{"_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_75abe6831d5729360e1b1b6e7cf5a0690280f7a3317d800d091294db7cfcd3e3","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_75abe6831d5729360e1b1b6e7cf5a0690280f7a3317d800d091294db7cfcd3e3","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"82256aa7e87f15166d8f136fa6a6c7320a702a23cd37ac362be5b32bd3c9db8c","published":"Thu, 11 Jun 2026 00:00:00 -0400","receipt_hash":"82256aa7e87f15166d8f136fa6a6c7320a702a23cd37ac362be5b32bd3c9db8c","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":"82256aa7e87f15166d8f136fa6a6c7320a702a23cd37ac362be5b32bd3c9db8c","observed_at":"2026-06-11T04:43:37.662146Z","parent_run_hash":"5267801b61ae0d882196b5f37208a9a1633905a64ca7d933f1fa5075cd861491","published":"Thu, 11 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:2606.12384v1 Announce Type: cross \nAbstract: Recent advances in agentic Reinforcement Learning (RL) have substantially improved the multi-turn tool-use capabilities of large language model agents. However, most existing methods assign credit over coarse heuristic units, such as tool-call boundaries or fixed workflows, making it difficult to identify which intermediate decisions influence downstream outcomes. In this work, we study agentic RL from two perspectives: \\textit{where to branch and how to assign credit after branching}. Our pilot analysis shows that influential decision points are broadly distributed throughout the generated sequence rather than concentrated at tool calls, while token entropy alone does not reliably reflect their impact on final outcomes. Motivated by these observations, we propose \\textbf{Agentic Procedural Policy Optimization (APPO)}, which shifts branching and credit assignment from coarse interaction units to fine-grained decision points in the sequ","title":"APPO: Agentic Procedural Policy Optimization","url":"https://arxiv.org/abs/2606.12384","vendor":"arxiv_cs_ai"},"summary":"arXiv:2606.12384v1 Announce Type: cross \nAbstract: Recent advances in agentic Reinforcement Learning (RL) have substantially improved the multi-turn tool-use capabilities of large language model agents. However, most existing methods assign credit over coarse heuristic units, such as tool-call boundaries or fixed workflows, making it difficult to identify which intermediate decisions influence downstream outcomes. In this work, we study agentic RL from two perspectives: \\textit{where to branch and how to assign credit after branching}. Our pilot analysis shows that influential decision points are broadly distributed throughout the generated sequence rather than concentrated at tool calls, while token entropy alone does not reliably reflect their impact on final outcomes. Motivated by these observations, we propose \\textbf{Agentic Procedural Policy Optimization (APPO)}, which shifts branching and credit assignment from coarse interaction units to fine-grained decision points in the sequ","title":"APPO: Agentic Procedural Policy Optimization","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-11T04:43:37Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2606.12384"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:27d04e9ee8a1c127e4900631693a394e345ec432c6133e82cd020521dc3b8abf28bb909c3068fcd63427b4a054d6ce7062d67b986538eaa4b2c416735ff2970a","signer":"crovia.substrate","subject":{"observed_at":"2026-06-11T04:43:37Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2606.12384"},"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":"b9b1d80a12c5aeabb9fc5f5edc88d4ab0d6d3511d6149afc69ad0337df90d22c","leaf_index":227515,"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":"ef3220f9caeb168e5df459687c1b90e051388081599058be2f4ff1b8281df1ca","side":"left"},{"sibling":"b9a2e373cb560d820ee87f29d009282837bc491e4a9f426a2eb69c99afd7cbbd","side":"left"},{"sibling":"f2de4b2ca098554810bf1d3690a19c92672b6b4687aeb9673942e2409ccde46c","side":"right"},{"sibling":"62d42f56a9828b5e9fc77bc524ba2c7079dd23257469727426825e31e26f80c2","side":"left"},{"sibling":"3ac11b31c81b9785879a9f3911daf3e6d1a9033d0d17206182dfa884df46184a","side":"left"},{"sibling":"0bf236242aee339cdd7427a1d830278fd617cca4d6ae27d61b4ad03232e13fb5","side":"left"},{"sibling":"be2a37bcb238a826acf45455e518d42d73f440ba96d52faa79e4bc8b1793ea0f","side":"right"},{"sibling":"e5516844190de8c773a2f33a88fdd935790a83aa93beef323f043368177406bc","side":"left"},{"sibling":"2cfac7f042209c8533c6031bddc4a83bc156e0595f1b28efefbda208904f338a","side":"right"},{"sibling":"04e399458c5b36988cae0bf1c6dbe1b01349003b15cb5aa43f95c55acffe4ec3","side":"right"},{"sibling":"1383228337d54218bd8e5563aebb0b0dfe15c5269e3d5138e64c261d6130a88b","side":"right"},{"sibling":"57cb49c192550231071a0bf53a0821da2f79c585ec6c8d0fc76cebd62ccd78b2","side":"left"},{"sibling":"cdb58f86163046d3b15f857b03372ec75e1ad9ea4548e086793d528b9eed364d","side":"left"},{"sibling":"533d82482604463aa4a281b9d8b85917b383b7c5f924b2b494039524c55e8797","side":"left"},{"sibling":"b2590791b920ca2a4ed39de126d2c0b1a10d9e7e62f572f12425f214e767b6e1","side":"left"},{"sibling":"6cea4964f32722eb370847c2f7c9d6a9f0622c239538b07e6815a59d6fd8d49c","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":228173,"merkle_root":"7e416202c0bfd759bd2eea4236713b403993d99793fe8badb5065040080bece3","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260611T143708Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-11T21:59:35Z","sig_algorithm":"ed25519","signature":"231c80024bc3982dd493c45b31af95097e97aabc6d712a4e5bad7d0cbdd3c08e01ff395b0f8e72754bac97016e0cd0eed88b8a13cb71edbbcb9b6d72c10a7b03","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_75abe6831d5729360e1b1b6e7cf5a0690280f7a3317d800d091294db7cfcd3e3"}}