{"_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_02753951eb00249990c8bd69128667cbb3ed475b4ff740e7cb3e10f66289bd54","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_02753951eb00249990c8bd69128667cbb3ed475b4ff740e7cb3e10f66289bd54","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"dc20d9a44e542f85d248d6e0400ef5b323f202781bcd319dde8b3dae6bbf4116","published":"Thu, 07 May 2026 00:00:00 -0400","receipt_hash":"dc20d9a44e542f85d248d6e0400ef5b323f202781bcd319dde8b3dae6bbf4116","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":"dc20d9a44e542f85d248d6e0400ef5b323f202781bcd319dde8b3dae6bbf4116","observed_at":"2026-05-07T04:43:30.601849Z","parent_run_hash":"b20b3beeadde500bb99eda3b869d50b00c5259b2c78c650d83e786ac81b85801","published":"Thu, 07 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:2512.04277v3 Announce Type: replace-cross \nAbstract: Post-training with reinforcement learning (RL) typically optimizes a single scalar objective and ignores structure in how solutions are produced. We ask whether a scalar hint toward a canonical solver ordering, used only during RL post-training, improves performance even when fine-tuned on randomized solution sequences. On Zebra puzzles, we fine-tune a Transformer on randomized solution orders, then post-train it with Group Relative Policy Optimization (GRPO) using two rewards: a sparse task reward that is 1 only when the puzzle is fully solved, and an ordering reward that increases when the model's emission order aligns with the canonical solver order. To compare signals cleanly, we combine them via fixed mixtures and use a simple bootstrapped scaling to equalize component magnitudes at initialization. Mixed rewards generally outperform task-only optimization, suggesting that coarse ordering signals can steer RL post-training ","title":"Bootstrapped Mixed Rewards for RL Post-Training: Injecting Canonical Action Order","url":"https://arxiv.org/abs/2512.04277","vendor":"arxiv_cs_ai"},"summary":"arXiv:2512.04277v3 Announce Type: replace-cross \nAbstract: Post-training with reinforcement learning (RL) typically optimizes a single scalar objective and ignores structure in how solutions are produced. We ask whether a scalar hint toward a canonical solver ordering, used only during RL post-training, improves performance even when fine-tuned on randomized solution sequences. On Zebra puzzles, we fine-tune a Transformer on randomized solution orders, then post-train it with Group Relative Policy Optimization (GRPO) using two rewards: a sparse task reward that is 1 only when the puzzle is fully solved, and an ordering reward that increases when the model's emission order aligns with the canonical solver order. To compare signals cleanly, we combine them via fixed mixtures and use a simple bootstrapped scaling to equalize component magnitudes at initialization. Mixed rewards generally outperform task-only optimization, suggesting that coarse ordering signals can steer RL post-training ","title":"Bootstrapped Mixed Rewards for RL Post-Training: Injecting Canonical Action Order","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-07T04:43:30Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2512.04277"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:72bf94139caaf0a3c93c962b76adb2716fcad8f6011570c7809eb1a9edad463b5bce7e73f63257c8ca7b645470bfefd1a5ff6169bec47550c4effa76de70a20a","signer":"crovia.substrate","subject":{"observed_at":"2026-05-07T04:43:30Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2512.04277"},"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":"02454d0e1f0a01af5378709140bf32539b5e8508263c15ba4af92c4b7c0c1e0f","leaf_index":118397,"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":"b8a4e15d8f7b29d3ebef15722778ef7104d57cb6f8f6117235c31c23608f46f2","side":"left"},{"sibling":"dc2efb1245d8933eda6f464d071e43284d3256504d1d15a2fd99d1ae2a57b697","side":"right"},{"sibling":"762eb474c0ae0f85f0379235a608981ada9ba761306962ce6c1c8bfce7a8a46b","side":"left"},{"sibling":"4603564b359712be5197d112beffd09a3f31b6f4404475d57b2fc3cf450047d5","side":"left"},{"sibling":"dc4faf2b10313454613772af3edbbafdda1b8ec6ffc5051e84e0361b9010299b","side":"left"},{"sibling":"4f8fefea0bdad83d6e9dc76f781af14cbaa790887a598ce962ba2d18eff5e2c2","side":"left"},{"sibling":"32aaccf2eeff13821f2f71ee191f0ee0b074a7efb07f37d041ab73d669ff43ba","side":"left"},{"sibling":"432e5b2cf8e49f6f70fd5be7683dbbc02f1ebeff16b82fade70feaeeff078cab","side":"right"},{"sibling":"943780ddf0bc6538ed8b19cdb0e84ad78f5880f72d472b378c67229ade3fd90d","side":"right"},{"sibling":"9e688ad7df5f10379f7d9b9d109c3ea84968c044c36d5562f359706d012cf15b","side":"left"},{"sibling":"8e758a4477dfc0838d2e8ea2bdbd583bc3192683e75fd9cde217ee6a3b2f3ac8","side":"left"},{"sibling":"4219f746e463e594ccd6447debdf736a57e77319b12bcb74d8ece2b5860064c6","side":"left"},{"sibling":"05f89b32c00462e60adf95c1fe4579cdc2791b36e8b17573d8f3b5fd5da95a0b","side":"right"},{"sibling":"8ccd9937a2c0d5c04044d07d1557791b7d07bb31eac41a39a675608d44b38f23","side":"right"},{"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_02753951eb00249990c8bd69128667cbb3ed475b4ff740e7cb3e10f66289bd54"}}