{"_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_ee48d4cc0fa09627fe682c2eafa6f93cb64faa72de96da48fe162d20b210d616","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_ee48d4cc0fa09627fe682c2eafa6f93cb64faa72de96da48fe162d20b210d616","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"9d15a4ca01f594b0ecbbebfc78743e215ec1d8e0d523db25e2f7526d65e219de","published":"Tue, 26 May 2026 00:00:00 -0400","receipt_hash":"9d15a4ca01f594b0ecbbebfc78743e215ec1d8e0d523db25e2f7526d65e219de","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":"9d15a4ca01f594b0ecbbebfc78743e215ec1d8e0d523db25e2f7526d65e219de","observed_at":"2026-05-26T04:43:39.018238Z","parent_run_hash":"dca8dedd754ad6a1772113d6b97ee4f4ab9a0afbdeb44aaace5ff2d2446b164b","published":"Tue, 26 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:2605.23997v1 Announce Type: cross \nAbstract: Multimodal large language models via reinforcement learning (RL) have demonstrated remarkable capabilities in complex visual reasoning tasks, yet they remain limited in long-horizon multimodal scenarios, often suffering from visual hallucination and logical error. Current methods typically pre-encode high-dimensional visual scenes into discrete textual proxies to facilitate downstream reasoning. As the reasoning chain unfolds, however, the inherent information asymmetry between text and visual scenes tends to erode visual grounding, resulting in misguided reasoning and erroneous outputs. To address this issue, we introduce IVR-R1 (Iterative Visual-grounded Reasoning), a novel RL training framework that facilitates dynamic visual re-alignment that actively rectifies reasoning trajectories to guide policy optimization. Specifically, by leveraging a reward-driven screening mechanism to identify flawed rollouts, IVR-R1 executes a fine-grai","title":"IVR-R1: Refining Trajectories through Iterative Visual-Grounded Reasoning in Reinforcement Learning","url":"https://arxiv.org/abs/2605.23997","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.23997v1 Announce Type: cross \nAbstract: Multimodal large language models via reinforcement learning (RL) have demonstrated remarkable capabilities in complex visual reasoning tasks, yet they remain limited in long-horizon multimodal scenarios, often suffering from visual hallucination and logical error. Current methods typically pre-encode high-dimensional visual scenes into discrete textual proxies to facilitate downstream reasoning. As the reasoning chain unfolds, however, the inherent information asymmetry between text and visual scenes tends to erode visual grounding, resulting in misguided reasoning and erroneous outputs. To address this issue, we introduce IVR-R1 (Iterative Visual-grounded Reasoning), a novel RL training framework that facilitates dynamic visual re-alignment that actively rectifies reasoning trajectories to guide policy optimization. Specifically, by leveraging a reward-driven screening mechanism to identify flawed rollouts, IVR-R1 executes a fine-grai","title":"IVR-R1: Refining Trajectories through Iterative Visual-Grounded Reasoning in Reinforcement Learning","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-26T04:43:39Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2605.23997"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:53302348fff797182e143e94fc6ba3ba5b56a2534123db02f3a93f1d81aad3a53d209a355f0ba0aff2a5dea30a8ff59beba571ed1034f707b91c60912315440d","signer":"crovia.substrate","subject":{"observed_at":"2026-05-26T04:43:39Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.23997"},"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":"cea08f6bafa9058e044dad5177b43a83cab0778f15f9a5bbc212e242022c3b43","leaf_index":151483,"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":"f3e72eb482e89cee82bd762dfa6fec7bf6faf8ec74af0ff48df475d26fee43ce","side":"left"},{"sibling":"b889076949f9b749f3e36c1a8575aff2784ec31bdb2ec6c9f390a13ebbec4159","side":"left"},{"sibling":"c1addfd9cf1849c52783ab06ce52820524602010402aa9a5f19f8060f354d246","side":"right"},{"sibling":"21e9e7d653c419072fead85de97382716d945d0bec94ad7325172065b8195eaf","side":"left"},{"sibling":"ae7317fa192a5ddde9ac8162bdc060b9c5533f9e4806f58a53e4f53ef5a3f696","side":"left"},{"sibling":"78290b7423fc25cb78cad9db3afb82856cdef13b8c0352f9b7c946d0df95a4c4","side":"left"},{"sibling":"e5e0e8d837a1eb5f20af10583ad77cd53168b9effa387448a6f44515c3f60f17","side":"right"},{"sibling":"12607c0dd56c2db51bf46dd95ab0fe795f3f832d068cd7268fed3aeeb8a7cc29","side":"left"},{"sibling":"a808644c9a09dd75253c6c0ba9275dc94a6b6451ad5184ebdafda4a2722b36a5","side":"left"},{"sibling":"fdd22ebd87e5ba37d1153e47753a63818abb25df8fe45dbf735ba5c512c3355b","side":"left"},{"sibling":"cf593c482d17d202b94914915d0c65fb8713053548db64771d0ec5dbb404a07f","side":"left"},{"sibling":"134949308b15cffd6792ee2cf678119af34d69a64764d7c89cd47573c94e1cda","side":"left"},{"sibling":"e20a7391fed5b5f3b675af68344a3f5b050d6701e127b7db010af3941e59dfdb","side":"right"},{"sibling":"e5893793e3591ed7f5e58ca94ffcfba46bb30f69fb1c25d5ba8ef49eb99f9126","side":"right"},{"sibling":"35ca36cee447f0ef7064a25d55f59357c66901e31427729c4c1d8b14aa8adb6c","side":"left"},{"sibling":"e3eecaf996dbe7229a7bb1d234c97aea97a252c5f7c89f8547b6d091db0f0e40","side":"right"},{"sibling":"55bcbd4da3e20d93931f7e58673f10232e81a5b1514d7396cb4b71e8f95788d0","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":152106,"merkle_root":"ac5182c6f3dd09931f2a689df5f4be36df7b55e55bcf106e195671f5ed55fd8f","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260526T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-26T05:37:34Z","sig_algorithm":"ed25519","signature":"a401243fbd2c077d29a623c6ef616c78fbd5c8ce1930afa7af7165b2386e5a8cf15d5094983a1c962e71b27b911a3f3ce09c8cfab9393be2ce5ce8ee6513da06","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_ee48d4cc0fa09627fe682c2eafa6f93cb64faa72de96da48fe162d20b210d616"}}