{"_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_737fe55be0c9c5527c12eedf1033bbc1bba107ae1ad5125f676476f105dd359d","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_737fe55be0c9c5527c12eedf1033bbc1bba107ae1ad5125f676476f105dd359d","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"78846526026c806810561e855dedefe56d3a857606341ace6c71bd0563dd3fc3","published":"Wed, 06 May 2026 00:00:00 -0400","receipt_hash":"78846526026c806810561e855dedefe56d3a857606341ace6c71bd0563dd3fc3","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":"78846526026c806810561e855dedefe56d3a857606341ace6c71bd0563dd3fc3","observed_at":"2026-05-06T04:43:18.518819Z","parent_run_hash":"184209fc0f2ebdc4b721e1a74f74ab17637dab3344682b6e6bd1f3e5e8f2cd00","published":"Wed, 06 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:2605.00944v1 Announce Type: cross \nAbstract: Sample-level rankings are increasingly used in data-centric NLP for analysis, filtering, debugging, and curation, yet existing pipelines typically score training examples pointwise and rank them as if they were independent. This assumption is fragile in the presence of exact duplicates, near-duplicates, paraphrases, and other redundant structure common in NLP corpora, where stochastic training can make highly similar examples receive unstable relative orderings across random seeds. We study stable sample-level ranking under redundancy and propose \\textsc{SCARV}, a modular aggregation framework that operates on top of an existing scoring proxy. \\textsc{SCARV} combines robust multi-seed aggregation with a structure-aware aggregation/allocation step over redundancy clusters. Across synthetic redundancy, naturally mined QQP redundancy, multiple proxy families, several NLP tasks, and end-to-end DistilBERT fine-tuning, \\textsc{SCARV} substan","title":"SCARV: Structure-Constrained Aggregation for Stable Sample Ranking in Redundant NLP Datasets","url":"https://arxiv.org/abs/2605.00944","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.00944v1 Announce Type: cross \nAbstract: Sample-level rankings are increasingly used in data-centric NLP for analysis, filtering, debugging, and curation, yet existing pipelines typically score training examples pointwise and rank them as if they were independent. This assumption is fragile in the presence of exact duplicates, near-duplicates, paraphrases, and other redundant structure common in NLP corpora, where stochastic training can make highly similar examples receive unstable relative orderings across random seeds. We study stable sample-level ranking under redundancy and propose \\textsc{SCARV}, a modular aggregation framework that operates on top of an existing scoring proxy. \\textsc{SCARV} combines robust multi-seed aggregation with a structure-aware aggregation/allocation step over redundancy clusters. Across synthetic redundancy, naturally mined QQP redundancy, multiple proxy families, several NLP tasks, and end-to-end DistilBERT fine-tuning, \\textsc{SCARV} substan","title":"SCARV: Structure-Constrained Aggregation for Stable Sample Ranking in Redundant NLP Datasets","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-06T04:43:18Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2605.00944"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:da542ce8013a351088f1d639a13ad943f0eb58b81a7620f220f3436b8ec76283d1eb5318cf6247804898eb9abcee1e363c9e79c0bd499b2306b6272a54436302","signer":"crovia.substrate","subject":{"observed_at":"2026-05-06T04:43:18Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.00944"},"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":"bfe028490a5dc1c4b88aa5306b49cd7c1c05a0010586053bff01867024c6ca23","leaf_index":116185,"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":"47f36fcc98f76d1ef99dacc591ecd747f75209a39af35db9ef4019997afd30c6","side":"left"},{"sibling":"e4dfebb1ad80f9eac7e8ad2f8f712e21dd45404342b81b7672278f766b0561e0","side":"right"},{"sibling":"c17aebe0673a78d0615bee21a800e573840713f21ab35a4a6aa1d4e3e7830a8b","side":"right"},{"sibling":"230bf7c2b3479329f43606fa110ede46a8a61b1f606a0ebe6f0ca185c606191d","side":"left"},{"sibling":"6dc864ee008829f32624e5438446e37e007760bf33854a20cc61e391ad16d714","side":"left"},{"sibling":"4ff896366d638624ce0156fbad5fe2f0defc8e4ce1a02a5ae6703d8238f6d885","side":"right"},{"sibling":"f80ae3990cd3c4b61ffd8daa9d6ee7b1b36304ac3557faf836fe49c3e7d7fef2","side":"left"},{"sibling":"337e888c904278e2dba91f3f1f4ea3c78aa6421dad9d2b8e076ce153c74c3f82","side":"left"},{"sibling":"aece872b65a68d3775a2636761a78e8ecbdc28b94538a659e6069c57bef430e0","side":"left"},{"sibling":"fb3602a0ad8c9fcab7b18e13690c40ca4a2f5402557d976d681a369555c04ae2","side":"right"},{"sibling":"ddc060ac400459417799f688c75d5b271636afa40d89ec7fc98652473a8061f6","side":"left"},{"sibling":"282afa51266e47629e34d808a360bbb276348bcc5a24bdcc93e83a76e580293e","side":"right"},{"sibling":"05f89b32c00462e60adf95c1fe4579cdc2791b36e8b17573d8f3b5fd5da95a0b","side":"right"},{"sibling":"8ccd9937a2c0d5c04044d07d1557791b7d07bb31eac41a39a675608d44b38f23","side":"right"},{"sibling":"3a5e69cf0803f4c91f3895ed7c9a95748fef240bec4422e167c05300f79f06c0","side":"left"},{"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_737fe55be0c9c5527c12eedf1033bbc1bba107ae1ad5125f676476f105dd359d"}}