{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WWF7IPRFI3U5QRH3SLHHZ4EHDT","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":"c4a9de80c678310788a4bcd864f70e12f28c1187c35ccb5d2a1d26a8cff85b09","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T18:50:15Z","title_canon_sha256":"bc1d6b0e6b3c29f92258057db88f456da9aded19227114f7546cd702308588d5"},"schema_version":"1.0","source":{"id":"2411.18674","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.18674","created_at":"2026-07-05T10:58:20Z"},{"alias_kind":"arxiv_version","alias_value":"2411.18674v2","created_at":"2026-07-05T10:58:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18674","created_at":"2026-07-05T10:58:20Z"},{"alias_kind":"pith_short_12","alias_value":"WWF7IPRFI3U5","created_at":"2026-07-05T10:58:20Z"},{"alias_kind":"pith_short_16","alias_value":"WWF7IPRFI3U5QRH3","created_at":"2026-07-05T10:58:20Z"},{"alias_kind":"pith_short_8","alias_value":"WWF7IPRF","created_at":"2026-07-05T10:58:20Z"}],"graph_snapshots":[{"event_id":"sha256:0941d7e16aa0ac34261b2be49a56fca2230dda7e81ac598bc0459e0b3098156c","target":"graph","created_at":"2026-07-05T10:58:20Z","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/2411.18674/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Knowledge distillation (KD) is the de facto standard for compressing large-scale models into smaller ones. Prior works have explored ever more complex KD strategies involving different objective functions, teacher-ensembles, and weight inheritance. In this work we explore an alternative, yet simple approach -- active data curation as effective distillation for contrastive multimodal pretraining. Our simple online batch selection method, ACID, outperforms strong KD baselines across various model-, data- and compute-configurations. Further, we find such an active data curation strategy to in fac","authors_text":"Alessio Tonioni, Federico Tombari, Muhammad Ferjad Naeem, Nikhil Parthasarathy, Olivier J. H\\'enaff, Samuel Albanie, Talfan Evans, Vishaal Udandarao, Yongqin Xian","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T18:50:15Z","title":"Active Data Curation Effectively Distills Large-Scale Multimodal Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18674","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:e05d0585a2736a22a8a7323104362dc84ef5b5b4ea5efe082c28efa5e8762a24","target":"record","created_at":"2026-07-05T10:58:20Z","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":"c4a9de80c678310788a4bcd864f70e12f28c1187c35ccb5d2a1d26a8cff85b09","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T18:50:15Z","title_canon_sha256":"bc1d6b0e6b3c29f92258057db88f456da9aded19227114f7546cd702308588d5"},"schema_version":"1.0","source":{"id":"2411.18674","kind":"arxiv","version":2}},"canonical_sha256":"b58bf43e2546e9d844fb92ce7cf0871cd7362efa87e286a7db7ee8be1ad7e4e8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b58bf43e2546e9d844fb92ce7cf0871cd7362efa87e286a7db7ee8be1ad7e4e8","first_computed_at":"2026-07-05T10:58:20.780365Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:58:20.780365Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V0oOEYUbK4ezgTsOUxF2DGD7QbhYabV7Qfb/2/X2MhQf3dJlbIaomTrkJiS8Bvi+CeMZ3jf393Fq52AU38MaDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:58:20.780884Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.18674","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e05d0585a2736a22a8a7323104362dc84ef5b5b4ea5efe082c28efa5e8762a24","sha256:0941d7e16aa0ac34261b2be49a56fca2230dda7e81ac598bc0459e0b3098156c"],"state_sha256":"5638b6ca9657025da1369433c6d842100a714920a0f9aa9cd1f8a41a21ad742e"}