{"_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_12443daaab05a219c85c2ad5325b38fde62356e6185acd56c1434d83e8534541","bitcoin_anchor":{"bitcoin_attestations":["bitcoin_block_949451"],"calendar_attestations":["https://finney.calendar.eternitywall.com","https://btc.calendar.catallaxy.com","https://alice.btc.calendar.opentimestamps.org","https://bob.btc.calendar.opentimestamps.org"],"ots_url":"/registry/data/substrate/anchors/77fc9c28fae777b81da5b495b3115474df6592dfac590333213d3bdf8b94a9b3.ots","stamped_at":"2026-05-15T03:00:03Z","status":"bitcoin"},"envelope":{"anchors":[{"chain":"crovia.axiom_graph","height":0,"merkle_proof":"spider_vendor_press_v1","root_at_anchor":"spider_vendor_press_v1"}],"axiom_id":"axm_12443daaab05a219c85c2ad5325b38fde62356e6185acd56c1434d83e8534541","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"9ab5792519b1134d1d8ee25180c245cf77083dd97e23be8d55245669a5ed8c29","published":"Tue, 05 May 2026 00:00:00 -0400","receipt_hash":"9ab5792519b1134d1d8ee25180c245cf77083dd97e23be8d55245669a5ed8c29","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":"9ab5792519b1134d1d8ee25180c245cf77083dd97e23be8d55245669a5ed8c29","observed_at":"2026-05-05T04:43:28.458286Z","parent_run_hash":"84f40dd8e6af9caa9f2a7fd632024f0e0192177c4532d9af5caf61b409324d7a","published":"Tue, 05 May 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:2604.28075v2 Announce Type: replace-cross \nAbstract: Recent research has shown that filtering massive English web corpora into high-quality subsets significantly improves training efficiency. However, for high-resource non-English languages like German, French, or Japanese, aggressive filtering creates a strategic dilemma: should practitioners prioritize diversity by training once on large amounts of lightly filtered web data, or prioritize quality by strictly filtering for a high-quality core and repeating it over multiple epochs? We investigate this trade-off for German by constructing hierarchical quality filters applied to 500M web documents, comparing multi-epoch training on the filtered subsets against single-pass training on a diverse corpus. Our experiments across multiple model scales and token budgets show that repeating high-quality data consistently outperforms single-pass training on larger, less filtered sets. Notably, the performance gap persists even after 7 epoch","title":"Repetition over Diversity: High-Signal Data Filtering for Sample-Efficient German Language Modeling","url":"https://arxiv.org/abs/2604.28075","vendor":"arxiv_cs_ai"},"summary":"arXiv:2604.28075v2 Announce Type: replace-cross \nAbstract: Recent research has shown that filtering massive English web corpora into high-quality subsets significantly improves training efficiency. However, for high-resource non-English languages like German, French, or Japanese, aggressive filtering creates a strategic dilemma: should practitioners prioritize diversity by training once on large amounts of lightly filtered web data, or prioritize quality by strictly filtering for a high-quality core and repeating it over multiple epochs? We investigate this trade-off for German by constructing hierarchical quality filters applied to 500M web documents, comparing multi-epoch training on the filtered subsets against single-pass training on a diverse corpus. Our experiments across multiple model scales and token budgets show that repeating high-quality data consistently outperforms single-pass training on larger, less filtered sets. Notably, the performance gap persists even after 7 epoch","title":"Repetition over Diversity: High-Signal Data Filtering for Sample-Efficient German Language Modeling","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-05T04:43:28Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2604.28075"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:637d52a778efdff6018c5f4c61fd31b0168af64b54b3e14ca77bac30e9b83e365d01d00041c7fb7c152857f6fb5cc53fdcec2351b555d2c527a6fb96bf50610f","signer":"crovia.substrate","subject":{"observed_at":"2026-05-05T04:43:28Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2604.28075"},"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":"b82e0bcaef69d077ca3ef687336cbb1704dc94c42bf1c3f0893a443bbf9004a3","leaf_index":114433,"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":"c41fdfbdfba83120c9edc2845026b891e5d92021d14523d4c350cc58cf40c5ff","side":"left"},{"sibling":"de4d2fbf76acb1a8379d651eee85832e45d10ffbdfa5da800de40627e58b590e","side":"right"},{"sibling":"813253ac361ae8e6aff216a6547924c144ad5943d11a21dbcfdf9b77cd444d94","side":"right"},{"sibling":"636e5c740ffb305c64bd34c6af80e3ef44162e959e7fc04eb8a719326e556753","side":"right"},{"sibling":"e9c23979d50a19e7b13a4b02947e176d6bce8617f91e8248771f9e1349591e2e","side":"right"},{"sibling":"5f09b565e30eaa54686d7cd6ec452e3c43419fa19fb97a02f35451febdced7b7","side":"right"},{"sibling":"fbd6574e5a818c12793849c75490787580564c4f072759205cbb2bfd2639f6ff","side":"right"},{"sibling":"27b2499080a0faaf795697a58b31185b5bd299971493824026af4543d84295ae","side":"right"},{"sibling":"79216ea1cdb095fddf30c2914a5fd7ccfe00cef50c3af9b506288bdce49818ef","side":"left"},{"sibling":"8df6c69f776fbba620634f6baf125eeaa6fdf9426e461e649028010d9a703f42","side":"left"},{"sibling":"ea40d1bd0432ad4dd90f023c692aaab8c8f54e27ce652e82f2ec8e16cacfb632","side":"left"},{"sibling":"673cd6d27b696232f7f65e7a0733c7df6bc9fac3bcb569907ebb0de1c72c4bb2","side":"left"},{"sibling":"76d7c4385d71ae8104107105be66eddb792e01ed6e493db5a9b4eec5441abb76","side":"left"},{"sibling":"b03f005860bf95148ea89c703a32ca19ab7a2ca71b58bb628ff94a9edb8703b0","side":"left"},{"sibling":"21d1e30b556f553dc939fddc23e6367f0a7755ebe3dd489dc0001cef017beb7f","side":"right"},{"sibling":"f2817ab288b5324fe49770372c7a10f33f7cd11005f8d4c0a730316f5229dc98","side":"left"},{"sibling":"725fac972e772ca0dc598810ea1abc70df472f72d2d6ab8a0baee2b80e5d2f4c","side":"left"},{"sibling":"98fc57dfef8873b512edc8340f7181df57302bb96777625e072235c62d7c5895","side":"right"}]},"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":134292,"merkle_root":"77fc9c28fae777b81da5b495b3115474df6592dfac590333213d3bdf8b94a9b3","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260515T023701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-15T02:37:25Z","sig_algorithm":"ed25519","signature":"68107a834b00b24f5d4501e5ec727445311f132a486567ecc4c72a4e6dff24c8c21f2de3105293353ba5fdbe370d032819af6aa70f694e2e39b6af6737507009","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_12443daaab05a219c85c2ad5325b38fde62356e6185acd56c1434d83e8534541"}}