{"_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_3382e3abe5a43600338a2cafebf0ccb57fd4fa91f461a25dd251decbc55633a9","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_3382e3abe5a43600338a2cafebf0ccb57fd4fa91f461a25dd251decbc55633a9","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"63c0084322f05123f294998c44337b89b3de2e4dba1bf621f94d25968d772815","published":"Wed, 06 May 2026 00:00:00 -0400","receipt_hash":"63c0084322f05123f294998c44337b89b3de2e4dba1bf621f94d25968d772815","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":"63c0084322f05123f294998c44337b89b3de2e4dba1bf621f94d25968d772815","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:2605.02363v1 Announce Type: cross \nAbstract: Deployed language models must produce outputs that are both correct and format-compliant. We study this structured-output reliability gap using two mathematical benchmarks -- GSM8K and MATH -- as a controlled testbed: ground truth is unambiguous and the output contract is strict (JSON with required fields). We evaluate three 7-9B models under five prompting strategies and report output accuracy -- the joint event of mathematical correctness and valid JSON structure -- as the primary metric. A systematic format failure emerges: NAIVE prompting (no system prompt) achieves up to 85% task accuracy on GSM8K but 0% output accuracy across all models and datasets. REFERENCE prompting (a minimal hand-written JSON format prompt) fares little better, yielding 0% output accuracy for two of four models tested. Constrained decoding enforces syntactic validity but incurs 3.6x-8.2x latency overhead and in several settings degrades task performance sub","title":"When Correct Isn't Usable: Improving Structured Output Reliability in Small Language Models","url":"https://arxiv.org/abs/2605.02363","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.02363v1 Announce Type: cross \nAbstract: Deployed language models must produce outputs that are both correct and format-compliant. We study this structured-output reliability gap using two mathematical benchmarks -- GSM8K and MATH -- as a controlled testbed: ground truth is unambiguous and the output contract is strict (JSON with required fields). We evaluate three 7-9B models under five prompting strategies and report output accuracy -- the joint event of mathematical correctness and valid JSON structure -- as the primary metric. A systematic format failure emerges: NAIVE prompting (no system prompt) achieves up to 85% task accuracy on GSM8K but 0% output accuracy across all models and datasets. REFERENCE prompting (a minimal hand-written JSON format prompt) fares little better, yielding 0% output accuracy for two of four models tested. Constrained decoding enforces syntactic validity but incurs 3.6x-8.2x latency overhead and in several settings degrades task performance sub","title":"When Correct Isn't Usable: Improving Structured Output Reliability in Small Language Models","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/2605.02363"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:0b93fc2a0347d85feee3130d96df131afe8e5b29406d68eb52cc99ee75e5966c9439edeabd31fd41f1646764b5361583ab179905f80f4cde36f4a63174dba007","signer":"crovia.substrate","subject":{"observed_at":"2026-05-06T04:43:18Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.02363"},"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":"12a6492e2b827739f7dfd56ee884fbd71b042b0f172479af833b2a2c2d93910d","leaf_index":116348,"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":"3417e5283b53c1e03a461330eca4f5647ec22ae0f85beb4020c45dc35850e56f","side":"right"},{"sibling":"d5ee292e4cb795a39f057e6f4547051b64d3713e1a8e813935b8a47b6c9c3028","side":"right"},{"sibling":"4294424d15a161dd0e26852e7de022a2c0774c6be99b95e7ab015c392f875c53","side":"left"},{"sibling":"0e34465774e07eb77d8f3d23efb9b6bad6b448ce8b2c54746ce423889a6ad215","side":"left"},{"sibling":"bdfa65c58cdde8aff4cfd6b67bf90058225e308074a302c3b5c30dc2a327db87","side":"left"},{"sibling":"1520586bfd4793dc79a128f0850786d392c8af1a7e3e5f9fdeeabdde90ee49b9","side":"left"},{"sibling":"ad3a284c05693695f2eb1381482f2a0de6f97623fdcf5a64fcab04a5e47aac4a","side":"left"},{"sibling":"29a1d68ae3b47209a045f8f53476ebb8528406538f56ab779e7eb4bfc2794b92","side":"right"},{"sibling":"7a43f13f6340a269b939be4b6e73a199a4e8061f0cf9dbb9ba629243174142d3","side":"right"},{"sibling":"c750384c973eaf46aa237cdabe7a75729862dd4101dca10cb8e0626e0ec2d34a","side":"left"},{"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_3382e3abe5a43600338a2cafebf0ccb57fd4fa91f461a25dd251decbc55633a9"}}