{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:WWF7IPRFI3U5QRH3SLHHZ4EHDT","short_pith_number":"pith:WWF7IPRF","canonical_record":{"source":{"id":"2411.18674","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T18:50:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bc1d6b0e6b3c29f92258057db88f456da9aded19227114f7546cd702308588d5","abstract_canon_sha256":"c4a9de80c678310788a4bcd864f70e12f28c1187c35ccb5d2a1d26a8cff85b09"},"schema_version":"1.0"},"canonical_sha256":"b58bf43e2546e9d844fb92ce7cf0871cd7362efa87e286a7db7ee8be1ad7e4e8","source":{"kind":"arxiv","id":"2411.18674","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:WWF7IPRFI3U5QRH3SLHHZ4EHDT","target":"record","payload":{"canonical_record":{"source":{"id":"2411.18674","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T18:50:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bc1d6b0e6b3c29f92258057db88f456da9aded19227114f7546cd702308588d5","abstract_canon_sha256":"c4a9de80c678310788a4bcd864f70e12f28c1187c35ccb5d2a1d26a8cff85b09"},"schema_version":"1.0"},"canonical_sha256":"b58bf43e2546e9d844fb92ce7cf0871cd7362efa87e286a7db7ee8be1ad7e4e8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:20.780884Z","signature_b64":"V0oOEYUbK4ezgTsOUxF2DGD7QbhYabV7Qfb/2/X2MhQf3dJlbIaomTrkJiS8Bvi+CeMZ3jf393Fq52AU38MaDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b58bf43e2546e9d844fb92ce7cf0871cd7362efa87e286a7db7ee8be1ad7e4e8","last_reissued_at":"2026-07-05T10:58:20.780365Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:20.780365Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.18674","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":"2026-07-05T10:58:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XAtKcChqTPN6upCb5jHt1ARDV2d+bKJhZbD1HDlTSObbqUUgtMkdwJA0BOWkRkh4tNsPrAEOtiBmlDuEB4eqDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:58:49.916059Z"},"content_sha256":"e05d0585a2736a22a8a7323104362dc84ef5b5b4ea5efe082c28efa5e8762a24","schema_version":"1.0","event_id":"sha256:e05d0585a2736a22a8a7323104362dc84ef5b5b4ea5efe082c28efa5e8762a24"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:WWF7IPRFI3U5QRH3SLHHZ4EHDT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Active Data Curation Effectively Distills Large-Scale Multimodal Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alessio Tonioni, Federico Tombari, Muhammad Ferjad Naeem, Nikhil Parthasarathy, Olivier J. H\\'enaff, Samuel Albanie, Talfan Evans, Vishaal Udandarao, Yongqin Xian","submitted_at":"2024-11-27T18:50:15Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18674","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/2411.18674/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":"2026-07-05T10:58:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aEeOaRZZxFKwMhIQbzG+982eOfgtvJC6MM738MAdTKFq5KouiTH0NtFKYaOjWSCA3HCHxLq5lOYrCUo6eHllAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:58:49.916584Z"},"content_sha256":"0941d7e16aa0ac34261b2be49a56fca2230dda7e81ac598bc0459e0b3098156c","schema_version":"1.0","event_id":"sha256:0941d7e16aa0ac34261b2be49a56fca2230dda7e81ac598bc0459e0b3098156c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WWF7IPRFI3U5QRH3SLHHZ4EHDT/bundle.json","state_url":"https://pith.science/pith/WWF7IPRFI3U5QRH3SLHHZ4EHDT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WWF7IPRFI3U5QRH3SLHHZ4EHDT/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":"2026-08-09T03:58:49Z","links":{"resolver":"https://pith.science/pith/WWF7IPRFI3U5QRH3SLHHZ4EHDT","bundle":"https://pith.science/pith/WWF7IPRFI3U5QRH3SLHHZ4EHDT/bundle.json","state":"https://pith.science/pith/WWF7IPRFI3U5QRH3SLHHZ4EHDT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WWF7IPRFI3U5QRH3SLHHZ4EHDT/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vcusp0/7l/V0gfkavlOwHyF5kq1iCSOJgDhPnK1gDhW/cJIDY91XcDvUN8dvMK0pnWdDWtPYaPY3rcLV5tgXCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T03:58:49.920107Z","bundle_sha256":"f9d36eb64da4bb2dbb90a75b26a4b240c9e4fa37fd43601049402dd4d60b6853"}}