{"_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_d36e54def54c8cca5efb7731b4e39c485020d8f65e8a97c1d7923ec6280e40bd","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_d36e54def54c8cca5efb7731b4e39c485020d8f65e8a97c1d7923ec6280e40bd","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"de96b1f1daac8eaf508edfa76d53e05b4f835985c59ebb98f3bd180fc2966be8","published":"Wed, 27 May 2026 00:00:00 -0400","receipt_hash":"de96b1f1daac8eaf508edfa76d53e05b4f835985c59ebb98f3bd180fc2966be8","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":"de96b1f1daac8eaf508edfa76d53e05b4f835985c59ebb98f3bd180fc2966be8","observed_at":"2026-05-27T04:43:18.926230Z","parent_run_hash":"6f581915edab4326e2b95fed7c82c2ee149e978d6d7c2443439442a927c31dfa","published":"Wed, 27 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:2605.26322v1 Announce Type: new \nAbstract: Theory of Mind (ToM), the ability to infer others' knowledge, intentions, and emotions, is commonly evaluated in large language models (LLMs) using end-point question answering, where performance is judged solely by the final answer to a social reasoning query. This paradigm obscures whether the model actually constructs the underlying mental-state representations required for robust reasoning, particularly in scenarios involving divergent, evolving, or mistaken beliefs. In order to address this research gap, we introduce OmniToM, a benchmark that directly evaluates these representations by requiring explicit modeling of belief structures for all relevant actors within a narrative. These structures are composed of belief propositions: minimal statements of what an actor takes to be true about the world or another actor's mental state, allowing knowledge, intentions, emotions, and false beliefs to be analyzed in a common format. Models ar","title":"OmniToM: Benchmarking Theory of Mind in LLMs via Explicit Belief Modeling","url":"https://arxiv.org/abs/2605.26322","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.26322v1 Announce Type: new \nAbstract: Theory of Mind (ToM), the ability to infer others' knowledge, intentions, and emotions, is commonly evaluated in large language models (LLMs) using end-point question answering, where performance is judged solely by the final answer to a social reasoning query. This paradigm obscures whether the model actually constructs the underlying mental-state representations required for robust reasoning, particularly in scenarios involving divergent, evolving, or mistaken beliefs. In order to address this research gap, we introduce OmniToM, a benchmark that directly evaluates these representations by requiring explicit modeling of belief structures for all relevant actors within a narrative. These structures are composed of belief propositions: minimal statements of what an actor takes to be true about the world or another actor's mental state, allowing knowledge, intentions, emotions, and false beliefs to be analyzed in a common format. Models ar","title":"OmniToM: Benchmarking Theory of Mind in LLMs via Explicit Belief Modeling","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-27T04:43:18Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2605.26322"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:79fd4e46ef4a50d6b4018f2f2c4bd40d841a44be0f0f10aeebffe39e4d71afd282d0f2dbc355868b94d1bebbcee651bd8887f99adc1bbe79c32d9bf5fa84a604","signer":"crovia.substrate","subject":{"observed_at":"2026-05-27T04:43:18Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.26322"},"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":"cd66d328d95186e4c62828d37075fcc999da5b60bbd22b63dc99ed4345a0a1b8","leaf_index":153562,"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":"18a4081fe81d9342f426925dc6fefc8f8ec9ecf12d774c67ec069001f955168e","side":"right"},{"sibling":"a72bc124ddfae366a138ef5dc1efbb0434f6ba59caf7669bf6e0a4c68efc1783","side":"left"},{"sibling":"28bb9cb26b14ddfbbc21fa1d34f3b18f4c9d009d6c9a64829912f562258b6f7e","side":"right"},{"sibling":"a3ce2d57f8613e758e0abbf61e9a2dadc0a587160ec2f512ce9a908f4507218a","side":"left"},{"sibling":"52f77db38f3f5e7b4fccd5cbaf178ed32d00303c05e290c82032e121f5e6435e","side":"left"},{"sibling":"1dda89a8b20f64ca914eae5528c867b75a5c890b30c8fa7ec2e214fc644a68d6","side":"right"},{"sibling":"7e29d20bc58bb43ef3f6cdd944eb9f9025decb57a8f63cc2a0d59200f1d77bef","side":"left"},{"sibling":"dcc303c972d90ed3630aef0a6c2a3edd8c5b29cb2cc61805abaf9ddf885832e7","side":"left"},{"sibling":"94a845c78066cc7024ea52be995e0288a46b35a3430ba66fe7b939b2ddeb255c","side":"left"},{"sibling":"083e753237e7e2c337ddece20acebeca13943581cb5f796fe3e86bdba2ead0ed","side":"left"},{"sibling":"b1f51950a0c51a4dd0cca928c048f5b59153bd52927ad638066a0cf61b44365d","side":"left"},{"sibling":"64f0cee43abfb8301986ce9f1637f992794ecd7ee43659e68b16aea49363c2d0","side":"right"},{"sibling":"d415e6939aee710631f5062799379b547d2c3e3d9a68f263bbb5a693285ab2ca","side":"left"},{"sibling":"374c02d15fb12bd356c179c94766043a982052c6132af8bfc15361b431ffa9f7","side":"right"},{"sibling":"35ca36cee447f0ef7064a25d55f59357c66901e31427729c4c1d8b14aa8adb6c","side":"left"},{"sibling":"990705096edf483cc877217308f731dc42d6f6d99f82880167bbdbbfef32560a","side":"right"},{"sibling":"dd265753d95fa2e2fb4f5768e37fab6f691ccff09ad60d0910ff7dc23bac9226","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":154065,"merkle_root":"4993cfdc172e7880b60667f16789dc2e831ff000f81bb1ecba248e73f1510eca","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260527T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-27T05:37:36Z","sig_algorithm":"ed25519","signature":"76ecf118011540405e96506e6219752df04a2850632f2903dc6f10e08b98bc5a42c8d9e1cb5b7c5bf714479806a403df5f34399afa40c23fbb71493a1f77bd0c","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_d36e54def54c8cca5efb7731b4e39c485020d8f65e8a97c1d7923ec6280e40bd"}}