{"_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_5053c4e8ce22fc6115549a43d681f78eaa8e9fe97269a5d065959040ee2e3a05","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_5053c4e8ce22fc6115549a43d681f78eaa8e9fe97269a5d065959040ee2e3a05","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"8643f4eba95a1e0c8dcb694992942d4a9930151c12679d82d48ac60b4c8fcf31","published":"Thu, 18 Jun 2026 00:00:00 -0400","receipt_hash":"8643f4eba95a1e0c8dcb694992942d4a9930151c12679d82d48ac60b4c8fcf31","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":"8643f4eba95a1e0c8dcb694992942d4a9930151c12679d82d48ac60b4c8fcf31","observed_at":"2026-06-18T04:43:37.219665Z","parent_run_hash":"de79a40f7b3537d88842f7ac355e799c5df2adcb4fc32a4e28096d4bbdf01739","published":"Thu, 18 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:2606.18192v2 Announce Type: replace \nAbstract: As high-quality public web corpora become increasingly exhausted, clean long-context documents have become a scarce and expensive source of training data for large language models (LLMs). Existing long-context corpora are often proprietary and costly to acquire, synthetically generated, or concentrated in narrow domains such as programming. We introduce the Stanford EDGAR Filings Dataset (SEFD), an open reconstruction of SEC filings into layout-faithful MultiMarkdown for financial language modeling and evaluation. SEFD makes audited financial statements, risk disclosures, ownership reports, accounting notes, and market-moving event filings usable as long-context pretraining data and as a basis for financial reasoning, forecasting, compliance, and document understanding. The resulting corpus is token-efficient, model-ready, and has less than 0.1% overlap with Common Crawl-derived corpora. We release SEFD-v1, a 152B-token initial publi","title":"The Stanford EDGAR Filings Dataset: Reconstructing U.S. Corporate and Financial Disclosures into Layout-Faithful and Token-Efficient Pretraining Data","url":"https://arxiv.org/abs/2606.18192","vendor":"arxiv_cs_ai"},"summary":"arXiv:2606.18192v2 Announce Type: replace \nAbstract: As high-quality public web corpora become increasingly exhausted, clean long-context documents have become a scarce and expensive source of training data for large language models (LLMs). Existing long-context corpora are often proprietary and costly to acquire, synthetically generated, or concentrated in narrow domains such as programming. We introduce the Stanford EDGAR Filings Dataset (SEFD), an open reconstruction of SEC filings into layout-faithful MultiMarkdown for financial language modeling and evaluation. SEFD makes audited financial statements, risk disclosures, ownership reports, accounting notes, and market-moving event filings usable as long-context pretraining data and as a basis for financial reasoning, forecasting, compliance, and document understanding. The resulting corpus is token-efficient, model-ready, and has less than 0.1% overlap with Common Crawl-derived corpora. We release SEFD-v1, a 152B-token initial publi","title":"The Stanford EDGAR Filings Dataset: Reconstructing U.S. Corporate and Financial Disclosures into Layout-Faithful and Token-Efficient Pretraining Data","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-18T04:43:37Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2606.18192"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:1baad62b383b23df8920f5f7021917cb7663536e86eb3a83b3d785446dbbc2c15b6b7d8775c934545eaeefc4ecbd8cc3b4bf5b1630e07ba2d8b234e15a3f7b00","signer":"crovia.substrate","subject":{"observed_at":"2026-06-18T04:43:37Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2606.18192"},"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":"2300f6519f358915402475ef27e892198ffdbfc70bc0b1ec496096d7646d7ad5","leaf_index":233454,"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":"6d1deb058bd9d11c5c358fbeeb82d216776118298c4b2035b0e91ecc9e3b15f6","side":"right"},{"sibling":"2cd196e470036589851d07eee4aefb9a58aa1ebbae7fac63d69a48c2521651f5","side":"left"},{"sibling":"b5fd9598be01e56ca85a288db6299e0182fca90b99bd1e54444b1e14b19b4ee2","side":"left"},{"sibling":"00a95e7be5e834dde2934e45832ee29d3fed2fd7c66cb7b8196e8453eb1ee247","side":"left"},{"sibling":"9c5fe820720030bfbb5836637d771871f47ff32080535c15eb3e212aba010eaa","side":"right"},{"sibling":"24c6005cea779de0d384886e9577460fe94470dc3328cf3564609ce6ec386fbc","side":"left"},{"sibling":"8942c0022e58c4389bb72bd28400c56919b0d25c91e8d4c9f09dec03626b6f4b","side":"left"},{"sibling":"b4c26795680b2096400acbdc34159290b2a0589778819fc7e052c7a60bb5c873","side":"left"},{"sibling":"429c2a92a65e6eeaa2eda0a35fdb9e541472a1eace4c69a4d01a618a659a110f","side":"left"},{"sibling":"d97d1ebe04af6ea572f9d4334004d01026acffa3da5be2883c7566513c76e2c0","side":"left"},{"sibling":"571eb56e7ce00fe1f38d0ac4fc56828d01b2cfc1ab9089cde245c0656bee0514","side":"left"},{"sibling":"7ac50038a8ced3aeaf1194a2407a4a09346b0e4399da36ecde4390675a0c4bf1","side":"left"},{"sibling":"8c5e2b48dc31ef0edcd35c3db048235aa78cc48443aa2a8da3aa6e9b5524d2c4","side":"right"},{"sibling":"e616c34dbaf9456d5a6d3e2da82cde8621293c9f6d8a4cf9e441d7fd9cc81579","side":"right"},{"sibling":"94c0c932e61657f5e37fdba43f6ca9eddea8359425a7c1558dabe566911d5304","side":"right"},{"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":234491,"merkle_root":"02576a6980e38bab47864ae2c57b5a5ff21e554e9bdf8f64bdf28155ff1aabec","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260618T143732Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-18T18:33:39Z","sig_algorithm":"ed25519","signature":"b6c708778fc38b7789a2b91156cfe87252a7cd3a1d29121cba11a0c78f8cf104ca3019fc50a962fa5a216bcc4922fc8f3f69c04d1f8332c6dc0d931e1012e502","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_5053c4e8ce22fc6115549a43d681f78eaa8e9fe97269a5d065959040ee2e3a05"}}