{"_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_2509f4f3cece8f684bfa94b4a5c7fc7f24fdc0e4796ec4df72f3aa4d20723cdc","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_2509f4f3cece8f684bfa94b4a5c7fc7f24fdc0e4796ec4df72f3aa4d20723cdc","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"2e025e4509dc34aac9f307050823c5191eb2dd9f4fa7e8f4f007d420b19cdff9","published":"Tue, 09 Jun 2026 00:00:00 -0400","receipt_hash":"2e025e4509dc34aac9f307050823c5191eb2dd9f4fa7e8f4f007d420b19cdff9","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":"2e025e4509dc34aac9f307050823c5191eb2dd9f4fa7e8f4f007d420b19cdff9","observed_at":"2026-06-09T04:43:45.619596Z","parent_run_hash":"f2344865fd128464efd1bacba326b5a7ccea707694b8c5650dd51ae8c46ac8a1","published":"Tue, 09 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:2606.08976v1 Announce Type: new \nAbstract: LLM-based RTL generation and reasoning is a promising direction for hardware design automation. High-quality benchmarks are critical infrastructure for tracking progress in this direction. However, existing RTL benchmarks face inherent limitations in both scale and task scope. The designs they cover are typically small and simple, and the tasks focus almost entirely on specification-to-RTL generation. Frontier models' performance already saturates on the existing benchmarks. Scaling these benchmarks up is fundamentally difficult because aligned labels are required for benchmarking, such as specifications and testbenches. Such aligned high-quality data are rarely available for real-world designs. We introduce RTL-BenchLS, a large-scale benchmark addressing both limitations above. It contains over 10,000 formally verified Verilog designs, covering substantially larger and more complex designs than existing benchmarks. Beyond specification-","title":"RTL-BenchLS: A Large-Scale Benchmark for RTL Reasoning and Generation with Large Language Models","url":"https://arxiv.org/abs/2606.08976","vendor":"arxiv_cs_ai"},"summary":"arXiv:2606.08976v1 Announce Type: new \nAbstract: LLM-based RTL generation and reasoning is a promising direction for hardware design automation. High-quality benchmarks are critical infrastructure for tracking progress in this direction. However, existing RTL benchmarks face inherent limitations in both scale and task scope. The designs they cover are typically small and simple, and the tasks focus almost entirely on specification-to-RTL generation. Frontier models' performance already saturates on the existing benchmarks. Scaling these benchmarks up is fundamentally difficult because aligned labels are required for benchmarking, such as specifications and testbenches. Such aligned high-quality data are rarely available for real-world designs. We introduce RTL-BenchLS, a large-scale benchmark addressing both limitations above. It contains over 10,000 formally verified Verilog designs, covering substantially larger and more complex designs than existing benchmarks. Beyond specification-","title":"RTL-BenchLS: A Large-Scale Benchmark for RTL Reasoning and Generation with Large Language Models","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-09T04:43:45Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2606.08976"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:483b68fb98859ec51ed9bdc297309b077b791b0c736014034e6dd23c415fd4ca52f9e9acb85d522ae54cc00cb05d3d9b8eb33efa3a8472a738f3fdeb30f6e401","signer":"crovia.substrate","subject":{"observed_at":"2026-06-09T04:43:45Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2606.08976"},"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":"74910480a0ceb94c0c27ce4065c8d86f464b0627465dca4092c879d215240b55","leaf_index":224025,"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":"3eaae54695e927d93af8b8e2434b5a0cc5f71397da3d3906930040ee0b19d08a","side":"left"},{"sibling":"b19bcf6db55a2b9c663790bc8e4eb1b61c20e198f9adf122a2d1a39b41fa2cfa","side":"right"},{"sibling":"44310be3a6f541e02fa3d22de44b97326eee4762cf8ab42a0dfdad3d1fc15393","side":"right"},{"sibling":"9c1b5121cd6a07cab8c24e0e5e1ebc6f85e81856e832c5cbee755c103968917b","side":"left"},{"sibling":"b2f2267c38acff0dafecece1e8a521e42805b6ce05197de91d3b957e470879b0","side":"left"},{"sibling":"7639b7b8450a9c35a0488bbe3a9d302d9d58b4404f478bd3f1362ff40c9706c1","side":"right"},{"sibling":"7d319425db25fb3c3f1998c36dfe19db51428e3c4629360b23d76d78a49611fd","side":"right"},{"sibling":"e9dc257685cfad8bb0dae07b2db5d353319e50598398bbbe195a915649748f95","side":"right"},{"sibling":"dd5d61819b080d26c4380e26887a8eb889d51e2c022f796a39855defe6f68d95","side":"left"},{"sibling":"e8dcea313a54920d83e4f72d5a4223f986c719f264241d171c4712efaaf1fc54","side":"left"},{"sibling":"5480e1ea31f4744f9bd7c4261771fe51f2cdb01e705cc17320bfc202d935ca12","side":"right"},{"sibling":"24fdc29d461691aedb6fa920758206b5bb43851f477ef7a04c34aaed84b8971b","side":"left"},{"sibling":"036922da4e1e2c46d948f070454bfad299b7406fb00735ea9d8bd1e687f5f445","side":"right"},{"sibling":"533d82482604463aa4a281b9d8b85917b383b7c5f924b2b494039524c55e8797","side":"left"},{"sibling":"b2590791b920ca2a4ed39de126d2c0b1a10d9e7e62f572f12425f214e767b6e1","side":"left"},{"sibling":"87c6b850dfec08ac35a693d9db3a3315250a68adb1cfab9b1015f212b63b15bd","side":"right"},{"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":224761,"merkle_root":"e9f7b49b652e869ab97ffba9c5a31356b2d0e3dc5d00bb28944adf737c46b1e7","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260609T103805Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-09T14:15:34Z","sig_algorithm":"ed25519","signature":"8ad8076fb12c8e486ae1d1559a9a7ba8e2ee996a9ad3d8ba7bcdbdbd88ab3a15bcb429707aca6d3e9d8b97e2ba755b3dcc77b1abb6601ccb829842719a6fb30d","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_2509f4f3cece8f684bfa94b4a5c7fc7f24fdc0e4796ec4df72f3aa4d20723cdc"}}