{"_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_c9334a7e67f876d151101a793eaa49dd81dcc2b9a71d6f8f892b724f9314d25f","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_c9334a7e67f876d151101a793eaa49dd81dcc2b9a71d6f8f892b724f9314d25f","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"466331b43fb36f8705b90e8ae08f4ebbf3af76ecbd972e2bac4980f2a4797dd8","published":"Fri, 26 Jun 2026 00:00:00 -0400","receipt_hash":"466331b43fb36f8705b90e8ae08f4ebbf3af76ecbd972e2bac4980f2a4797dd8","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":"466331b43fb36f8705b90e8ae08f4ebbf3af76ecbd972e2bac4980f2a4797dd8","observed_at":"2026-06-26T04:43:58.168958Z","parent_run_hash":"9459505a803125e4b968df08c74ed0054a2aafd44e4e1a036e3b0709a8a65cb4","published":"Fri, 26 Jun 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:2606.26492v1 Announce Type: cross \nAbstract: Deep Learning (DL) programs can fail during training for many reasons, and diagnosing the cause is a costly and time-consuming maintenance task. Techniques for diagnosing such failures are commonly assessed using within-program cross-validation, which may be inadequate for deployment settings involving previously unseen programs. It is therefore necessary to assess how performance differs across these settings and to identify the causes of any performance gap in established fault diagnosis techniques for DL. We investigate this gap using DynFault, a corpus of 5,542 fault-injected training traces from 38 real-world DL programs. We found a gap of 0.190 in balanced accuracy for existing fault diagnosis techniques between within-program evaluation and holding out whole programs. We also found the gap comes from program-level structure in the features, which led us to examine two runtime feature sets, curvature features and optimizer featur","title":"Evaluation-Strategy Gap in Fault Diagnosis of Deep Learning Programs","url":"https://arxiv.org/abs/2606.26492","vendor":"arxiv_cs_ai"},"summary":"arXiv:2606.26492v1 Announce Type: cross \nAbstract: Deep Learning (DL) programs can fail during training for many reasons, and diagnosing the cause is a costly and time-consuming maintenance task. Techniques for diagnosing such failures are commonly assessed using within-program cross-validation, which may be inadequate for deployment settings involving previously unseen programs. It is therefore necessary to assess how performance differs across these settings and to identify the causes of any performance gap in established fault diagnosis techniques for DL. We investigate this gap using DynFault, a corpus of 5,542 fault-injected training traces from 38 real-world DL programs. We found a gap of 0.190 in balanced accuracy for existing fault diagnosis techniques between within-program evaluation and holding out whole programs. We also found the gap comes from program-level structure in the features, which led us to examine two runtime feature sets, curvature features and optimizer featur","title":"Evaluation-Strategy Gap in Fault Diagnosis of Deep Learning Programs","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-26T04:43:58Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2606.26492"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:1ecb1d81d2cbae96e1fe593e264a06031876ecc54dc86e4d4bf93cee8feebcb8b8eaa10b2f35dfee47c66cf13ace72c87519420f0151ff135c489c6921625b03","signer":"crovia.substrate","subject":{"observed_at":"2026-06-26T04:43:58Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2606.26492"},"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":"55bbe21c35933be5498a879ad779bdd78464e21da624377d0c3e45532fcd1aad","leaf_index":251119,"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":"07c94a6819397a321c7d4e91f8795abdc76665302d0fe85de16b47242c1c5b98","side":"left"},{"sibling":"6e7fcc832c9ad31c22e54112de0e6d6300f65a0ed11037cb1fdd00d5abb625b1","side":"left"},{"sibling":"76e7349728efbcdc36f87886b6d8c94534ae3c58f838f88ff72da4b8ddeda6de","side":"left"},{"sibling":"6fb3b43a9d65de28e236f674060113203e2864360bb7787a3ec7ec9c721695ea","side":"left"},{"sibling":"0e43315bac1aef9284b22e1e1ec564a60c92a04b16c84bfa8ec3c3c8aa82d975","side":"right"},{"sibling":"92cd327d65300d9092d295875064bd3bc7c40618e92d136fc9e99599d4ed2feb","side":"left"},{"sibling":"f9190af89759db1d872794d338826ddd18310851f89900539ca641d4cae8ad95","side":"left"},{"sibling":"762a50202e5bb846bfb5afec2f3cc80d9313546598c6c53f53acc51c6325b763","side":"left"},{"sibling":"e276c2896e885a069398e8350a2d9aae49ed0ab34771e352045341312283b40a","side":"right"},{"sibling":"b6709caadc8510310ee2ec0b66d1058fcad31c91c65cc2bad6f46a693d553580","side":"right"},{"sibling":"a72c3b8804a37d1a9d18e02e6fdb048bc8ea6b0746909cd2de10bdbabc793737","side":"left"},{"sibling":"803703dc2c50a646fa77b57c0056e9a5126611ba4bcde0d6013ccd6b2d44bdbf","side":"right"},{"sibling":"e78f244b1b8df6d5e3fdc6dd76b5c27d4e6fe3b93b8cd61355497b63d7e4cfe8","side":"left"},{"sibling":"6167cb552ed6871fbf0afcf3db01d1017af7d472b136fcbe5404d1df09f41cc1","side":"right"},{"sibling":"f29798d8bb6aa9900eab878992d9ff0c53266debd87472f31ab26a6a3fb55880","side":"left"},{"sibling":"a04392fb9f2a3a620840e3b3fecd93d12e6d224e481c162389d8ae64e7194599","side":"left"},{"sibling":"c300cf0154c136afc09b1702a0be98f4ba5b6dc5cf57e8cc714ec1eaf4196eff","side":"left"},{"sibling":"d841ad93efda0869e5eb97678f348f03f5caab4353e05ff4bf18f47fb945b822","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":251380,"merkle_root":"e042805d07cd8dc777d49695ad78b8d4ec9721df271ff0245d7706773c30b4a5","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260626T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-26T05:37:59Z","sig_algorithm":"ed25519","signature":"c68a6e827804771acd244208495c5e35c6f417307db3c76192f038dedaa5b5f86e019074a3bea353357ff7457924c4f7907832638bb9a4d3d18e7a7f50c6a10b","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_c9334a7e67f876d151101a793eaa49dd81dcc2b9a71d6f8f892b724f9314d25f"}}