{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4SRJPGRHT72PK4OH22GSFM56R6","short_pith_number":"pith:4SRJPGRH","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"},"canonical_sha256":"e4a2979a279ff4f571c7d68d22b3be8f8cdd3ad8e5216e2428d1b6dacb54d587","source":{"kind":"arxiv","id":"2506.01586","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01586","created_at":"2026-07-05T11:14:16Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01586v1","created_at":"2026-07-05T11:14:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01586","created_at":"2026-07-05T11:14:16Z"},{"alias_kind":"pith_short_12","alias_value":"4SRJPGRHT72P","created_at":"2026-07-05T11:14:16Z"},{"alias_kind":"pith_short_16","alias_value":"4SRJPGRHT72PK4OH","created_at":"2026-07-05T11:14:16Z"},{"alias_kind":"pith_short_8","alias_value":"4SRJPGRH","created_at":"2026-07-05T11:14:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4SRJPGRHT72PK4OH22GSFM56R6","target":"record","payload":{"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"},"canonical_sha256":"e4a2979a279ff4f571c7d68d22b3be8f8cdd3ad8e5216e2428d1b6dacb54d587","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"},"source_kind":"arxiv","source_id":"2506.01586","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":"2026-07-05T11:14:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3ORaTJnuPLBvBW9df1utdkasgW91xV0qqcs3ds7xfswIEB9OWUjQjE0/yXe/oZLd7+4MLsMAK3rWass2sEufDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T23:11:38.181562Z"},"content_sha256":"05344e74bde84b738ef28806efd2f775ef14f2e938fc350ac1901442891d21cf","schema_version":"1.0","event_id":"sha256:05344e74bde84b738ef28806efd2f775ef14f2e938fc350ac1901442891d21cf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4SRJPGRHT72PK4OH22GSFM56R6","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:14:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Tese/ydc6PZg5LBIsJ44yBOlUducm+nRXVDaWBqY+BSZ61ShvzIBizRbVzfoGSjpucBeuhVGWBVfb2xZdtwfDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T23:11:38.182067Z"},"content_sha256":"b5d2f8d3724ec5619d4f44d6c76bb5d228e34c90b46c5bbca2a3537845cbcd2a","schema_version":"1.0","event_id":"sha256:b5d2f8d3724ec5619d4f44d6c76bb5d228e34c90b46c5bbca2a3537845cbcd2a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4SRJPGRHT72PK4OH22GSFM56R6/bundle.json","state_url":"https://pith.science/pith/4SRJPGRHT72PK4OH22GSFM56R6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4SRJPGRHT72PK4OH22GSFM56R6/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":"2026-08-08T23:11:38Z","links":{"resolver":"https://pith.science/pith/4SRJPGRHT72PK4OH22GSFM56R6","bundle":"https://pith.science/pith/4SRJPGRHT72PK4OH22GSFM56R6/bundle.json","state":"https://pith.science/pith/4SRJPGRHT72PK4OH22GSFM56R6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4SRJPGRHT72PK4OH22GSFM56R6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4SRJPGRHT72PK4OH22GSFM56R6","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":"038ef65e54e7dda2af624e4af3dc9a19c05717447a65d8e0fdcdb16798dab5ba","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-02T12:18:20Z","title_canon_sha256":"bcced092a3c06caa9d06f0976a845f9af2fd3ca0458ec661c684cb999cda6b6e"},"schema_version":"1.0","source":{"id":"2506.01586","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01586","created_at":"2026-07-05T11:14:16Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01586v1","created_at":"2026-07-05T11:14:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01586","created_at":"2026-07-05T11:14:16Z"},{"alias_kind":"pith_short_12","alias_value":"4SRJPGRHT72P","created_at":"2026-07-05T11:14:16Z"},{"alias_kind":"pith_short_16","alias_value":"4SRJPGRHT72PK4OH","created_at":"2026-07-05T11:14:16Z"},{"alias_kind":"pith_short_8","alias_value":"4SRJPGRH","created_at":"2026-07-05T11:14:16Z"}],"graph_snapshots":[{"event_id":"sha256:b5d2f8d3724ec5619d4f44d6c76bb5d228e34c90b46c5bbca2a3537845cbcd2a","target":"graph","created_at":"2026-07-05T11:14:16Z","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/2506.01586/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Chengyou Jia, Hangwei Qian, Ivor W. Tsang, Minnan Luo, Xiaojun Chang, Zhuohang Dang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-02T12:18:20Z","title":"Multi-Modal Dataset Distillation in the Wild"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01586","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":"sha256:05344e74bde84b738ef28806efd2f775ef14f2e938fc350ac1901442891d21cf","target":"record","created_at":"2026-07-05T11:14:16Z","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":"038ef65e54e7dda2af624e4af3dc9a19c05717447a65d8e0fdcdb16798dab5ba","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-02T12:18:20Z","title_canon_sha256":"bcced092a3c06caa9d06f0976a845f9af2fd3ca0458ec661c684cb999cda6b6e"},"schema_version":"1.0","source":{"id":"2506.01586","kind":"arxiv","version":1}},"canonical_sha256":"e4a2979a279ff4f571c7d68d22b3be8f8cdd3ad8e5216e2428d1b6dacb54d587","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e4a2979a279ff4f571c7d68d22b3be8f8cdd3ad8e5216e2428d1b6dacb54d587","first_computed_at":"2026-07-05T11:14:16.247356Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:16.247356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f39lTEOuuu6BK2uhH5aMcG5x2Q9aZjXsHi3hwpss54mwRwBfm6pzDL+OZ3T6Emic3aJsIuts141+vWIdr9ohDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:16.247785Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.01586","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05344e74bde84b738ef28806efd2f775ef14f2e938fc350ac1901442891d21cf","sha256:b5d2f8d3724ec5619d4f44d6c76bb5d228e34c90b46c5bbca2a3537845cbcd2a"],"state_sha256":"a9f1619789ad271643e27859012de794c58e5a9e285fcc7e534659bb30219eb1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qo0Jj7GzKmw7stKtFqwyyMsxcwuoVxY11T+PkozZMbR0oNrG5+4k1t+9Y9bFWgG+WvaiV/JOauLVxI+nSXpmDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T23:11:38.186827Z","bundle_sha256":"b638cc0e5695afc42dda3e301fbb071860ffc854ec280879de63384969503bb9"}}