{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:7Z5VBZLETTRGN5O46TGC2BPNZZ","short_pith_number":"pith:7Z5VBZLE","canonical_record":{"source":{"id":"2303.17169","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-30T06:02:40Z","cross_cats_sorted":[],"title_canon_sha256":"483817ee189c62ef5167a2e0abac150cc773c82f3847463ea3840ed2b437e0ac","abstract_canon_sha256":"20ad12b56be492797d2e39d3e90553087fc9c9b8f5cb83be990bc54d0c03be08"},"schema_version":"1.0"},"canonical_sha256":"fe7b50e5649ce266f5dcf4cc2d05edce6276d3808ffdafa39b3672f962ed18d0","source":{"kind":"arxiv","id":"2303.17169","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.17169","created_at":"2026-07-05T05:56:20Z"},{"alias_kind":"arxiv_version","alias_value":"2303.17169v1","created_at":"2026-07-05T05:56:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.17169","created_at":"2026-07-05T05:56:20Z"},{"alias_kind":"pith_short_12","alias_value":"7Z5VBZLETTRG","created_at":"2026-07-05T05:56:20Z"},{"alias_kind":"pith_short_16","alias_value":"7Z5VBZLETTRGN5O4","created_at":"2026-07-05T05:56:20Z"},{"alias_kind":"pith_short_8","alias_value":"7Z5VBZLE","created_at":"2026-07-05T05:56:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:7Z5VBZLETTRGN5O46TGC2BPNZZ","target":"record","payload":{"canonical_record":{"source":{"id":"2303.17169","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-30T06:02:40Z","cross_cats_sorted":[],"title_canon_sha256":"483817ee189c62ef5167a2e0abac150cc773c82f3847463ea3840ed2b437e0ac","abstract_canon_sha256":"20ad12b56be492797d2e39d3e90553087fc9c9b8f5cb83be990bc54d0c03be08"},"schema_version":"1.0"},"canonical_sha256":"fe7b50e5649ce266f5dcf4cc2d05edce6276d3808ffdafa39b3672f962ed18d0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:56:20.442007Z","signature_b64":"Zn4rpmjyHdSrpitO3uynM0PHsbVhmTdfGyOljYnS9zfYVIsQB/IAVDY2aMzQ/ZkM73uPaxeNujcokN6PjTRZAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe7b50e5649ce266f5dcf4cc2d05edce6276d3808ffdafa39b3672f962ed18d0","last_reissued_at":"2026-07-05T05:56:20.441637Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:56:20.441637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.17169","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":"2026-07-05T05:56:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N1dyIFQPKCoDDeUJXYO2GNgenTGXXm9vqXGvgcES3qhR7K+0gEvxksyEetGCgdaKRoLOWAGdNa9fp4uy4bADDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:06:36.995458Z"},"content_sha256":"578eb1bd23f9664c6c8c0976e21c06339ef7c5dddecb093bcc5a9c7cb3c8e008","schema_version":"1.0","event_id":"sha256:578eb1bd23f9664c6c8c0976e21c06339ef7c5dddecb093bcc5a9c7cb3c8e008"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:7Z5VBZLETTRGN5O46TGC2BPNZZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Task-Oriented Multi-Modal Mutual Leaning for Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiangjiang Liu, Jingdong Wang, Junkun Yuan, Luping Zhou, Shengsheng Wang, Sifan Long, Zhen Zhao, Zichang Tan","submitted_at":"2023-03-30T06:02:40Z","abstract_excerpt":"Prompt learning has become one of the most efficient paradigms for adapting large pre-trained vision-language models to downstream tasks. Current state-of-the-art methods, like CoOp and ProDA, tend to adopt soft prompts to learn an appropriate prompt for each specific task. Recent CoCoOp further boosts the base-to-new generalization performance via an image-conditional prompt. However, it directly fuses identical image semantics to prompts of different labels and significantly weakens the discrimination among different classes as shown in our experiments. Motivated by this observation, we firs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.17169","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/2303.17169/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":"2026-07-05T05:56:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/R8XiRV03J0cpDqQC1T51IM32O/Udh2n16OEqXdcWFuaU+KarC0HV+VOI1uZhp2zFy/3s+gszRL0za9wPXqmDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:06:36.996387Z"},"content_sha256":"279ca953caca8c2de98b0aeaaf40ec41cd686f204c3cbe29bbb575faf5368d91","schema_version":"1.0","event_id":"sha256:279ca953caca8c2de98b0aeaaf40ec41cd686f204c3cbe29bbb575faf5368d91"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7Z5VBZLETTRGN5O46TGC2BPNZZ/bundle.json","state_url":"https://pith.science/pith/7Z5VBZLETTRGN5O46TGC2BPNZZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7Z5VBZLETTRGN5O46TGC2BPNZZ/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":"2026-08-04T10:06:36Z","links":{"resolver":"https://pith.science/pith/7Z5VBZLETTRGN5O46TGC2BPNZZ","bundle":"https://pith.science/pith/7Z5VBZLETTRGN5O46TGC2BPNZZ/bundle.json","state":"https://pith.science/pith/7Z5VBZLETTRGN5O46TGC2BPNZZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7Z5VBZLETTRGN5O46TGC2BPNZZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7Z5VBZLETTRGN5O46TGC2BPNZZ","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":"20ad12b56be492797d2e39d3e90553087fc9c9b8f5cb83be990bc54d0c03be08","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-30T06:02:40Z","title_canon_sha256":"483817ee189c62ef5167a2e0abac150cc773c82f3847463ea3840ed2b437e0ac"},"schema_version":"1.0","source":{"id":"2303.17169","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.17169","created_at":"2026-07-05T05:56:20Z"},{"alias_kind":"arxiv_version","alias_value":"2303.17169v1","created_at":"2026-07-05T05:56:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.17169","created_at":"2026-07-05T05:56:20Z"},{"alias_kind":"pith_short_12","alias_value":"7Z5VBZLETTRG","created_at":"2026-07-05T05:56:20Z"},{"alias_kind":"pith_short_16","alias_value":"7Z5VBZLETTRGN5O4","created_at":"2026-07-05T05:56:20Z"},{"alias_kind":"pith_short_8","alias_value":"7Z5VBZLE","created_at":"2026-07-05T05:56:20Z"}],"graph_snapshots":[{"event_id":"sha256:279ca953caca8c2de98b0aeaaf40ec41cd686f204c3cbe29bbb575faf5368d91","target":"graph","created_at":"2026-07-05T05:56:20Z","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/2303.17169/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Prompt learning has become one of the most efficient paradigms for adapting large pre-trained vision-language models to downstream tasks. Current state-of-the-art methods, like CoOp and ProDA, tend to adopt soft prompts to learn an appropriate prompt for each specific task. Recent CoCoOp further boosts the base-to-new generalization performance via an image-conditional prompt. However, it directly fuses identical image semantics to prompts of different labels and significantly weakens the discrimination among different classes as shown in our experiments. Motivated by this observation, we firs","authors_text":"Jiangjiang Liu, Jingdong Wang, Junkun Yuan, Luping Zhou, Shengsheng Wang, Sifan Long, Zhen Zhao, Zichang Tan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-30T06:02:40Z","title":"Task-Oriented Multi-Modal Mutual Leaning for Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.17169","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":"sha256:578eb1bd23f9664c6c8c0976e21c06339ef7c5dddecb093bcc5a9c7cb3c8e008","target":"record","created_at":"2026-07-05T05:56:20Z","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":"20ad12b56be492797d2e39d3e90553087fc9c9b8f5cb83be990bc54d0c03be08","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-30T06:02:40Z","title_canon_sha256":"483817ee189c62ef5167a2e0abac150cc773c82f3847463ea3840ed2b437e0ac"},"schema_version":"1.0","source":{"id":"2303.17169","kind":"arxiv","version":1}},"canonical_sha256":"fe7b50e5649ce266f5dcf4cc2d05edce6276d3808ffdafa39b3672f962ed18d0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fe7b50e5649ce266f5dcf4cc2d05edce6276d3808ffdafa39b3672f962ed18d0","first_computed_at":"2026-07-05T05:56:20.441637Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:56:20.441637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zn4rpmjyHdSrpitO3uynM0PHsbVhmTdfGyOljYnS9zfYVIsQB/IAVDY2aMzQ/ZkM73uPaxeNujcokN6PjTRZAg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:56:20.442007Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.17169","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:578eb1bd23f9664c6c8c0976e21c06339ef7c5dddecb093bcc5a9c7cb3c8e008","sha256:279ca953caca8c2de98b0aeaaf40ec41cd686f204c3cbe29bbb575faf5368d91"],"state_sha256":"8d99e2c8bbbc576d218bf5a1d04f9d5c207950e0ecee64a5d821aeaf1b3fe80c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oxxH5sbeR4VZUoEHQ6p8DM+6xTrsu3sbJ12GjbhkmttPcwX3FpvpGmaMzkdfna4bdiKQj5BHGOJHsA0QHt+VCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T10:06:37.002777Z","bundle_sha256":"b3214a99b485dd0e31a192da1a3900807c39af66d81962062dc7b8ee09168134"}}