822d30bd49f19327dab6aec4373b877ebbff029d7","schema_version":"1.0","event_id":"sha256:f3bff1935031b41d83ba17c822d30bd49f19327dab6aec4373b877ebbff029d7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:SNBYB3WC5EP232EWCRF2UJX3BO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Instruction-ViT: Multi-Modal Prompts for Instruction Learning in ViT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chong Ma, Dajiang Zhu, Dinggang Shen, Junjie Yao, Lin Zhao, Lu Zhang, Tianming Liu, Wei Liu, Xiang Li, Xiaowei Yu, Xi Jiang, Xinyu Liu, Yi Pan, Yixuan Yuan, Yuzhong Chen, Zhenxiang Xiao, Zihao Wu","submitted_at":"2023-04-29T08:59:12Z","abstract_excerpt":"Prompts have been proven to play a crucial role in large language models, and in recent years, vision models have also been using prompts to improve scalability for multiple downstream tasks. In this paper, we focus on adapting prompt design based on instruction tuning into a visual transformer model for image classification which we called Instruction-ViT. The key idea is to implement multi-modal prompts (text or image prompt) related to category information to guide the fine-tuning of the model. Based on the experiments of several image captionining tasks, the performance and domain adaptabi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.00201","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/2305.00201/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":"2026-07-05T06:05:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hc/fDss7lmsBwr+iw1HMltnTHsmkuLH++cnF59aledY0E+AV/jeloJip5KoBFPHGdTrkex0Y34xJVR7KqjrcCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:21:20.522392Z"},"content_sha256":"3edf1722702b3a3ad05ff94a7f02d08213223ee99c7ec7fa1b4124b88ef23bc2","schema_version":"1.0","event_id":"sha256:3edf1722702b3a3ad05ff94a7f02d08213223ee99c7ec7fa1b4124b88ef23bc2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SNBYB3WC5EP232EWCRF2UJX3BO/bundle.json","state_url":"https://pith.science/pith/SNBYB3WC5EP232EWCRF2UJX3BO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SNBYB3WC5EP232EWCRF2UJX3BO/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":"2026-07-06T19:21:20Z","links":{"resolver":"https://pith.science/pith/SNBYB3WC5EP232EWCRF2UJX3BO","bundle":"https://pith.science/pith/SNBYB3WC5EP232EWCRF2UJX3BO/bundle.json","state":"https://pith.science/pith/SNBYB3WC5EP232EWCRF2UJX3BO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SNBYB3WC5EP232EWCRF2UJX3BO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SNBYB3WC5EP232EWCRF2UJX3BO","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":"4eccb75e8928dbf8ae0b3b1a52a6021eb4bae8b8891d773e1789f9509726a469","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-29T08:59:12Z","title_canon_sha256":"beefe2e817ceeb687aa4a2e580287c7017b0262157cc0eeb1d4d32f6cfc5e87d"},"schema_version":"1.0","source":{"id":"2305.00201","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.00201","created_at":"2026-07-05T06:05:38Z"},{"alias_kind":"arxiv_version","alias_value":"2305.00201v1","created_at":"2026-07-05T06:05:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.00201","created_at":"2026-07-05T06:05:38Z"},{"alias_kind":"pith_short_12","alias_value":"SNBYB3WC5EP2","created_at":"2026-07-05T06:05:38Z"},{"alias_kind":"pith_short_16","alias_value":"SNBYB3WC5EP232EW","created_at":"2026-07-05T06:05:38Z"},{"alias_kind":"pith_short_8","alias_value":"SNBYB3WC","created_at":"2026-07-05T06:05:38Z"}],"graph_snapshots":[{"event_id":"sha256:3edf1722702b3a3ad05ff94a7f02d08213223ee99c7ec7fa1b4124b88ef23bc2","target":"graph","created_at":"2026-07-05T06:05:38Z","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/2305.00201/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Prompts have been proven to play a crucial role in large language models, and in recent years, vision models have also been using prompts to improve scalability for multiple downstream tasks. In this paper, we focus on adapting prompt design based on instruction tuning into a visual transformer model for image classification which we called Instruction-ViT. The key idea is to implement multi-modal prompts (text or image prompt) related to category information to guide the fine-tuning of the model. Based on the experiments of several image captionining tasks, the performance and domain adaptabi","authors_text":"Chong Ma, Dajiang Zhu, Dinggang Shen, Junjie Yao, Lin Zhao, Lu Zhang, Tianming Liu, Wei Liu, Xiang Li, Xiaowei Yu, Xi Jiang, Xinyu Liu, Yi Pan, Yixuan Yuan, Yuzhong Chen, Zhenxiang Xiao, Zihao Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-29T08:59:12Z","title":"Instruction-ViT: Multi-Modal Prompts for Instruction Learning in ViT"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.00201","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:f3bff1935031b41d83ba17c822d30bd49f19327dab6aec4373b877ebbff029d7","target":"record","created_at":"2026-07-05T06:05:38Z","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":"4eccb75e8928dbf8ae0b3b1a52a6021eb4bae8b8891d773e1789f9509726a469","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-29T08:59:12Z","title_canon_sha256":"beefe2e817ceeb687aa4a2e580287c7017b0262157cc0eeb1d4d32f6cfc5e87d"},"schema_version":"1.0","source":{"id":"2305.00201","kind":"arxiv","version":1}},"canonical_sha256":"934380eec2e91fade896144baa26fb0b8e3c0a7db9c24421cfbb0eb0bf329a6f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"934380eec2e91fade896144baa26fb0b8e3c0a7db9c24421cfbb0eb0bf329a6f","first_computed_at":"2026-07-05T06:05:38.477160Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:05:38.477160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7aw/pnY8cXVFsDiClmbVPRXGnhdGsXT9xXlHsn/GHy3wTlVte7YpOpFurv2n4sBDhmy8LcUVaNdQJ8b12DZwAA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:05:38.477565Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.00201","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f3bff1935031b41d83ba17c822d30bd49f19327dab6aec4373b877ebbff029d7","sha256:3edf1722702b3a3ad05ff94a7f02d08213223ee99c7ec7fa1b4124b88ef23bc2"],"state_sha256":"fc81c34c834861062c3137c985dea6710d5ccb499aafb605be24ea2fc1b40fa7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6UkXJHwjMRmwTosTnrJ4QBtraIL9MKVzvc/DTuUSlrtGZLr2mrCweWgP7OYQO5fTlK7RFc8ebQpWmdqRIE2qAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T19:21:20.524347Z","bundle_sha256":"33c3babc2f6e1fe52ad965de29076df2c9b4f45010e81220bd9f622dc0302d9f"}}