{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:XBUMV42O26JLH6KYRGM5S6UHPY","short_pith_number":"pith:XBUMV42O","canonical_record":{"source":{"id":"2607.22662","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-29T03:25:36Z","cross_cats_sorted":[],"title_canon_sha256":"628dad5c0001666ba1a402f5a825848881f5abfcb4c3fdd6174909ecc825437e","abstract_canon_sha256":"ed74a6b7bdc77e987944e76c67143d1b1ff088f50d1601b5b4667baf3a321a36"},"schema_version":"1.0"},"canonical_sha256":"b868caf34ed792b3f9588999d97a877e0d05aea3a0374aeef56f6acb2e5e56cd","source":{"kind":"arxiv","id":"2607.22662","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.22662","created_at":"2026-07-28T00:21:47Z"},{"alias_kind":"arxiv_version","alias_value":"2607.22662v1","created_at":"2026-07-28T00:21:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22662","created_at":"2026-07-28T00:21:47Z"},{"alias_kind":"pith_short_12","alias_value":"XBUMV42O26JL","created_at":"2026-07-28T00:21:47Z"},{"alias_kind":"pith_short_16","alias_value":"XBUMV42O26JLH6KY","created_at":"2026-07-28T00:21:47Z"},{"alias_kind":"pith_short_8","alias_value":"XBUMV42O","created_at":"2026-07-28T00:21:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:XBUMV42O26JLH6KYRGM5S6UHPY","target":"record","payload":{"canonical_record":{"source":{"id":"2607.22662","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-29T03:25:36Z","cross_cats_sorted":[],"title_canon_sha256":"628dad5c0001666ba1a402f5a825848881f5abfcb4c3fdd6174909ecc825437e","abstract_canon_sha256":"ed74a6b7bdc77e987944e76c67143d1b1ff088f50d1601b5b4667baf3a321a36"},"schema_version":"1.0"},"canonical_sha256":"b868caf34ed792b3f9588999d97a877e0d05aea3a0374aeef56f6acb2e5e56cd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T00:21:47.899425Z","signature_b64":"VEEtOUtrWA5zKELRQPRSvyW8G6pFBKshVcsKomsojERYBOWj56JImmQis6Igkhzl6H+uF7kuJi3iWVtg/DCWBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b868caf34ed792b3f9588999d97a877e0d05aea3a0374aeef56f6acb2e5e56cd","last_reissued_at":"2026-07-28T00:21:47.898326Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T00:21:47.898326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.22662","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":"2026-07-28T00:21:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ho1IvqkNCm6Dh+ofNx1k5vOMxjJbDypOZLOJPL9y3vZBRJ/uBhm8C0gdAxOEn9X9O4n0vrEobzgsIuxY4SvhBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T07:39:50.157593Z"},"content_sha256":"4ccca2e415f339d24a9a96f251b85da4983cbd5f260649e11276b4995f903cfa","schema_version":"1.0","event_id":"sha256:4ccca2e415f339d24a9a96f251b85da4983cbd5f260649e11276b4995f903cfa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:XBUMV42O26JLH6KYRGM5S6UHPY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CuraWeb: Joint Optimization of Quality, Redundancy, and Diversity for Web-Scale Pretraining Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Gan Dong, Jianxiao Yang, Jian Yang, Jingang Wang, Juncheng Diao, Peiguang Li, Rongxiang Weng, Shuguang Jiao, Xiao Wei, Xunliang Cai, Yongwei Zhou, Yuchun Fan, Zhiye Zou, Zhizhao Zeng, Zhongda Su","submitted_at":"2026-06-29T03:25:36Z","abstract_excerpt":"Open-web corpora curated via highly selective filters, such as FineWeb-Edu and DCLM, constitute the core of LLM pretraining data and have significantly advanced LLM performance. However, these pipelines typically rely on singular optimization objectives, which inevitably narrows distributional diversity and marginalizes long-tail knowledge, thereby restricting data coverage and underutilizing the vast potential of the open web. To address this limitation, we propose a novel curation paradigm that shifts from linear pruning to the joint optimization of quality, redundancy, and diversity. This f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22662","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/2607.22662/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":"2026-07-28T00:21:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2xPSC1bWVYEQQilrMhd+z/gp+Ej8WIy9jWw6oKxue82MjW5GCr5w3I9a1F5v/WhksOgvLUysl2Lyp6uGgf7+BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T07:39:50.158169Z"},"content_sha256":"203b9502ff8cd95f9951698c194662a743fc177cfa6d8e763d8d864f045bd59f","schema_version":"1.0","event_id":"sha256:203b9502ff8cd95f9951698c194662a743fc177cfa6d8e763d8d864f045bd59f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XBUMV42O26JLH6KYRGM5S6UHPY/bundle.json","state_url":"https://pith.science/pith/XBUMV42O26JLH6KYRGM5S6UHPY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XBUMV42O26JLH6KYRGM5S6UHPY/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":"2026-08-20T07:39:50Z","links":{"resolver":"https://pith.science/pith/XBUMV42O26JLH6KYRGM5S6UHPY","bundle":"https://pith.science/pith/XBUMV42O26JLH6KYRGM5S6UHPY/bundle.json","state":"https://pith.science/pith/XBUMV42O26JLH6KYRGM5S6UHPY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XBUMV42O26JLH6KYRGM5S6UHPY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XBUMV42O26JLH6KYRGM5S6UHPY","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":"ed74a6b7bdc77e987944e76c67143d1b1ff088f50d1601b5b4667baf3a321a36","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-29T03:25:36Z","title_canon_sha256":"628dad5c0001666ba1a402f5a825848881f5abfcb4c3fdd6174909ecc825437e"},"schema_version":"1.0","source":{"id":"2607.22662","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.22662","created_at":"2026-07-28T00:21:47Z"},{"alias_kind":"arxiv_version","alias_value":"2607.22662v1","created_at":"2026-07-28T00:21:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22662","created_at":"2026-07-28T00:21:47Z"},{"alias_kind":"pith_short_12","alias_value":"XBUMV42O26JL","created_at":"2026-07-28T00:21:47Z"},{"alias_kind":"pith_short_16","alias_value":"XBUMV42O26JLH6KY","created_at":"2026-07-28T00:21:47Z"},{"alias_kind":"pith_short_8","alias_value":"XBUMV42O","created_at":"2026-07-28T00:21:47Z"}],"graph_snapshots":[{"event_id":"sha256:203b9502ff8cd95f9951698c194662a743fc177cfa6d8e763d8d864f045bd59f","target":"graph","created_at":"2026-07-28T00:21:47Z","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/2607.22662/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Open-web corpora curated via highly selective filters, such as FineWeb-Edu and DCLM, constitute the core of LLM pretraining data and have significantly advanced LLM performance. However, these pipelines typically rely on singular optimization objectives, which inevitably narrows distributional diversity and marginalizes long-tail knowledge, thereby restricting data coverage and underutilizing the vast potential of the open web. To address this limitation, we propose a novel curation paradigm that shifts from linear pruning to the joint optimization of quality, redundancy, and diversity. This f","authors_text":"Gan Dong, Jianxiao Yang, Jian Yang, Jingang Wang, Juncheng Diao, Peiguang Li, Rongxiang Weng, Shuguang Jiao, Xiao Wei, Xunliang Cai, Yongwei Zhou, Yuchun Fan, Zhiye Zou, Zhizhao Zeng, Zhongda Su","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-29T03:25:36Z","title":"CuraWeb: Joint Optimization of Quality, Redundancy, and Diversity for Web-Scale Pretraining Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22662","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":"sha256:4ccca2e415f339d24a9a96f251b85da4983cbd5f260649e11276b4995f903cfa","target":"record","created_at":"2026-07-28T00:21:47Z","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":"ed74a6b7bdc77e987944e76c67143d1b1ff088f50d1601b5b4667baf3a321a36","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-29T03:25:36Z","title_canon_sha256":"628dad5c0001666ba1a402f5a825848881f5abfcb4c3fdd6174909ecc825437e"},"schema_version":"1.0","source":{"id":"2607.22662","kind":"arxiv","version":1}},"canonical_sha256":"b868caf34ed792b3f9588999d97a877e0d05aea3a0374aeef56f6acb2e5e56cd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b868caf34ed792b3f9588999d97a877e0d05aea3a0374aeef56f6acb2e5e56cd","first_computed_at":"2026-07-28T00:21:47.898326Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T00:21:47.898326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VEEtOUtrWA5zKELRQPRSvyW8G6pFBKshVcsKomsojERYBOWj56JImmQis6Igkhzl6H+uF7kuJi3iWVtg/DCWBA==","signature_status":"signed_v1","signed_at":"2026-07-28T00:21:47.899425Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.22662","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ccca2e415f339d24a9a96f251b85da4983cbd5f260649e11276b4995f903cfa","sha256:203b9502ff8cd95f9951698c194662a743fc177cfa6d8e763d8d864f045bd59f"],"state_sha256":"3c21b3a1fa546a86f9567998d098169cd99b1ae07fcf286933a695006ed90fd8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SIsbPafjVcYMbCLwEaMATZOHexpjU+xS3iz35zzQ7qAyP6OedGC3xMV269hR3hqG+aB22h+dhsarcILEv1BZDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T07:39:50.163385Z","bundle_sha256":"644ac7af900f913e79cdaeeb48cce2528cd45874ac25eba9e76d3a0cea07df26"}}