{"_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_1d371db4485b9fec870a53e98017d2f8823d24c7b652e9d725743b34fd96c65d","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_1d371db4485b9fec870a53e98017d2f8823d24c7b652e9d725743b34fd96c65d","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"e8c745ea571758d0b0b14e78937e5bf8be6cb67ae2e4a53d7973d4eee5db1bdc","published":"Thu, 28 May 2026 00:00:00 -0400","receipt_hash":"e8c745ea571758d0b0b14e78937e5bf8be6cb67ae2e4a53d7973d4eee5db1bdc","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":"e8c745ea571758d0b0b14e78937e5bf8be6cb67ae2e4a53d7973d4eee5db1bdc","observed_at":"2026-05-28T04:43:38.862500Z","parent_run_hash":"58f8b4a134069e0a15ea3949252489597eb86dd27c9ca3fb15c6fb838ce49ef3","published":"Thu, 28 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:2604.20857v2 Announce Type: replace-cross \nAbstract: Scientific papers use schematic diagrams to communicate methods, workflows, and system structure, yet existing scientific-figure corpora often mix them with plots, screenshots, and photographs and rarely preserve document context. We introduce DiagramBank, a quality-audited dataset of 57,100 schematic diagrams curated from OpenReview-hosted AI/ML venues. Each record links a diagram image to its paper title, abstract, figure caption, in-text figure-reference spans, venue/year metadata, provenance fields, and filtering labels. DiagramBank is a reusable resource for scientific-document understanding, diagram retrieval, corpus analysis, and future benchmark construction. We describe its extraction and cascade-filtering pipeline, release schema, confidence-controlled views, dataset card, and indexing utilities. A manual blind audit of the released cascade-filtered records estimates 93.67% precision, and a separate CLIP threshold ana","title":"DiagramBank: A Quality-Audited Dataset of Scientific Schematic Diagrams with Multi-Level Document Context","url":"https://arxiv.org/abs/2604.20857","vendor":"arxiv_cs_ai"},"summary":"arXiv:2604.20857v2 Announce Type: replace-cross \nAbstract: Scientific papers use schematic diagrams to communicate methods, workflows, and system structure, yet existing scientific-figure corpora often mix them with plots, screenshots, and photographs and rarely preserve document context. We introduce DiagramBank, a quality-audited dataset of 57,100 schematic diagrams curated from OpenReview-hosted AI/ML venues. Each record links a diagram image to its paper title, abstract, figure caption, in-text figure-reference spans, venue/year metadata, provenance fields, and filtering labels. DiagramBank is a reusable resource for scientific-document understanding, diagram retrieval, corpus analysis, and future benchmark construction. We describe its extraction and cascade-filtering pipeline, release schema, confidence-controlled views, dataset card, and indexing utilities. A manual blind audit of the released cascade-filtered records estimates 93.67% precision, and a separate CLIP threshold ana","title":"DiagramBank: A Quality-Audited Dataset of Scientific Schematic Diagrams with Multi-Level Document Context","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-28T04:43:38Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2604.20857"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:8d9386fb548288874997515b45536efc9242bc7e6c48ff371c7b5b67a36d3fa0269eb75457ac4325b41002c0a34c8a3b726a01d101b55667a214cfe628334c09","signer":"crovia.substrate","subject":{"observed_at":"2026-05-28T04:43:38Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2604.20857"},"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":"727b426bd1d542d307911ad15324d9078ba89e27d971c857348f468dd504f321","leaf_index":156089,"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":"1f2b7c6df34d531c984b809f1a85518d03a0d0d8f4d788c0ee41a82239855bc8","side":"left"},{"sibling":"ba14c884e38ea885852e9510f48bc52caab5564fad43aa00fd0dbf7e6996a656","side":"right"},{"sibling":"0bf2c091ebc821fff5e5098948b770fb0c564557f2f6fe7c4a3d704d6272c00f","side":"right"},{"sibling":"65dd127ba9f93a7d59d5d018d567f831839c92254407fc763ef7ec3ac33edcb1","side":"left"},{"sibling":"a665d9b2c45b9366a0eb9b91dd4879b6df482e73d2ebf7ca01d1840b2f1749f2","side":"left"},{"sibling":"2ba878cad6297d84951dcb3b0ea15ec63cfceeceb50d97c8bb449a686b2bf608","side":"left"},{"sibling":"d3f68fd0f5543c1264db6df2dd0afb3f1c81739409d8453f09d6f36acf66cb77","side":"right"},{"sibling":"1edf9a008b98a304748398083d1a13a2c7d3eb3bd83b9b734c4d8e1ed72f9e97","side":"left"},{"sibling":"92ebfba9adaa779ba57179e1e0f933c2128036a29e48cb81e4e64272dbbbb5c0","side":"left"},{"sibling":"f292d3278e493ec60902181b8c0bd5c89c0a1168ef928222fe6161287982f7f0","side":"right"},{"sibling":"2209295faf1a5bf51c97c6fd5a839a8181a4ea44f490420381530f35df7d9b2f","side":"right"},{"sibling":"5784576a15214ea9fc3569e6e1cff1ef443c0b1fc0d036028489088af089de27","side":"right"},{"sibling":"311772ec218efcb2da5a337f9e9f042fe1cc0028643adb0a354787e4ea7911b7","side":"right"},{"sibling":"66331bac84ca0f8983eb09fac7eaf95af234f1b82680b793eabff4ee25caac40","side":"left"},{"sibling":"35ca36cee447f0ef7064a25d55f59357c66901e31427729c4c1d8b14aa8adb6c","side":"left"},{"sibling":"7b6f0bea4291a5e63574dfca9aa0f9756f450c9478c3d07474d39a7ababb51f9","side":"right"},{"sibling":"1d39fe14b21e2ebbfb87e882423b24ee9469eae1e4c77af5b799ac4db9537467","side":"right"},{"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":156177,"merkle_root":"c5705a0243d16afd8b1ebfd731b7aa304079c442c2a7906493c5bbed374c69ec","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260528T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-28T05:37:36Z","sig_algorithm":"ed25519","signature":"f087e13febc8bb6a2e0812610de64cebc65be92915518d9c4b230799c3b161839b04c4eb1b02741f938f35545a76ab76555b04c782bdc2f9a44852d171d65909","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_1d371db4485b9fec870a53e98017d2f8823d24c7b652e9d725743b34fd96c65d"}}