{"_canonicalization":{"envelope_id":"axm_ + sha256(envelope minus {signature, axiom_id, anchors})","envelope_signature":"ed25519(envelope minus {signature, axiom_id})","json":"sort_keys=True, separators=(',',':'), ensure_ascii=False, allow_nan=False, utf-8","leaf_hash":"sha256(0x00 || canonical_json(envelope_full))","seal_signature":"ed25519(seal minus {signature, sig_algorithm})"},"axiom_id":"axm_90cf02f93ec9548694a87e2918962f98351ec7c059aa9e6a6c09ba557dc5cc26","bitcoin_anchor":{"bitcoin_attestations":[],"calendar_attestations":[],"ots_url":"","stamped_at":"","status":"pending_next_stamp"},"envelope":{"anchors":[{"chain":"crovia.axiom_graph","height":0,"merkle_proof":"spider_vendor_press_v1","root_at_anchor":"spider_vendor_press_v1"}],"axiom_id":"axm_90cf02f93ec9548694a87e2918962f98351ec7c059aa9e6a6c09ba557dc5cc26","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"b691ca59d40b9dcb9f169f3e2229714d9879891827344e619bac355ca6ba4cb2","published":"Fri, 10 Jul 2026 00:00:00 -0400","receipt_hash":"b691ca59d40b9dcb9f169f3e2229714d9879891827344e619bac355ca6ba4cb2","schema":"spider.news.vendor_press.v1","spider":"vendor_press","spider_record":{"axiom_subtype":"news.vendor_press.v1","category":"news","decision_hint":"POSITIVE","envelope_target":"AX.OBS","fingerprint":"b691ca59d40b9dcb9f169f3e2229714d9879891827344e619bac355ca6ba4cb2","observed_at":"2026-07-10T04:43:53.465232Z","parent_run_hash":"06997be187ba20932a2030c56de194579eacf484085252a25bee544eab183e91","published":"Fri, 10 Jul 2026 00:00:00 -0400","runtime_version":"0.1.0","schema":"spider.news.vendor_press.v1","source_status":200,"source_url":"https://export.arxiv.org/rss/cs.AI","spider":"vendor_press","summary_excerpt":"arXiv:2607.08646v1 Announce Type: cross \nAbstract: 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-scale data processing. To address these challenges, we propose UltraX, a function-calling refinement framework for large-scale pre-training data that completes the editing function space by introducing insertion in addition to deletion and modification, enabling fine-grained instance-level editing. Specifically, UltraX builds a reliable program-s","title":"UltraX: Refining Pre-Training Data at Scale with Adaptive Programmatic Editing","url":"https://arxiv.org/abs/2607.08646","vendor":"arxiv_cs_ai"},"summary":"arXiv:2607.08646v1 Announce Type: cross \nAbstract: 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-scale data processing. To address these challenges, we propose UltraX, a function-calling refinement framework for large-scale pre-training data that completes the editing function space by introducing insertion in addition to deletion and modification, enabling fine-grained instance-level editing. Specifically, UltraX builds a reliable program-s","title":"UltraX: Refining Pre-Training Data at Scale with Adaptive Programmatic Editing","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-10T04:43:53Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2607.08646"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:ea902ad9ee5c8432180ddf2d194fd04c4a45bd102ce19959fd06070eae96df198e39b90696e37a4b3f3cecde03bd57ee59f489a049757fe56f334c2cb6ffdc0e","signer":"crovia.substrate","subject":{"observed_at":"2026-07-10T04:43:53Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2607.08646"},"tsa":{"authority":"crovia.substrate.bootstrap","rfc3161_token":"{\"kind\":\"crovia.bootstrap.tsa\",\"source_jsonl\":\"/opt/crovia/spider/data/news/vendor_press_v1.jsonl\",\"source_seal_merkle_root\":\"spider_vendor_press_v1\",\"upgrade_path\":\"Sessione H \\u2014 OpenTimestamps weekly anchor\"}"},"zk_mode":"clear","zk_proof":null},"ledger":{"leaf_hash":"c7c7e2d8182ef29f5507542d25899f1285b6ef1f73f2f3036d41fd97b1451612","leaf_index":299499,"ledger_path":"/opt/crovia/substrate/axiom_ledger.jsonl"},"merkle_proof":{"hash_alg":"sha256","leaf_prefix":"0x00","node_prefix":"0x01","odd_leaf_rule":"duplicate_last","path":[{"sibling":"93516a80dde28d34016372ff7341ce2df2639e109702df0184e9bc320b1f0377","side":"left"},{"sibling":"8001ee198b62c4ec02ccbfc99b4a524c4275fb5cbff736cc8d4b5539dc07bd3a","side":"left"},{"sibling":"2c3707397127fb1e14b42140ec824d4f791fb80a29b99ecc82d1d3db76b64796","side":"right"},{"sibling":"dbe657c37bdb79e7c0a8985ea778a7202de87316f52db94908bda960eefec124","side":"left"},{"sibling":"65927017fdfd7ca0e9c71a80f1bf99a7c312875fbfd928572651f1ccb80904bf","side":"right"},{"sibling":"1e8021b095c74bdab85562264f566a914165bb59331cdb96722f48e8df9f939a","side":"left"},{"sibling":"7a96803ed93140d8d4c0e1fe53c891fc73447ccfce6e55b7c43e7a06979f307a","side":"left"},{"sibling":"b1b72243c904808d4df9b283c65832a729a411520c97fd9d17f891f214971a0a","side":"left"},{"sibling":"2c5ce75ad134aa442d7fbb5dc9968b0f2e48097c2ffaa2111d405de1c4a9c48b","side":"left"},{"sibling":"36a2c507282befad57202dd10278a66d37b402692f195a22d2275b3d1b2488d8","side":"right"},{"sibling":"f80e8d47e0860527b906fc2dba9a52609f7f623f2772479ae922cc019bab36d9","side":"right"},{"sibling":"cae83500ab2c25555aa6b5eaf9232696d15a868d91b34f7531dd955daadf70f7","side":"right"},{"sibling":"64dab64d51bdcb909e2a5e37efb8909d6704ecf824be484b5d2b60ee6e518890","side":"left"},{"sibling":"576f134a23c19a758ae5efd53016092a74b9900e878cf6eb4f3dab6be682b395","side":"right"},{"sibling":"3c65f53d7c3e4feba7c745e8df1327760ffa768eec84336db14d515a31731532","side":"right"},{"sibling":"d8b9143917b539c543cf4448cec00131f8b807bd8004979c54ebe09798748c66","side":"left"},{"sibling":"8728642cdb98496d916cc653f0d919d7eb2e89d0c529927c9e89091074ad584c","side":"right"},{"sibling":"8025674cb002a22ae243ca0c295c18c1d0ee119189ea88e08ac14a3a1468b8e3","side":"right"},{"sibling":"1cecb7f447febd025aac272837c80de218aecc6485d2395a509b2a1f1b9c746e","side":"left"}]},"schema":"crovia.axiom_proof.v1","seal":{"first_collector_run_id":"","first_receipt_hash":"","jsonl_path":"/opt/crovia/substrate/axiom_ledger.jsonl","key_id":"430895f101d38164","last_collector_run_id":"","last_receipt_hash":"","leaf_count":299721,"merkle_root":"f7115d63193d3285ca28cb9f741ecea2513f9b3e492e785f97076f3cf8f9bb98","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260710T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-10T05:38:19Z","sig_algorithm":"ed25519","signature":"4eeedeb744885bff6523d66b1cb86bde62b36917696367addfd980d90b31011daece2e01b20608e4c0870ec31dd0bcb57d297447f01f153bf0716ad527142b00","signer_version":"1.1.0"},"trust_root":{"key_id":"430895f101d38164","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","signature_algorithm":"ed25519","url":"/registry/canon/TRUST_ROOT.md"},"verifier":{"spec":"/registry/canon/AXIOM_RECEIPT_v1.md","url":"/v/axm_90cf02f93ec9548694a87e2918962f98351ec7c059aa9e6a6c09ba557dc5cc26"}}