{"_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_a2a14a586f3a7b20ddf2d7d75d91538af26eda9ec7b17d7dac40c89725155c6b","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_a2a14a586f3a7b20ddf2d7d75d91538af26eda9ec7b17d7dac40c89725155c6b","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"7a632e0222d704221842fc50986e2cbd6072e7b7e188b3613aee50787c117efb","published":"Wed, 13 May 2026 00:00:00 -0400","receipt_hash":"7a632e0222d704221842fc50986e2cbd6072e7b7e188b3613aee50787c117efb","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":"7a632e0222d704221842fc50986e2cbd6072e7b7e188b3613aee50787c117efb","observed_at":"2026-05-13T04:43:23.245186Z","parent_run_hash":"2a6c2eea51fc0fdbbd1acb92c878f75767034fb102189f6a665cf0ad0e16536e","published":"Wed, 13 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:2605.08747v2 Announce Type: new \nAbstract: Standard embodied evaluations do not independently score whether an agent correctly commits to task completion at episode closure, a capacity we call terminal commitment. Behaviorally distinct failures--never completing the task, completing it but failing to stop, and reporting success without sufficient evidence--collapse into the same benchmark failure. We introduce VIGIL, an evaluation framework that makes terminal commitment independently measurable. Under VIGIL's default protocol, agents observe only egocentric RGB, receive no action-success signals, and must end each episode with a semantic report checked deterministically against hidden world state. This yields two separate scores: world-state completion (W) and benchmark success (B), where B additionally requires a correct terminal report. This decoupling makes four outcome categories distinguishable: missed execution, post-attainment drift, unsupported commitment, and verified s","title":"Done, But Not Sure: Disentangling World Completion from Self-Termination in Embodied Agents","url":"https://arxiv.org/abs/2605.08747","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.08747v2 Announce Type: new \nAbstract: Standard embodied evaluations do not independently score whether an agent correctly commits to task completion at episode closure, a capacity we call terminal commitment. Behaviorally distinct failures--never completing the task, completing it but failing to stop, and reporting success without sufficient evidence--collapse into the same benchmark failure. We introduce VIGIL, an evaluation framework that makes terminal commitment independently measurable. Under VIGIL's default protocol, agents observe only egocentric RGB, receive no action-success signals, and must end each episode with a semantic report checked deterministically against hidden world state. This yields two separate scores: world-state completion (W) and benchmark success (B), where B additionally requires a correct terminal report. This decoupling makes four outcome categories distinguishable: missed execution, post-attainment drift, unsupported commitment, and verified s","title":"Done, But Not Sure: Disentangling World Completion from Self-Termination in Embodied Agents","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-13T04:43:23Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2605.08747"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:901e49f72e09a7a6653399e25cd9e2832f0e380a8fd9c2d60b0adbfd1b43dd82c687a97d1584d227d6d012b0092d7f37eee2b3d7e79677a9aba8c07c6c6dd506","signer":"crovia.substrate","subject":{"observed_at":"2026-05-13T04:43:23Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.08747"},"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":"00ef5cee252bc580d17f4ff98062a81624e917daddb315c75454d74446ddc210","leaf_index":130810,"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":"32e00411af743ccc56580611c3c1c1516cd691049f5d75c298d74a8d0a35d7af","side":"right"},{"sibling":"1fae57f874606323d9b78d11ac239b6a68a5eda70975e0686e4125fbe392e7cd","side":"left"},{"sibling":"be6958c1b1d5b20a33d8399e2ffec03023a8b0980ded3c4d6387358e236e40b4","side":"right"},{"sibling":"f6224e3775d2e855dcdb06795c26a745ba9ed0ba0aa4197f29f63176d121e480","side":"left"},{"sibling":"faa9e662ca50aa2656dd62d1e5c3df1772b0a857ba20e5891611375d6ed10312","side":"left"},{"sibling":"5be85a2ca6238bc8d5b5474e4dd07027ad267209a1aa4ad4b415d197b1b1e18e","side":"left"},{"sibling":"e9c7d26c2fb7cdc9b4ec4b766fced88cdfef0a16254e8d6c349eefe592870c92","side":"left"},{"sibling":"7955fb5c18780780ebd0c129481f6b431d3c7bc9a5684bea51c4f13d54d0fd20","side":"left"},{"sibling":"2cdf0278f203c3924f9abe51f24da8450ad2d85d564d0c7ea68b368e28c336f4","side":"right"},{"sibling":"2170332c55df32c3e98553424d3e6242cef02b9714e5a34c7878ee7365425826","side":"left"},{"sibling":"ae6b2233fdba10d8b237d055d6febc6665ca818dcd31382efc2ab8723586948f","side":"left"},{"sibling":"d32d0a951c1d7e98a8e1951a587d83c97962daeeaa455643bc1d5d53744dc21e","side":"left"},{"sibling":"ffc4d51379293bc3e1910c7d612f409dc610fd9acf8241793fb89f82e1bad4ef","side":"left"},{"sibling":"62ac6554017807bd83187f5a3e5f4f72d6c482616429c2780e9fff1f4845fa04","side":"left"},{"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_a2a14a586f3a7b20ddf2d7d75d91538af26eda9ec7b17d7dac40c89725155c6b"}}