{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4SRJPGRHT72PK4OH22GSFM56R6","short_pith_number":"pith:4SRJPGRH","schema_version":"1.0","canonical_sha256":"e4a2979a279ff4f571c7d68d22b3be8f8cdd3ad8e5216e2428d1b6dacb54d587","source":{"kind":"arxiv","id":"2506.01586","version":1},"attestation_state":"computed","paper":{"title":"Multi-Modal Dataset Distillation in the Wild","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chengyou Jia, Hangwei Qian, Ivor W. Tsang, Minnan Luo, Xiaojun Chang, Zhuohang Dang","submitted_at":"2025-06-02T12:18:20Z","abstract_excerpt":"Recent multi-modal models have shown remarkable versatility in real-world applications. However, their rapid development encounters two critical data challenges. First, the training process requires large-scale datasets, leading to substantial storage and computational costs. Second, these data are typically web-crawled with inevitable noise, i.e., partially mismatched pairs, severely degrading model performance. To these ends, we propose Multi-modal dataset Distillation in the Wild, i.e., MDW, the first framework to distill noisy multi-modal datasets into compact clean ones for effective and "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.01586","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-02T12:18:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bcced092a3c06caa9d06f0976a845f9af2fd3ca0458ec661c684cb999cda6b6e","abstract_canon_sha256":"038ef65e54e7dda2af624e4af3dc9a19c05717447a65d8e0fdcdb16798dab5ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:16.247785Z","signature_b64":"f39lTEOuuu6BK2uhH5aMcG5x2Q9aZjXsHi3hwpss54mwRwBfm6pzDL+OZ3T6Emic3aJsIuts141+vWIdr9ohDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4a2979a279ff4f571c7d68d22b3be8f8cdd3ad8e5216e2428d1b6dacb54d587","last_reissued_at":"2026-07-05T11:14:16.247356Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:16.247356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Modal Dataset Distillation in the Wild","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chengyou Jia, Hangwei Qian, Ivor W. Tsang, Minnan Luo, Xiaojun Chang, Zhuohang Dang","submitted_at":"2025-06-02T12:18:20Z","abstract_excerpt":"Recent multi-modal models have shown remarkable versatility in real-world applications. However, their rapid development encounters two critical data challenges. First, the training process requires large-scale datasets, leading to substantial storage and computational costs. Second, these data are typically web-crawled with inevitable noise, i.e., partially mismatched pairs, severely degrading model performance. To these ends, we propose Multi-modal dataset Distillation in the Wild, i.e., MDW, the first framework to distill noisy multi-modal datasets into compact clean ones for effective and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01586","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/2506.01586/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.01586","created_at":"2026-07-05T11:14:16.247415+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01586v1","created_at":"2026-07-05T11:14:16.247415+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01586","created_at":"2026-07-05T11:14:16.247415+00:00"},{"alias_kind":"pith_short_12","alias_value":"4SRJPGRHT72P","created_at":"2026-07-05T11:14:16.247415+00:00"},{"alias_kind":"pith_short_16","alias_value":"4SRJPGRHT72PK4OH","created_at":"2026-07-05T11:14:16.247415+00:00"},{"alias_kind":"pith_short_8","alias_value":"4SRJPGRH","created_at":"2026-07-05T11:14:16.247415+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4SRJPGRHT72PK4OH22GSFM56R6","json":"https://pith.science/pith/4SRJPGRHT72PK4OH22GSFM56R6.json","graph_json":"https://pith.science/api/pith-number/4SRJPGRHT72PK4OH22GSFM56R6/graph.json","events_json":"https://pith.science/api/pith-number/4SRJPGRHT72PK4OH22GSFM56R6/events.json","paper":"https://pith.science/paper/4SRJPGRH"},"agent_actions":{"view_html":"https://pith.science/pith/4SRJPGRHT72PK4OH22GSFM56R6","download_json":"https://pith.science/pith/4SRJPGRHT72PK4OH22GSFM56R6.json","view_paper":"https://pith.science/paper/4SRJPGRH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01586&json=true","fetch_graph":"https://pith.science/api/pith-number/4SRJPGRHT72PK4OH22GSFM56R6/graph.json","fetch_events":"https://pith.science/api/pith-number/4SRJPGRHT72PK4OH22GSFM56R6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4SRJPGRHT72PK4OH22GSFM56R6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4SRJPGRHT72PK4OH22GSFM56R6/action/storage_attestation","attest_author":"https://pith.science/pith/4SRJPGRHT72PK4OH22GSFM56R6/action/author_attestation","sign_citation":"https://pith.science/pith/4SRJPGRHT72PK4OH22GSFM56R6/action/citation_signature","submit_replication":"https://pith.science/pith/4SRJPGRHT72PK4OH22GSFM56R6/action/replication_record"}},"created_at":"2026-07-05T11:14:16.247415+00:00","updated_at":"2026-07-05T11:14:16.247415+00:00"}