{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2V6UDYAKFKQOA4UDHQSWRWEIXT","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":"2e5f171b72116f53a3ed91535e5be273a3a9b72c7cf1bca68508acf9288e146f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-12T08:40:57Z","title_canon_sha256":"ebe7e385cbf1cde3840758ac14e8f86187ae8028cc8c0702d9176a1685bb2dd5"},"schema_version":"1.0","source":{"id":"2502.08211","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.08211","created_at":"2026-07-05T11:20:09Z"},{"alias_kind":"arxiv_version","alias_value":"2502.08211v2","created_at":"2026-07-05T11:20:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08211","created_at":"2026-07-05T11:20:09Z"},{"alias_kind":"pith_short_12","alias_value":"2V6UDYAKFKQO","created_at":"2026-07-05T11:20:09Z"},{"alias_kind":"pith_short_16","alias_value":"2V6UDYAKFKQOA4UD","created_at":"2026-07-05T11:20:09Z"},{"alias_kind":"pith_short_8","alias_value":"2V6UDYAK","created_at":"2026-07-05T11:20:09Z"}],"graph_snapshots":[{"event_id":"sha256:197116e294afcc6800bb4d077c27a4ebaa6b24b89798c32c3227527f3b599257","target":"graph","created_at":"2026-07-05T11:20:09Z","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/2502.08211/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In an era overwhelmed by vast amounts of data, the effective curation of web-crawl datasets is essential for optimizing model performance. This paper tackles the challenges associated with the unstructured and heterogeneous nature of such datasets. Traditional heuristic curation methods often inadequately capture complex features, resulting in biases and the exclusion of relevant data. We introduce an advanced, learning-driven approach, Ensemble Curation Of DAta ThroUgh Multimodal Operators (EcoDatum), incorporating a novel quality-guided deduplication method to ensure balanced feature distrib","authors_text":"Daming Wang, Jinda Xu, Kangliang Chen, Minghua Chen, Qinya Li, Weiwei Zhao, Yuhao Song","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-12T08:40:57Z","title":"Quality over Quantity: Boosting Data Efficiency Through Ensembled Multimodal Data Curation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08211","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":"sha256:77654f0bb079ba53dd6ac6d170f588dd35ff3746274ea8a480889c2e956a9e8b","target":"record","created_at":"2026-07-05T11:20:09Z","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":"2e5f171b72116f53a3ed91535e5be273a3a9b72c7cf1bca68508acf9288e146f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-12T08:40:57Z","title_canon_sha256":"ebe7e385cbf1cde3840758ac14e8f86187ae8028cc8c0702d9176a1685bb2dd5"},"schema_version":"1.0","source":{"id":"2502.08211","kind":"arxiv","version":2}},"canonical_sha256":"d57d41e00a2aa0e072833c2568d888bce34c07ba3ad47da247133366231cb10e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d57d41e00a2aa0e072833c2568d888bce34c07ba3ad47da247133366231cb10e","first_computed_at":"2026-07-05T11:20:09.180188Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:20:09.180188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sbt1Gu6thNq3K5nQOIuDlyMaUy9t0NVEpvmu8Yvk8ynl8g+TmevIer5Tq39fgge7TQSKJGi3vCMv2/V68VesAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:20:09.180713Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.08211","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:77654f0bb079ba53dd6ac6d170f588dd35ff3746274ea8a480889c2e956a9e8b","sha256:197116e294afcc6800bb4d077c27a4ebaa6b24b89798c32c3227527f3b599257"],"state_sha256":"c8a91c9ef8a422f1486dcf23bc6b4cea52436bc286f7552a3378e12e08ee0c68"}