{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:DBS7N64WJ5WRZ5H5TQTATWR6PX","short_pith_number":"pith:DBS7N64W","canonical_record":{"source":{"id":"2309.13847","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-25T03:20:09Z","cross_cats_sorted":[],"title_canon_sha256":"6a234906e98560b67f4c3bae58b43583c64d790a794f128b9b808ad564deb1dc","abstract_canon_sha256":"9dfef745768e12e07b10ecfe6132a53d29c0e4f6639924bc0871f4c0829c9a43"},"schema_version":"1.0"},"canonical_sha256":"1865f6fb964f6d1cf4fd9c2609da3e7df35dc786ef43187695364c7b305547b2","source":{"kind":"arxiv","id":"2309.13847","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.13847","created_at":"2026-07-05T07:05:13Z"},{"alias_kind":"arxiv_version","alias_value":"2309.13847v2","created_at":"2026-07-05T07:05:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.13847","created_at":"2026-07-05T07:05:13Z"},{"alias_kind":"pith_short_12","alias_value":"DBS7N64WJ5WR","created_at":"2026-07-05T07:05:13Z"},{"alias_kind":"pith_short_16","alias_value":"DBS7N64WJ5WRZ5H5","created_at":"2026-07-05T07:05:13Z"},{"alias_kind":"pith_short_8","alias_value":"DBS7N64W","created_at":"2026-07-05T07:05:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:DBS7N64WJ5WRZ5H5TQTATWR6PX","target":"record","payload":{"canonical_record":{"source":{"id":"2309.13847","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-25T03:20:09Z","cross_cats_sorted":[],"title_canon_sha256":"6a234906e98560b67f4c3bae58b43583c64d790a794f128b9b808ad564deb1dc","abstract_canon_sha256":"9dfef745768e12e07b10ecfe6132a53d29c0e4f6639924bc0871f4c0829c9a43"},"schema_version":"1.0"},"canonical_sha256":"1865f6fb964f6d1cf4fd9c2609da3e7df35dc786ef43187695364c7b305547b2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:13.655807Z","signature_b64":"f0G+kCVyujUZ9DeBK7etg/Rert38pbY1cvcLD74hb7xvgmR3BEN0tAdCA1xJ1BtMGOBd+u7X5URE7P1cRqL9Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1865f6fb964f6d1cf4fd9c2609da3e7df35dc786ef43187695364c7b305547b2","last_reissued_at":"2026-07-05T07:05:13.655337Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:13.655337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.13847","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":"2026-07-05T07:05:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tMmLbwi2+bghFeY7QKKnvCF81JjCn0FDFC8Z+nm53WUZJID+PBF1Amk3r1fp0Q0o3C/z3v3XzY9ZXQAsFUNEBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:29:44.618758Z"},"content_sha256":"a95bcf45e5fd273344281b1f639df76f86c3052122b476f03264e93835dedc76","schema_version":"1.0","event_id":"sha256:a95bcf45e5fd273344281b1f639df76f86c3052122b476f03264e93835dedc76"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:DBS7N64WJ5WRZ5H5TQTATWR6PX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tuning Multi-mode Token-level Prompt Alignment across Modalities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Chen, Dongsheng Wang, Hanwang Zhang, Miaoge Li, Mingsheng Xu, Xinyang Liu","submitted_at":"2023-09-25T03:20:09Z","abstract_excerpt":"Advancements in prompt tuning of vision-language models have underscored their potential in enhancing open-world visual concept comprehension. However, prior works only primarily focus on single-mode (only one prompt for each modality) and holistic level (image or sentence) semantic alignment, which fails to capture the sample diversity, leading to sub-optimal prompt discovery. To address the limitation, we propose a multi-mode token-level tuning framework that leverages the optimal transportation to learn and align a set of prompt tokens across modalities. Specifically, we rely on two essenti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.13847","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/2309.13847/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":"2026-07-05T07:05:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KqN+qzcAJTz4Oanxs47wcnuMw4F86VNyo7/kwoG7w9xuYA0lgr0VZBJoSeukOzze/2q5pY+JBZLhHJm4+klWAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:29:44.619125Z"},"content_sha256":"4222302e82cf2bdae483b7eda20baec70070006ef0c2d86e8b6c22b628576134","schema_version":"1.0","event_id":"sha256:4222302e82cf2bdae483b7eda20baec70070006ef0c2d86e8b6c22b628576134"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DBS7N64WJ5WRZ5H5TQTATWR6PX/bundle.json","state_url":"https://pith.science/pith/DBS7N64WJ5WRZ5H5TQTATWR6PX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DBS7N64WJ5WRZ5H5TQTATWR6PX/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":"2026-07-06T08:29:44Z","links":{"resolver":"https://pith.science/pith/DBS7N64WJ5WRZ5H5TQTATWR6PX","bundle":"https://pith.science/pith/DBS7N64WJ5WRZ5H5TQTATWR6PX/bundle.json","state":"https://pith.science/pith/DBS7N64WJ5WRZ5H5TQTATWR6PX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DBS7N64WJ5WRZ5H5TQTATWR6PX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:DBS7N64WJ5WRZ5H5TQTATWR6PX","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":"9dfef745768e12e07b10ecfe6132a53d29c0e4f6639924bc0871f4c0829c9a43","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-25T03:20:09Z","title_canon_sha256":"6a234906e98560b67f4c3bae58b43583c64d790a794f128b9b808ad564deb1dc"},"schema_version":"1.0","source":{"id":"2309.13847","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.13847","created_at":"2026-07-05T07:05:13Z"},{"alias_kind":"arxiv_version","alias_value":"2309.13847v2","created_at":"2026-07-05T07:05:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.13847","created_at":"2026-07-05T07:05:13Z"},{"alias_kind":"pith_short_12","alias_value":"DBS7N64WJ5WR","created_at":"2026-07-05T07:05:13Z"},{"alias_kind":"pith_short_16","alias_value":"DBS7N64WJ5WRZ5H5","created_at":"2026-07-05T07:05:13Z"},{"alias_kind":"pith_short_8","alias_value":"DBS7N64W","created_at":"2026-07-05T07:05:13Z"}],"graph_snapshots":[{"event_id":"sha256:4222302e82cf2bdae483b7eda20baec70070006ef0c2d86e8b6c22b628576134","target":"graph","created_at":"2026-07-05T07:05:13Z","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/2309.13847/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Advancements in prompt tuning of vision-language models have underscored their potential in enhancing open-world visual concept comprehension. However, prior works only primarily focus on single-mode (only one prompt for each modality) and holistic level (image or sentence) semantic alignment, which fails to capture the sample diversity, leading to sub-optimal prompt discovery. To address the limitation, we propose a multi-mode token-level tuning framework that leverages the optimal transportation to learn and align a set of prompt tokens across modalities. Specifically, we rely on two essenti","authors_text":"Bo Chen, Dongsheng Wang, Hanwang Zhang, Miaoge Li, Mingsheng Xu, Xinyang Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-25T03:20:09Z","title":"Tuning Multi-mode Token-level Prompt Alignment across Modalities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.13847","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:a95bcf45e5fd273344281b1f639df76f86c3052122b476f03264e93835dedc76","target":"record","created_at":"2026-07-05T07:05:13Z","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":"9dfef745768e12e07b10ecfe6132a53d29c0e4f6639924bc0871f4c0829c9a43","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-25T03:20:09Z","title_canon_sha256":"6a234906e98560b67f4c3bae58b43583c64d790a794f128b9b808ad564deb1dc"},"schema_version":"1.0","source":{"id":"2309.13847","kind":"arxiv","version":2}},"canonical_sha256":"1865f6fb964f6d1cf4fd9c2609da3e7df35dc786ef43187695364c7b305547b2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1865f6fb964f6d1cf4fd9c2609da3e7df35dc786ef43187695364c7b305547b2","first_computed_at":"2026-07-05T07:05:13.655337Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:05:13.655337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f0G+kCVyujUZ9DeBK7etg/Rert38pbY1cvcLD74hb7xvgmR3BEN0tAdCA1xJ1BtMGOBd+u7X5URE7P1cRqL9Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:05:13.655807Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.13847","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a95bcf45e5fd273344281b1f639df76f86c3052122b476f03264e93835dedc76","sha256:4222302e82cf2bdae483b7eda20baec70070006ef0c2d86e8b6c22b628576134"],"state_sha256":"d321e2b2940db231cc456d502e4ecad422cc87daa63083a1c34633545eb66fbd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kniDpdOWOF1L2ZKRBOcBl6D5UaMGQcQzjh2rXFQ8ZnHZ3veUcZLD+8kESgEvFs/XZXofQteLTNy7NVbq1j+eBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T08:29:44.621145Z","bundle_sha256":"0bb79cc41c276b236c6ccfb6c8df0b786cef6f70d89bd628e099a52844add01b"}}