{"_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_eaebf3b9a5c68a22d886a31ff1aa6dc40d3e0b2919967e429f5b82bcb88dff5b","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_eaebf3b9a5c68a22d886a31ff1aa6dc40d3e0b2919967e429f5b82bcb88dff5b","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"4df7f83de1cde92fb52bdb310361afdc64161679202cd711b7a0e74a49202a75","published":"Thu, 11 Jun 2026 00:00:00 -0400","receipt_hash":"4df7f83de1cde92fb52bdb310361afdc64161679202cd711b7a0e74a49202a75","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":"4df7f83de1cde92fb52bdb310361afdc64161679202cd711b7a0e74a49202a75","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:2606.11559v1 Announce Type: new \nAbstract: Reinforcement learning typically improves multi-turn agent capabilities through the terminal outcome of the trajectories, which makes it difficult to determine credit assignments for each intermediate turns. Recent on-policy self-distillation methods offer a promising alternative by converting privileged feedback into dense token-level supervision through a self-teacher. Our study is motivated by the unexpected performance degradation observed when naively extending this paradigm to multi-turn settings, which we attribute to a lack of alignment between privileged feedback, such as successful trajectories or terminal outcomes, and the student's current decision context. We introduce HERO, a hindsight-enhanced self-distillation framework that uses next environment observations as locally aligned feedback. After each rollout, HERO reflects on the completed interaction to convert each observation into a compact turn-level diagnosis, that cap","title":"HERO: Hindsight-Enhanced Reflection from Environment Observations for Agentic Self-Distillation","url":"https://arxiv.org/abs/2606.11559","vendor":"arxiv_cs_ai"},"summary":"arXiv:2606.11559v1 Announce Type: new \nAbstract: Reinforcement learning typically improves multi-turn agent capabilities through the terminal outcome of the trajectories, which makes it difficult to determine credit assignments for each intermediate turns. Recent on-policy self-distillation methods offer a promising alternative by converting privileged feedback into dense token-level supervision through a self-teacher. Our study is motivated by the unexpected performance degradation observed when naively extending this paradigm to multi-turn settings, which we attribute to a lack of alignment between privileged feedback, such as successful trajectories or terminal outcomes, and the student's current decision context. We introduce HERO, a hindsight-enhanced self-distillation framework that uses next environment observations as locally aligned feedback. After each rollout, HERO reflects on the completed interaction to convert each observation into a compact turn-level diagnosis, that cap","title":"HERO: Hindsight-Enhanced Reflection from Environment Observations for Agentic Self-Distillation","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/2606.11559"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:0004dcc35fa17de7000852b0c7cb76d9abbb79e4bad03b4f4dc757acde086b72b3d647e63e868f9bf1073e047ef2a286861495461d9bb1c6952828a3dd9b7304","signer":"crovia.substrate","subject":{"observed_at":"2026-06-11T04:43:37Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2606.11559"},"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":"44a946e8d147d235f79c6447af3daab2ee3091fb7b935dba6fc3c0a3971ce7c3","leaf_index":227334,"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":"75332a2f3ec85e20c83b5de522bf9711efa3b32255f8734df05e79ae8f88df99","side":"right"},{"sibling":"18f0b4308ea179502adc4868c7e444474c593f3e1ff85c39a0d05a8c8eb1f26d","side":"left"},{"sibling":"4200d3f54790ee8f6f7ef1ca82af4f952774f7439a4576333be02ccf70984d93","side":"left"},{"sibling":"f1a332d3f77229bd4171c99e88019794d985dd3adb588da296cae0a5318565b5","side":"right"},{"sibling":"01c61f70d74c0bc0936d3f32814f6628cb17cd1e57ab800df12350d1551ec9ec","side":"right"},{"sibling":"b2b753a82c989b78f14b304926149833480952d0604588016e1128cd65a65961","side":"right"},{"sibling":"98a196a185b8283495ee2af791dddabecad12b9667f3282e20e2ada5f5abd314","side":"right"},{"sibling":"a6d2c01df24bdf78d7a3a20470793a1585a197c5d8c3f07fc4049ed07458246d","side":"right"},{"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_eaebf3b9a5c68a22d886a31ff1aa6dc40d3e0b2919967e429f5b82bcb88dff5b"}}