{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VWKB4KJG5XAJKW7ZQH6P6Z2UBL","short_pith_number":"pith:VWKB4KJG","canonical_record":{"source":{"id":"2406.17711","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-25T16:52:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b0dc21deb351687f6597a0240d8c95ac42bc684a30c0f9f8dd6722d2344957d8","abstract_canon_sha256":"5aae069d0083b50df31d1111b9024ad2d4cbcd12e91f54d452bb4e0da9f9ac5f"},"schema_version":"1.0"},"canonical_sha256":"ad941e2926edc0955bf981fcff67540ad8f14896a15d4b88c1eb730a4419b8cd","source":{"kind":"arxiv","id":"2406.17711","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.17711","created_at":"2026-07-05T08:36:39Z"},{"alias_kind":"arxiv_version","alias_value":"2406.17711v1","created_at":"2026-07-05T08:36:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.17711","created_at":"2026-07-05T08:36:39Z"},{"alias_kind":"pith_short_12","alias_value":"VWKB4KJG5XAJ","created_at":"2026-07-05T08:36:39Z"},{"alias_kind":"pith_short_16","alias_value":"VWKB4KJG5XAJKW7Z","created_at":"2026-07-05T08:36:39Z"},{"alias_kind":"pith_short_8","alias_value":"VWKB4KJG","created_at":"2026-07-05T08:36:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VWKB4KJG5XAJKW7ZQH6P6Z2UBL","target":"record","payload":{"canonical_record":{"source":{"id":"2406.17711","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-25T16:52:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b0dc21deb351687f6597a0240d8c95ac42bc684a30c0f9f8dd6722d2344957d8","abstract_canon_sha256":"5aae069d0083b50df31d1111b9024ad2d4cbcd12e91f54d452bb4e0da9f9ac5f"},"schema_version":"1.0"},"canonical_sha256":"ad941e2926edc0955bf981fcff67540ad8f14896a15d4b88c1eb730a4419b8cd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:36:39.014606Z","signature_b64":"Kw9O07Yz9fE99VK3CepQyB/DHdyY0j4X2ne+kbl9G8D6JHfrcJU/CRFgaxe0yT+FGY9K8JaA9DbaVZmUvsN+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad941e2926edc0955bf981fcff67540ad8f14896a15d4b88c1eb730a4419b8cd","last_reissued_at":"2026-07-05T08:36:39.014161Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:36:39.014161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.17711","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":"2026-07-05T08:36:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZhP7bjB2INqGygs5uO4UAzEhqYHP2EYroRHrIY+ljkXHYJBPQrCCWv+TOa8NS5BUNkX4cGJJQ2iyuh75BEUMAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:08:05.576565Z"},"content_sha256":"fdd56126ea383005f43f06dfac3bbcc3aa9c1b47ef4c8b98da9ac4511b6e59f3","schema_version":"1.0","event_id":"sha256:fdd56126ea383005f43f06dfac3bbcc3aa9c1b47ef4c8b98da9ac4511b6e59f3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VWKB4KJG5XAJKW7ZQH6P6Z2UBL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data curation via joint example selection further accelerates multimodal learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hamza Merzic, Nikhil Parthasarathy, Olivier J. Henaff, Talfan Evans","submitted_at":"2024-06-25T16:52:37Z","abstract_excerpt":"Data curation is an essential component of large-scale pretraining. In this work, we demonstrate that jointly selecting batches of data is more effective for learning than selecting examples independently. Multimodal contrastive objectives expose the dependencies between data and thus naturally yield criteria for measuring the joint learnability of a batch. We derive a simple and tractable algorithm for selecting such batches, which significantly accelerate training beyond individually-prioritized data points. As performance improves by selecting from larger super-batches, we also leverage rec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.17711","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/2406.17711/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":"2026-07-05T08:36:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yJpG6HX+OXF+26dA3DGi+zqvttIWT5F69XRuAElULCo2wwtyN6D0MuLkFIhUJHOE5Vfs+VE+3F/M9OdpOIiZBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:08:05.577505Z"},"content_sha256":"e800556f1807c8d057561a08f0b41989efe58b70b98164d3dac01163f2e09432","schema_version":"1.0","event_id":"sha256:e800556f1807c8d057561a08f0b41989efe58b70b98164d3dac01163f2e09432"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VWKB4KJG5XAJKW7ZQH6P6Z2UBL/bundle.json","state_url":"https://pith.science/pith/VWKB4KJG5XAJKW7ZQH6P6Z2UBL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VWKB4KJG5XAJKW7ZQH6P6Z2UBL/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":"2026-08-03T22:08:05Z","links":{"resolver":"https://pith.science/pith/VWKB4KJG5XAJKW7ZQH6P6Z2UBL","bundle":"https://pith.science/pith/VWKB4KJG5XAJKW7ZQH6P6Z2UBL/bundle.json","state":"https://pith.science/pith/VWKB4KJG5XAJKW7ZQH6P6Z2UBL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VWKB4KJG5XAJKW7ZQH6P6Z2UBL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VWKB4KJG5XAJKW7ZQH6P6Z2UBL","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":"5aae069d0083b50df31d1111b9024ad2d4cbcd12e91f54d452bb4e0da9f9ac5f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-25T16:52:37Z","title_canon_sha256":"b0dc21deb351687f6597a0240d8c95ac42bc684a30c0f9f8dd6722d2344957d8"},"schema_version":"1.0","source":{"id":"2406.17711","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.17711","created_at":"2026-07-05T08:36:39Z"},{"alias_kind":"arxiv_version","alias_value":"2406.17711v1","created_at":"2026-07-05T08:36:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.17711","created_at":"2026-07-05T08:36:39Z"},{"alias_kind":"pith_short_12","alias_value":"VWKB4KJG5XAJ","created_at":"2026-07-05T08:36:39Z"},{"alias_kind":"pith_short_16","alias_value":"VWKB4KJG5XAJKW7Z","created_at":"2026-07-05T08:36:39Z"},{"alias_kind":"pith_short_8","alias_value":"VWKB4KJG","created_at":"2026-07-05T08:36:39Z"}],"graph_snapshots":[{"event_id":"sha256:e800556f1807c8d057561a08f0b41989efe58b70b98164d3dac01163f2e09432","target":"graph","created_at":"2026-07-05T08:36:39Z","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/2406.17711/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data curation is an essential component of large-scale pretraining. In this work, we demonstrate that jointly selecting batches of data is more effective for learning than selecting examples independently. Multimodal contrastive objectives expose the dependencies between data and thus naturally yield criteria for measuring the joint learnability of a batch. We derive a simple and tractable algorithm for selecting such batches, which significantly accelerate training beyond individually-prioritized data points. As performance improves by selecting from larger super-batches, we also leverage rec","authors_text":"Hamza Merzic, Nikhil Parthasarathy, Olivier J. Henaff, Talfan Evans","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-25T16:52:37Z","title":"Data curation via joint example selection further accelerates multimodal learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.17711","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:fdd56126ea383005f43f06dfac3bbcc3aa9c1b47ef4c8b98da9ac4511b6e59f3","target":"record","created_at":"2026-07-05T08:36:39Z","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":"5aae069d0083b50df31d1111b9024ad2d4cbcd12e91f54d452bb4e0da9f9ac5f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-25T16:52:37Z","title_canon_sha256":"b0dc21deb351687f6597a0240d8c95ac42bc684a30c0f9f8dd6722d2344957d8"},"schema_version":"1.0","source":{"id":"2406.17711","kind":"arxiv","version":1}},"canonical_sha256":"ad941e2926edc0955bf981fcff67540ad8f14896a15d4b88c1eb730a4419b8cd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad941e2926edc0955bf981fcff67540ad8f14896a15d4b88c1eb730a4419b8cd","first_computed_at":"2026-07-05T08:36:39.014161Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:36:39.014161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Kw9O07Yz9fE99VK3CepQyB/DHdyY0j4X2ne+kbl9G8D6JHfrcJU/CRFgaxe0yT+FGY9K8JaA9DbaVZmUvsN+Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:36:39.014606Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.17711","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fdd56126ea383005f43f06dfac3bbcc3aa9c1b47ef4c8b98da9ac4511b6e59f3","sha256:e800556f1807c8d057561a08f0b41989efe58b70b98164d3dac01163f2e09432"],"state_sha256":"9d3c83d9b1b763f413044a4d09df1ce4dc1e1149ee768eedb1da413a0329dacb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CrbU9odMHk77u3ZYDOCAuZAxkBdQW9D1y63X03MZ05jj3AlIgKdutCrpFNTiXtJd5YzBTI9JaCp5s9pYfX+0Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T22:08:05.585236Z","bundle_sha256":"05019222a94c4a5728f4d904c661551fa9cd6b0e4f9ceb9f6e0600e9c2e84966"}}