{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:W7JIC7LSBYMIHAPPPCCUIZ2H3G","short_pith_number":"pith:W7JIC7LS","canonical_record":{"source":{"id":"2607.08646","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-09T16:18:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cd473c08f1adc82ccfeddd392527f0e9f353dd173d7c1342d3236578f6b4582c","abstract_canon_sha256":"d34d5fc7dbf9beafd19f32f71033b40258905be5d8528096e0c85d4bde87c191"},"schema_version":"1.0"},"canonical_sha256":"b7d2817d720e188381ef7885446747d9a05d26f1e52309d4b23b190a367fe105","source":{"kind":"arxiv","id":"2607.08646","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.08646","created_at":"2026-07-10T01:19:56Z"},{"alias_kind":"arxiv_version","alias_value":"2607.08646v1","created_at":"2026-07-10T01:19:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08646","created_at":"2026-07-10T01:19:56Z"},{"alias_kind":"pith_short_12","alias_value":"W7JIC7LSBYMI","created_at":"2026-07-10T01:19:56Z"},{"alias_kind":"pith_short_16","alias_value":"W7JIC7LSBYMIHAPP","created_at":"2026-07-10T01:19:56Z"},{"alias_kind":"pith_short_8","alias_value":"W7JIC7LS","created_at":"2026-07-10T01:19:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:W7JIC7LSBYMIHAPPPCCUIZ2H3G","target":"record","payload":{"canonical_record":{"source":{"id":"2607.08646","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-09T16:18:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cd473c08f1adc82ccfeddd392527f0e9f353dd173d7c1342d3236578f6b4582c","abstract_canon_sha256":"d34d5fc7dbf9beafd19f32f71033b40258905be5d8528096e0c85d4bde87c191"},"schema_version":"1.0"},"canonical_sha256":"b7d2817d720e188381ef7885446747d9a05d26f1e52309d4b23b190a367fe105","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-10T01:19:56.482029Z","signature_b64":"u6fUZPl33sqEdbdLWIKcHJ8rvKgF5VuUsnhiIR47yF5hwIhHogqXZB6OpjpJh4gpjmo4BkHV8eqwgBHnwxC0CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7d2817d720e188381ef7885446747d9a05d26f1e52309d4b23b190a367fe105","last_reissued_at":"2026-07-10T01:19:56.481612Z","signature_status":"signed_v1","first_computed_at":"2026-07-10T01:19:56.481612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.08646","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":"2026-07-10T01:19:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SukIVkcv+rE4wXZF29kas5cT3s92zKeDJ4lcyijLm5bDZU0QrLaCEP1j0m0np57T7nbqssflM2KYWuMZrsKbDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:22:30.652644Z"},"content_sha256":"c7c5084d0b0fa88febcb3d59903c69219ae4daad6d494ac146243e101fc6b8bc","schema_version":"1.0","event_id":"sha256:c7c5084d0b0fa88febcb3d59903c69219ae4daad6d494ac146243e101fc6b8bc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:W7JIC7LSBYMIHAPPPCCUIZ2H3G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"UltraX: Refining Pre-Training Data at Scale with Adaptive Programmatic Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dongsheng Liu, Hengyu Zhao, Jie Cai, Jie Zhou, Qiang Ma, XinLong Zhao, Xuanhe Zhou, Xu Han, Yudong Wang, Zheng Wang, Zhiyuan Liu, Zixuan Fu","submitted_at":"2026-07-09T16:18:07Z","abstract_excerpt":"As available training data approaches its physical limit, gains from Scaling Laws have begun to diminish. Consequently, improving Large Language Models (LLMs) now depends less on data expansion and more on higher-quality data utilization. However, in the context of large-scale corpora, existing refinement methodologies face significant limitations in quality, efficiency, and reliability: Rule-based approaches are constrained by fixed heuristics and struggle with instance-level variations; LLM-based approaches improve quality but fail to meet the efficiency and reliability requirements of large"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08646","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/2607.08646/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":"2026-07-10T01:19:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YoKjapjSdMIp4Stp0YFzI6D/o+fR0/ZgoJAqQ/xLs8JQG/GeGM9lXtk/Fxp8xgPvJH2vgZbR6AqU5Y0CEAB1AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:22:30.653144Z"},"content_sha256":"21d708c09d06d7ffcd3c0aa145c5b43ad72de7bf8b1accc1548a25250427d44c","schema_version":"1.0","event_id":"sha256:21d708c09d06d7ffcd3c0aa145c5b43ad72de7bf8b1accc1548a25250427d44c"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:W7JIC7LSBYMIHAPPPCCUIZ2H3G","target":"integrity","payload":{"note":"URL 'https://github.com/openbmb/UltraX' returned status 404 (Not Found) at last check.","snippet":null,"arxiv_id":"2607.08646","detector":"external_links","evidence":{"url":"https://github.com/openbmb/UltraX","final_url":"https://github.com/openbmb/UltraX","host_kind":"github","status_code":404,"status_text":"Not Found","verdict_class":"incontrovertible","checked_at_unix":1783683269.1312454},"severity":"critical","ref_index":null,"audited_at":"2026-07-10T11:34:32.916973Z","event_type":"pith.integrity.v1","detected_doi":null,"detector_url":"https://pith.science/pith-integrity-protocol#external_links","external_url":"https://github.com/openbmb/UltraX","finding_type":"dead_code_link","evidence_hash":"8ecb0d1101a1586f7252d41d1c50976b76bf394db104ea381fa2b6dec74711ee","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":11942,"payload_sha256":"94f1933ffa5c9a5b95ed625b5ad75b12da78d811489a3c16b5036d6791e6926f","signature_b64":"OyEaIWtCnyyQROlj0Zm7Y4RH6WxCtPS8iLc4ZAUbbCIxw6XSc2Wh0jZUIrj6dPt3dmB4x0Ew/I3b2ixgvkyYAA==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-10T11:39:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hA7ahz9duQlzB6Cp94T6lkSZGyVDPy3kdE7jFfcBRv12UZlHjq6Tx4f+PAe157ukyzTTJ3HsKCVi0c2Ou0VWDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:22:30.685464Z"},"content_sha256":"e3ca8fdddf7d2277e047f30c9185933e0cd3dddd20131fbabec2596548ba30fb","schema_version":"1.0","event_id":"sha256:e3ca8fdddf7d2277e047f30c9185933e0cd3dddd20131fbabec2596548ba30fb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W7JIC7LSBYMIHAPPPCCUIZ2H3G/bundle.json","state_url":"https://pith.science/pith/W7JIC7LSBYMIHAPPPCCUIZ2H3G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W7JIC7LSBYMIHAPPPCCUIZ2H3G/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":"2026-08-05T20:22:30Z","links":{"resolver":"https://pith.science/pith/W7JIC7LSBYMIHAPPPCCUIZ2H3G","bundle":"https://pith.science/pith/W7JIC7LSBYMIHAPPPCCUIZ2H3G/bundle.json","state":"https://pith.science/pith/W7JIC7LSBYMIHAPPPCCUIZ2H3G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W7JIC7LSBYMIHAPPPCCUIZ2H3G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:W7JIC7LSBYMIHAPPPCCUIZ2H3G","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d34d5fc7dbf9beafd19f32f71033b40258905be5d8528096e0c85d4bde87c191","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-09T16:18:07Z","title_canon_sha256":"cd473c08f1adc82ccfeddd392527f0e9f353dd173d7c1342d3236578f6b4582c"},"schema_version":"1.0","source":{"id":"2607.08646","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.08646","created_at":"2026-07-10T01:19:56Z"},{"alias_kind":"arxiv_version","alias_value":"2607.08646v1","created_at":"2026-07-10T01:19:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08646","created_at":"2026-07-10T01:19:56Z"},{"alias_kind":"pith_short_12","alias_value":"W7JIC7LSBYMI","created_at":"2026-07-10T01:19:56Z"},{"alias_kind":"pith_short_16","alias_value":"W7JIC7LSBYMIHAPP","created_at":"2026-07-10T01:19:56Z"},{"alias_kind":"pith_short_8","alias_value":"W7JIC7LS","created_at":"2026-07-10T01:19:56Z"}],"graph_snapshots":[{"event_id":"sha256:21d708c09d06d7ffcd3c0aa145c5b43ad72de7bf8b1accc1548a25250427d44c","target":"graph","created_at":"2026-07-10T01:19:56Z","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/2607.08646/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As available training data approaches its physical limit, gains from Scaling Laws have begun to diminish. Consequently, improving Large Language Models (LLMs) now depends less on data expansion and more on higher-quality data utilization. However, in the context of large-scale corpora, existing refinement methodologies face significant limitations in quality, efficiency, and reliability: Rule-based approaches are constrained by fixed heuristics and struggle with instance-level variations; LLM-based approaches improve quality but fail to meet the efficiency and reliability requirements of large","authors_text":"Dongsheng Liu, Hengyu Zhao, Jie Cai, Jie Zhou, Qiang Ma, XinLong Zhao, Xuanhe Zhou, Xu Han, Yudong Wang, Zheng Wang, Zhiyuan Liu, Zixuan Fu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-09T16:18:07Z","title":"UltraX: Refining Pre-Training Data at Scale with Adaptive Programmatic Editing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08646","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:c7c5084d0b0fa88febcb3d59903c69219ae4daad6d494ac146243e101fc6b8bc","target":"record","created_at":"2026-07-10T01:19:56Z","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":"d34d5fc7dbf9beafd19f32f71033b40258905be5d8528096e0c85d4bde87c191","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-09T16:18:07Z","title_canon_sha256":"cd473c08f1adc82ccfeddd392527f0e9f353dd173d7c1342d3236578f6b4582c"},"schema_version":"1.0","source":{"id":"2607.08646","kind":"arxiv","version":1}},"canonical_sha256":"b7d2817d720e188381ef7885446747d9a05d26f1e52309d4b23b190a367fe105","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b7d2817d720e188381ef7885446747d9a05d26f1e52309d4b23b190a367fe105","first_computed_at":"2026-07-10T01:19:56.481612Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-10T01:19:56.481612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u6fUZPl33sqEdbdLWIKcHJ8rvKgF5VuUsnhiIR47yF5hwIhHogqXZB6OpjpJh4gpjmo4BkHV8eqwgBHnwxC0CQ==","signature_status":"signed_v1","signed_at":"2026-07-10T01:19:56.482029Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.08646","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c7c5084d0b0fa88febcb3d59903c69219ae4daad6d494ac146243e101fc6b8bc","sha256:21d708c09d06d7ffcd3c0aa145c5b43ad72de7bf8b1accc1548a25250427d44c","sha256:e3ca8fdddf7d2277e047f30c9185933e0cd3dddd20131fbabec2596548ba30fb"],"state_sha256":"4dc2c3dbf4af32dda48fedb9f259ed34784e2fae540ef5e53f99aa03c62437ce"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ET3ch2ISRAqoeKvpoj+qNvmM758J6fNweGCR9ZYuf759ciRmaz21vXTmjlqmR8QlrqM+mUmhxvYyxIkrGNc9Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T20:22:30.689181Z","bundle_sha256":"cc7c8fe8397720fceb2fc26eb565ab4b4edfe96ca5b328dab9f62e9c69ee74de"}}