{"_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_cc4471ddabf3787dc077774071e61268197ae0e230edc7adbe7d82d1c6804ba3","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_cc4471ddabf3787dc077774071e61268197ae0e230edc7adbe7d82d1c6804ba3","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"dfe322162c019f73d1e2be6eb110db0f77d0eb961d9ed2dad7366d119f614238","published":"Tue, 19 May 2026 00:00:00 -0400","receipt_hash":"dfe322162c019f73d1e2be6eb110db0f77d0eb961d9ed2dad7366d119f614238","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":"dfe322162c019f73d1e2be6eb110db0f77d0eb961d9ed2dad7366d119f614238","observed_at":"2026-05-19T04:43:36.782648Z","parent_run_hash":"fefa4c726316a95c5dda9fc1ca07a38a811cf7ffa9825b2f09b365abacd9b32d","published":"Tue, 19 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:2605.16790v1 Announce Type: cross \nAbstract: Tool use enables large language models to solve complex tasks through sequences of API calls, yet existing reinforcement learning approaches fail to scale to multi-step composition settings. Outcome-based rewards provide only sparse feedback, while trajectory-supervised rewards depend on annotated reference solutions, penalizing valid alternatives and limiting scalability. We propose TIER: Trajectory-Invariant Execution Rewards, a reward framework that derives supervision directly from function schemas and runtime execution, rather than from reference trajectories. The reward decomposes into format validity, schema adherence, execution success, and answer correctness, providing dense, interpretable sequence-level feedback derived from fine-grained verification of individual steps of tool use. This design allows any valid execution path to receive credit, naturally supporting multiple solution strategies and adapting to evolving tool in","title":"TIER: Trajectory-Invariant Execution Rewards for Multi-Step Tool Composition","url":"https://arxiv.org/abs/2605.16790","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.16790v1 Announce Type: cross \nAbstract: Tool use enables large language models to solve complex tasks through sequences of API calls, yet existing reinforcement learning approaches fail to scale to multi-step composition settings. Outcome-based rewards provide only sparse feedback, while trajectory-supervised rewards depend on annotated reference solutions, penalizing valid alternatives and limiting scalability. We propose TIER: Trajectory-Invariant Execution Rewards, a reward framework that derives supervision directly from function schemas and runtime execution, rather than from reference trajectories. The reward decomposes into format validity, schema adherence, execution success, and answer correctness, providing dense, interpretable sequence-level feedback derived from fine-grained verification of individual steps of tool use. This design allows any valid execution path to receive credit, naturally supporting multiple solution strategies and adapting to evolving tool in","title":"TIER: Trajectory-Invariant Execution Rewards for Multi-Step Tool Composition","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-19T04:43:36Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2605.16790"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:0a28f5a19a52d3c41e672f78f9e2321fbae2c4ecadef2ac96b82a1f98a25364c3cda447e27685bbb612f9ee876e39940c1b05bb6b17b54098984989225000507","signer":"crovia.substrate","subject":{"observed_at":"2026-05-19T04:43:36Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.16790"},"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":"c6296160fd8fe4ab34caa32876e7e5eba7cb723bafd697f0492f0146a9b87fc1","leaf_index":142643,"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":"bb5ba04f36ad5837367c21ead8c726f5905a760465262eef76197d0f95312338","side":"left"},{"sibling":"b6e7ec43f0496535a55f6e7c49ac931e34388c8f5c81eb842708ac1e1d903610","side":"left"},{"sibling":"97ebb3740f7b6f4d962ec3494f6e688213d080769ffdb0200a5e9cd55884d294","side":"right"},{"sibling":"77197695a9fcc0879ece8881c9e6663756ddb8a108bb115cb4de2fba5a26aeee","side":"right"},{"sibling":"05cbd2d882d5b173de653577c32a81db3c3fd0835c30eb055d6dac5a138bbb60","side":"left"},{"sibling":"d4a39fb3bfea767fa296ac8a64d492f56f7e036300aa1b1e95b9875173f523f8","side":"left"},{"sibling":"d1699c63b2a3c9d160a7dad72120a688f97fd9b9cc8ea79fe409f9e6aaaa5bbc","side":"right"},{"sibling":"0681a3895a908b2cd98c077a0abe5cdd8542f0ecb3a6294a35366c915b2e2e3e","side":"right"},{"sibling":"f1c796d3bd453570426dcee9ab20072f19762202f84b7993afba2c7c0ee9ec3b","side":"left"},{"sibling":"2e0ce989d789c88e796991ef014ce7e4e1f96c0d4ede9da8d31afcf5ba6a8f46","side":"right"},{"sibling":"202f1bead178ef3785968d50d3d188264a95192a077654c331612e04a34cbfbe","side":"left"},{"sibling":"72249c8c8b068386e35d16f4bd0bbeb9ba820ca217ef0f0d28396c9fe493f5f0","side":"left"},{"sibling":"ea64599340f7ffdf17ad0cbc1d9401ef8870a347e3847bdc106d06b1673df09c","side":"right"},{"sibling":"8f4c0fbe56b6c010fbb8c782ebcd478079bb3f991d8704e2534209a075d9163c","side":"left"},{"sibling":"4db1f363729507e27a60851cf6ed334d7b9acdef194ed7d419aba4d2bd367a4a","side":"right"},{"sibling":"a86ee18c45e7fcc408b6007eaece05aa75b2d9ae30252e9e878462b4dffbef7b","side":"right"},{"sibling":"1d18e7663d43ccff0122ecc7ee12645bb16afb607b218e81b1ea2408f863cb78","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":143302,"merkle_root":"999156d40a7c61d9ddd52b7338f3cbda3e68f53bace070c7b616ea194e23b123","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260519T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-19T05:37:30Z","sig_algorithm":"ed25519","signature":"b1a252cc66ff32bed1d10dd88a6b2a200e3856d3dbcfcc4ee55e02e00f3d548e854ed9c544704b222bd5d315492c4a935ba2d90d727c585a67899b0ad602fc05","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_cc4471ddabf3787dc077774071e61268197ae0e230edc7adbe7d82d1c6804ba3"}}