{"_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_ebec718c4f8af98ea2b80ef028128640ae1de575e01bdf75f98cbee409afd220","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_ebec718c4f8af98ea2b80ef028128640ae1de575e01bdf75f98cbee409afd220","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"d4e0a7ae41e18a9f10e382b915f1676b261464da8a678e9f147ffa179ca86e8d","published":"Tue, 07 Jul 2026 00:00:00 -0400","receipt_hash":"d4e0a7ae41e18a9f10e382b915f1676b261464da8a678e9f147ffa179ca86e8d","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":"d4e0a7ae41e18a9f10e382b915f1676b261464da8a678e9f147ffa179ca86e8d","observed_at":"2026-07-07T04:43:08.294902Z","parent_run_hash":"fc40a96e5d33ecc82922806c3ad18de4725d7af03964570396c8af4e48fb5bc1","published":"Tue, 07 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:2607.02502v2 Announce Type: replace-cross \nAbstract: On-policy self-distillation (OPSD) has emerged as a practical method for training large language models (LLMs) to reason, where a single model acts as both the teacher and the student with different levels of information access. However, recent studies have found that the teacher's dense token-level supervision, conditioned on privileged information, can lead to overfitting to in-domain patterns, suppress exploration, and hurt cross-domain generalization, while also introducing a more fundamental issue: *privileged information leakage*, where the student encodes answer-dependent shortcuts that are unavailable at test time. We introduce **DemoPSD**, a novel framework that resolves such problems through the idea of *selective adoption of teacher guidance*. Instead of fitting the full teacher distribution, DemoPSD steers the student toward a *reverse-KL barycenter target*, a weighted geometric combination of the teacher and studen","title":"DemoPSD: Disagreement-Modulated Policy Self-Distillation","url":"https://arxiv.org/abs/2607.02502","vendor":"arxiv_cs_ai"},"summary":"arXiv:2607.02502v2 Announce Type: replace-cross \nAbstract: On-policy self-distillation (OPSD) has emerged as a practical method for training large language models (LLMs) to reason, where a single model acts as both the teacher and the student with different levels of information access. However, recent studies have found that the teacher's dense token-level supervision, conditioned on privileged information, can lead to overfitting to in-domain patterns, suppress exploration, and hurt cross-domain generalization, while also introducing a more fundamental issue: *privileged information leakage*, where the student encodes answer-dependent shortcuts that are unavailable at test time. We introduce **DemoPSD**, a novel framework that resolves such problems through the idea of *selective adoption of teacher guidance*. Instead of fitting the full teacher distribution, DemoPSD steers the student toward a *reverse-KL barycenter target*, a weighted geometric combination of the teacher and studen","title":"DemoPSD: Disagreement-Modulated Policy Self-Distillation","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-07T04:43:08Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2607.02502"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:1ddbf8c548853e9b47356961bf56cb1c9ebdd0a4a2a411d8c54ee79664c17d716e94fe871c5d2af7ffa6a46eb61199e3fa026666d618a174da7fb88a1dc1c20b","signer":"crovia.substrate","subject":{"observed_at":"2026-07-07T04:43:08Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2607.02502"},"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":"8c1a003082a7d7eff8f47c51055095834d9c23ed44daed5569d9479fc34b667a","leaf_index":289493,"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":"c4a9451b1aedb5af8b29b703b50deed2cd3b04cc5d1721d8fa0f594251c021d6","side":"left"},{"sibling":"c1db814b6b11f60ca812fbeb4e9e43527084e836ef957686fc947202f9d52547","side":"right"},{"sibling":"559b81688e14417cb3c8e3559409142fcc4c9efdb53056005d6944f577bd6a4d","side":"left"},{"sibling":"a97c54334db251142d17b5d6582ca45fdb4e0a664214e094a8d85b37bbb1fa72","side":"right"},{"sibling":"b1473947883c9015ddb1e086f2ad5467db4f7933033a16b5f8cdcc8c488bf377","side":"left"},{"sibling":"fb389b55154ea0b0297c33636174e44e70ff0fd494114100bf2f0000817d739e","side":"right"},{"sibling":"cfbe804af9ce4b9de800ec832c2500fda63fc4167e375085524b5da509c213ea","side":"left"},{"sibling":"338d253a141554cbceab9dd091d805059d5d74af3605e7c62bd7529bdce399ff","side":"left"},{"sibling":"f6a26c200957df5b056969d2ac473b7e794709bf54454460f447a4af62c6bd58","side":"right"},{"sibling":"c6f2478caecaf381e6b06b04f99195339b88d0db4da957bf2106979ee4a0375c","side":"left"},{"sibling":"19d6dfd29bc47f35fa02e8fe765277ba9cc3e6da5072309f24ebaac5b5f295e3","side":"right"},{"sibling":"8e0ad7889eb2d4b40e5b6c3d8e2eb19d4e202374983f468aa76321823de07a9f","side":"left"},{"sibling":"aae716235efcb893a1f219dbcd5095070d08a497769fc6d50c14976aa26d5750","side":"right"},{"sibling":"a75ab4319e241beeddb1b3f5705febe0422937926c3479923ccfb0b0082fa4e3","side":"left"},{"sibling":"bd04fa605f883bfb2b81510d045b1e85e555a03da3be083619f61384dfe40ff8","side":"left"},{"sibling":"1b72ad8d12164fdf329e7871711be99d8569d140b21f94056e6962da21da9ce1","side":"right"},{"sibling":"5f5109c2bfdcc7a7e70554bba25862e2d7ce86b6b0cd48a72eb66d2eb735f321","side":"right"},{"sibling":"05fd8a05dddb2e7f72bbb5b290ca55c378f1aed709f132277908d9a5f30eb605","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":289613,"merkle_root":"dc428b9d9ba248d4f93f63147bf7c700bf5be7f500cec6c3507b9df6e9401601","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260707T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-07T05:38:15Z","sig_algorithm":"ed25519","signature":"c468b0e183383ab71992be40bda451093e6cd8cd8efb0d26f68e135a804b287c209d12a0f4fdd95c69c835c04b78df8cb1903dee1f53d4730b36f5332a29fe05","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_ebec718c4f8af98ea2b80ef028128640ae1de575e01bdf75f98cbee409afd220"}}