{"_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_bf95d01a207a8d9a7abd9e79d5960ace582ecf551b21196319a2c0b9cbb15a85","bitcoin_anchor":{"bitcoin_attestations":["bitcoin_block_949451"],"calendar_attestations":["https://finney.calendar.eternitywall.com","https://btc.calendar.catallaxy.com","https://alice.btc.calendar.opentimestamps.org","https://bob.btc.calendar.opentimestamps.org"],"ots_url":"/registry/data/substrate/anchors/77fc9c28fae777b81da5b495b3115474df6592dfac590333213d3bdf8b94a9b3.ots","stamped_at":"2026-05-15T03:00:03Z","status":"bitcoin"},"envelope":{"anchors":[{"chain":"crovia.axiom_graph","height":0,"merkle_proof":"spider_vendor_press_v1","root_at_anchor":"spider_vendor_press_v1"}],"axiom_id":"axm_bf95d01a207a8d9a7abd9e79d5960ace582ecf551b21196319a2c0b9cbb15a85","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"35f159590749708a50e14aa624ab7f6bed61774f4649c20f9ee8d7aea11f9029","published":"Mon, 11 May 2026 00:00:00 -0400","receipt_hash":"35f159590749708a50e14aa624ab7f6bed61774f4649c20f9ee8d7aea11f9029","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":"35f159590749708a50e14aa624ab7f6bed61774f4649c20f9ee8d7aea11f9029","observed_at":"2026-05-11T04:43:50.688999Z","parent_run_hash":"8244cc3d66edb4604be5ded19e92c0b47893b228a258432a9c53a5796a870982","published":"Mon, 11 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:2605.06977v1 Announce Type: cross \nAbstract: Reinforcement Learning from Human Feedback (RLHF) has become a cornerstone technique for post-training large language models. While most existing approaches rely on the reverse KL-regularization, recent empirical studies have begun exploring alternative divergences (e.g., forward KL, chi-squared) as regularizers in RLHF. However, a unified theoretical understanding of general $f$-divergence regularization remains under-explored. To fill this gap, this work develops a comprehensive theoretical framework for online RLHF with a general $f$-divergence regularized objective. Rather than treating each possible divergence function individually, we adopt a holistic perspective across the entire function class and propose two algorithms based on distinct sampling principles. The first extends the classical optimism principle with a carefully designed exploration bonus, while the second introduces a new method that exploits the sensitivity of th","title":"$f$-Divergence Regularized RLHF: Two Tales of Sampling and Unified Analyses","url":"https://arxiv.org/abs/2605.06977","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.06977v1 Announce Type: cross \nAbstract: Reinforcement Learning from Human Feedback (RLHF) has become a cornerstone technique for post-training large language models. While most existing approaches rely on the reverse KL-regularization, recent empirical studies have begun exploring alternative divergences (e.g., forward KL, chi-squared) as regularizers in RLHF. However, a unified theoretical understanding of general $f$-divergence regularization remains under-explored. To fill this gap, this work develops a comprehensive theoretical framework for online RLHF with a general $f$-divergence regularized objective. Rather than treating each possible divergence function individually, we adopt a holistic perspective across the entire function class and propose two algorithms based on distinct sampling principles. The first extends the classical optimism principle with a carefully designed exploration bonus, while the second introduces a new method that exploits the sensitivity of th","title":"$f$-Divergence Regularized RLHF: Two Tales of Sampling and Unified Analyses","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-11T04:43:50Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2605.06977"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:641182953b5f64f5615fd811eac81f8da8c9df6bb1a330fcb209a9fd3e7fb6dd4a779466cd64d1308263c05d8d8d641e0604e46d36c9afe9964175506a2c2408","signer":"crovia.substrate","subject":{"observed_at":"2026-05-11T04:43:50Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.06977"},"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":"028b53f62e006b27c9ec77853d029b8a58154ff0d9042201c316f8f2df40acf0","leaf_index":126396,"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":"60c85f1bf2a61531157ce05a107fe94c0723bbcdd5be832df27cc92e3e50dacc","side":"right"},{"sibling":"6c24f772a8e8ae461faf5c594e58a7ba1cfda72d21e5428c478776fd632b83bb","side":"right"},{"sibling":"0238b35ce21eb63278179ca0529d933e0c1bfb169695b0d37fea1a49ebf2915e","side":"left"},{"sibling":"bc3e558c6b83b34ae089079c404ecd9f4f105d62dcadcb4780693328e1c25a06","side":"left"},{"sibling":"0d666621526b39a8ab9955d943431819d8dd7d7440a95041767a34e231e52848","side":"left"},{"sibling":"4390b6d88cb326b09cf69bb35b987818fef2f283209f553fd39885bbc60bef5c","side":"left"},{"sibling":"155d707ea31ac86e33282c61cf9de432c647507cb7e49b48d8091a83db1fa305","side":"right"},{"sibling":"1affc3278ec6295fa1ae074997c4b0457549f963f09f201e1971c53031c8615e","side":"left"},{"sibling":"d2135da61742c6387f57e5dbeb0f84ba6602653b50838e32a22e26e69c963d0c","side":"left"},{"sibling":"fe7cf0b54f5bf9492865fdc338944ef352cdca1a4f9f377e2991ace599a3bb58","side":"right"},{"sibling":"1a581be91236d1f25e8d47fe5efa0e2b51b7f0f6d706ef76a9093067688e5d56","side":"left"},{"sibling":"878cc30108509c9fa1fc52705a216f519d73b647916fcbdfc30a389934d3364b","side":"left"},{"sibling":"ae7dfff36ba07d9f48c36c28a341482ef244ee13cd0efd49aee2bbef2fd65f87","side":"right"},{"sibling":"62ac6554017807bd83187f5a3e5f4f72d6c482616429c2780e9fff1f4845fa04","side":"left"},{"sibling":"3a5e69cf0803f4c91f3895ed7c9a95748fef240bec4422e167c05300f79f06c0","side":"left"},{"sibling":"f2817ab288b5324fe49770372c7a10f33f7cd11005f8d4c0a730316f5229dc98","side":"left"},{"sibling":"725fac972e772ca0dc598810ea1abc70df472f72d2d6ab8a0baee2b80e5d2f4c","side":"left"},{"sibling":"98fc57dfef8873b512edc8340f7181df57302bb96777625e072235c62d7c5895","side":"right"}]},"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":134292,"merkle_root":"77fc9c28fae777b81da5b495b3115474df6592dfac590333213d3bdf8b94a9b3","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260515T023701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-15T02:37:25Z","sig_algorithm":"ed25519","signature":"68107a834b00b24f5d4501e5ec727445311f132a486567ecc4c72a4e6dff24c8c21f2de3105293353ba5fdbe370d032819af6aa70f694e2e39b6af6737507009","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_bf95d01a207a8d9a7abd9e79d5960ace582ecf551b21196319a2c0b9cbb15a85"}}