{"_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_794aad7e5057b9da545aec2aafb0b5d9a2860117697be2be4a46c12ac751e7c6","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_794aad7e5057b9da545aec2aafb0b5d9a2860117697be2be4a46c12ac751e7c6","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"099004998b83c64743fc276ba215f980d6bf028ac9ebd0ec35a02d9fff0254cc","published":"Wed, 15 Jul 2026 00:00:00 -0400","receipt_hash":"099004998b83c64743fc276ba215f980d6bf028ac9ebd0ec35a02d9fff0254cc","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":"099004998b83c64743fc276ba215f980d6bf028ac9ebd0ec35a02d9fff0254cc","observed_at":"2026-07-15T04:44:03.592429Z","parent_run_hash":"d49a6cf532e74153266f377b7760fc948d950d80ed41fc3e3eb82b58f5597ead","published":"Wed, 15 Jul 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:2606.12634v3 Announce Type: replace-cross \nAbstract: Long-horizon tool-use reinforcement learning learns from outcome verification, but trajectory-level advantages are broadcast over reasoning, API, and answer tokens. Direct self-distillation can supply a denser signal, but in our experiments it can also destroy tool use by rehearsing teacher behavior without identifying which actions the verifier rewards. We introduce Sibling-Guided Credit Distillation (SGCD), which uses distillation for bounded credit weighting rather than as a competing actor loss. Dynamic sampling produces mixed successful and failed sibling rollouts; an external LLM summarizes their contrast into a training-only credit reference; and detached teacher/student divergence reshapes GRPO token advantages. The deployed student receives only the clean task prompt. Across AppWorld and tau^3-airline, SGCD reports higher held-out point estimates than GRPO-family comparators: AppWorld TGC improves from 42.9 to 45.6 on ","title":"Keep Policy Gradient in Charge: Sibling-Guided Credit Distillation for Long-Horizon Tool-Use Agents","url":"https://arxiv.org/abs/2606.12634","vendor":"arxiv_cs_ai"},"summary":"arXiv:2606.12634v3 Announce Type: replace-cross \nAbstract: Long-horizon tool-use reinforcement learning learns from outcome verification, but trajectory-level advantages are broadcast over reasoning, API, and answer tokens. Direct self-distillation can supply a denser signal, but in our experiments it can also destroy tool use by rehearsing teacher behavior without identifying which actions the verifier rewards. We introduce Sibling-Guided Credit Distillation (SGCD), which uses distillation for bounded credit weighting rather than as a competing actor loss. Dynamic sampling produces mixed successful and failed sibling rollouts; an external LLM summarizes their contrast into a training-only credit reference; and detached teacher/student divergence reshapes GRPO token advantages. The deployed student receives only the clean task prompt. Across AppWorld and tau^3-airline, SGCD reports higher held-out point estimates than GRPO-family comparators: AppWorld TGC improves from 42.9 to 45.6 on ","title":"Keep Policy Gradient in Charge: Sibling-Guided Credit Distillation for Long-Horizon Tool-Use Agents","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-15T04:44:03Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2606.12634"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:dac49104e3e35bec070a8ffb79d4a9167ca6d6e31a40a2f4338abb876a8eb7525e36647e124ef52916140bc6a9f79c9a5ad7761ba2ae0baa32dd22c13f006b00","signer":"crovia.substrate","subject":{"observed_at":"2026-07-15T04:44:03Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2606.12634"},"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":"fa4a0cdf0ec22997bd25cf58eea0d22b62402e4f383bc311315b269bf384d8f6","leaf_index":316585,"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":"36ba99eb81604e091d448983e8f1fcfb976b4a1bf9b15d8748994b5b065a3329","side":"left"},{"sibling":"dcf08c9a48b0008f79c63e52be9732dd3dee8439e77afdf51fe1e888f95f4276","side":"right"},{"sibling":"fa12295fc3e1eb2b6541a7bc22fd18e3deed9c6ffdaf3d5ee351a64cf2f976e4","side":"right"},{"sibling":"42094359e953e1dc2bb25d8488eac5a03f9f6785acc377d56b7ee85b24fa8ffa","side":"left"},{"sibling":"8a5d8846572d862e34028b57089bd7381aeabdaccd632e8e4a8e118f5129fa7d","side":"right"},{"sibling":"fc5fe414d03440bed7aa3c8fdd956b2cb0a844eb7ddc3f58126f36dc3900245e","side":"left"},{"sibling":"33661ca420513ca9092e711309245c4602733fe2714484fedf48cb9c8664fd0e","side":"right"},{"sibling":"af39fefe9ccf50e1288b21fab97d8bc62d8495b7dbe9a55a9ffa363740e34285","side":"left"},{"sibling":"1c7f1bf97993e3a126824f8350788b168c4c13264fb03a73b3ede312035d3527","side":"right"},{"sibling":"84a7590e6b24dd07ed46597f19deb75d9ad247b4227b17f30857ec7cc0fc5c21","side":"right"},{"sibling":"c8d3d8cb0183b912107f9781ad2a1b6c0c9424906c5907c09deeb5bea9d7b571","side":"left"},{"sibling":"0cb62c0ada57a2406a6bcb100889d3e8b29a15efeed07adaff5bb90a5e80612a","side":"right"},{"sibling":"0b69289b25462ddd6166f6f49004cfc8ada0ab4f10adafe188347817bdd46e37","side":"left"},{"sibling":"1418b281cd985b5ed411ef25f2017a1826cc14919b6fad3934e6ceeec693699b","side":"right"},{"sibling":"f302542c38ba7c3aab7c9280dd60259ecec777dca6e6f71b6f0729b0b8791b72","side":"left"},{"sibling":"d8b9143917b539c543cf4448cec00131f8b807bd8004979c54ebe09798748c66","side":"left"},{"sibling":"abe4a8c706e530484d1e96a8988cb09eab85928b2050985500ab289753fe3eec","side":"right"},{"sibling":"f436dccf82aa2c1eb7bfa3eb84316e116aaf64dc55cd9592597118f6cb0648f6","side":"right"},{"sibling":"1cecb7f447febd025aac272837c80de218aecc6485d2395a509b2a1f1b9c746e","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":316730,"merkle_root":"a8e6e5be81ea6f5b5f2227422459bf39455fe9f0b6602b4d1ce6977dbfd78bc7","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260715T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-15T05:38:24Z","sig_algorithm":"ed25519","signature":"df1678d268b5a07413e2ca6e748c3f40b6cfedea930a18d843489a4ab513da791bf0a886caab1b918d0989f8ebaaf3d0035ca2aa777913b1ad29979f1deb9a0c","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_794aad7e5057b9da545aec2aafb0b5d9a2860117697be2be4a46c12ac751e7c6"}}