{"_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_e08800e45276b0eebb3c3b236de1c7666a74dd4284ea40d902b2def8f83582c2","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_e08800e45276b0eebb3c3b236de1c7666a74dd4284ea40d902b2def8f83582c2","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"2c5f37b9417a83d52626b82c797df189409514a91d6634968654fd7b1b8612a2","published":"Wed, 13 May 2026 00:00:00 -0400","receipt_hash":"2c5f37b9417a83d52626b82c797df189409514a91d6634968654fd7b1b8612a2","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":"2c5f37b9417a83d52626b82c797df189409514a91d6634968654fd7b1b8612a2","observed_at":"2026-05-13T04:43:23.245186Z","parent_run_hash":"2a6c2eea51fc0fdbbd1acb92c878f75767034fb102189f6a665cf0ad0e16536e","published":"Wed, 13 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:2605.04539v3 Announce Type: replace-cross \nAbstract: Direct Preference Optimization (DPO), the efficient alternative to PPO-based RLHF, falls short on knowledge-intensive generation: standard preference signals from human annotators or LLM judges exhibit a systematic verbosity bias that rewards fluency over logical correctness. This blindspot leaves a logical alignment gap -- SFT models reach NLI entailment of only 0.05-0.22 despite producing fluent text. We propose RLearner-LLM with Hybrid-DPO: an automated preference pipeline that fuses a DeBERTa-v3 NLI signal with a verifier LLM score, removing human annotation while overcoming the \"alignment tax\" of single-signal optimization. Evaluated across five academic domains (Biology, Medicine, Law) with three base architectures (LLaMA-2-13B, Qwen3-8B, Gemma 4 E4B-it), RLearner-LLM yields up to 6x NLI improvement over SFT, with NLI gains in 11 of 15 cells and consistent answer-coverage gains. On Gemma 4 E4B-it (4.5B effective params), ","title":"RLearner-LLM: Balancing Logical Grounding and Fluency in Large Language Models via Hybrid Direct Preference Optimization","url":"https://arxiv.org/abs/2605.04539","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.04539v3 Announce Type: replace-cross \nAbstract: Direct Preference Optimization (DPO), the efficient alternative to PPO-based RLHF, falls short on knowledge-intensive generation: standard preference signals from human annotators or LLM judges exhibit a systematic verbosity bias that rewards fluency over logical correctness. This blindspot leaves a logical alignment gap -- SFT models reach NLI entailment of only 0.05-0.22 despite producing fluent text. We propose RLearner-LLM with Hybrid-DPO: an automated preference pipeline that fuses a DeBERTa-v3 NLI signal with a verifier LLM score, removing human annotation while overcoming the \"alignment tax\" of single-signal optimization. Evaluated across five academic domains (Biology, Medicine, Law) with three base architectures (LLaMA-2-13B, Qwen3-8B, Gemma 4 E4B-it), RLearner-LLM yields up to 6x NLI improvement over SFT, with NLI gains in 11 of 15 cells and consistent answer-coverage gains. On Gemma 4 E4B-it (4.5B effective params), ","title":"RLearner-LLM: Balancing Logical Grounding and Fluency in Large Language Models via Hybrid Direct Preference Optimization","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-13T04:43:23Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2605.04539"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:e98df2e868eaa991ed04e231389d02add5669e15ecd4a794fbc3bdfd6a26f7b1cae8e514298c82a869c201980152981ff6a59ce2a0bf7c9b2b3b98e82c7db207","signer":"crovia.substrate","subject":{"observed_at":"2026-05-13T04:43:23Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.04539"},"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":"a0bdf057d72a96ab8bd453a9d2531e80ed51a842eabce1de047404e20430b4c5","leaf_index":130849,"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":"d40f6438dfd5068a491c8b1b6a806adb564cafedd134bc766c3387edad63e329","side":"left"},{"sibling":"96643b29a6530288c5f7455b63c2d5a54218e314ea616c9235bb0e2d66253645","side":"right"},{"sibling":"775fe380803fcc9dce5e09b4dcac22aa398fe73981413b07d9a3ac74c606b0bb","side":"right"},{"sibling":"11efd5e369ae95731cb70fee02c8d9e7bfc32f4a8618317206f9eb051ea02549","side":"right"},{"sibling":"b73bac955728fbc7a1d40e8346b0a9c8343ba47f137d04c77ce84d2576334136","side":"right"},{"sibling":"ca1001e688dabc9b97e0629a3b469e0fce76daec3bb2590a909be1e05d9c5d00","side":"left"},{"sibling":"8c3518f7d38b276e607f8cbcb7f75921989c30b7fe9b7b7e1b44124372142599","side":"right"},{"sibling":"85f99166b87e29998300b931a3a01c0d1d77304f8efad796211b0ec7150ce694","side":"right"},{"sibling":"15cb4b41b9655a3093d130158e8145d2864f09dffa42ed180b96bc1d7e0f2f1b","side":"left"},{"sibling":"2170332c55df32c3e98553424d3e6242cef02b9714e5a34c7878ee7365425826","side":"left"},{"sibling":"ae6b2233fdba10d8b237d055d6febc6665ca818dcd31382efc2ab8723586948f","side":"left"},{"sibling":"d32d0a951c1d7e98a8e1951a587d83c97962daeeaa455643bc1d5d53744dc21e","side":"left"},{"sibling":"ffc4d51379293bc3e1910c7d612f409dc610fd9acf8241793fb89f82e1bad4ef","side":"left"},{"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_e08800e45276b0eebb3c3b236de1c7666a74dd4284ea40d902b2def8f83582c2"}}