{"_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_786261cba1d4e237a6958967d3829039f03f5a3ca08932e3d576982fba399a80","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_786261cba1d4e237a6958967d3829039f03f5a3ca08932e3d576982fba399a80","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"175600b6ff28f2d9a6742297eabb87d6b66c2a695bf0a4e7ec42b6b8dcc25fc8","published":"Wed, 03 Jun 2026 00:00:00 -0400","receipt_hash":"175600b6ff28f2d9a6742297eabb87d6b66c2a695bf0a4e7ec42b6b8dcc25fc8","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":"175600b6ff28f2d9a6742297eabb87d6b66c2a695bf0a4e7ec42b6b8dcc25fc8","observed_at":"2026-06-03T04:43:57.136784Z","parent_run_hash":"62ae9c8eda846b00bc49666345b338d00756c5203438666c4c1fc694cc364b84","published":"Wed, 03 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:2606.02884v1 Announce Type: cross \nAbstract: Reward guidance algorithms steer a learned generative process toward the reward-tilted measure at inference time. While empirically powerful, these methods are prone to reward hacking: the guided model over-optimizes the reward at the cost of fidelity to the learned distribution. Prior work has attributed this to the complexity of neural reward functions or implicit biases in diffusion training, but its fundamental origins remain poorly understood. We show that reward hacking arises from an approximation made in most practical implementations of reward-guided diffusion -- finite-particle plug-in estimation of the Doob h-function -- even in the simplest non-trivial settings of Gaussian and Gaussian mixture targets with quadratic rewards. In closed form, we isolate two distinct failure modes of the plug-in estimator: it leads to reward hacking within each mode and it cannot select high-reward modes. We propose a closed-form reward dampin","title":"Are we really tilting? The mechanics of reward guidance in flow and diffusion models","url":"https://arxiv.org/abs/2606.02884","vendor":"arxiv_cs_ai"},"summary":"arXiv:2606.02884v1 Announce Type: cross \nAbstract: Reward guidance algorithms steer a learned generative process toward the reward-tilted measure at inference time. While empirically powerful, these methods are prone to reward hacking: the guided model over-optimizes the reward at the cost of fidelity to the learned distribution. Prior work has attributed this to the complexity of neural reward functions or implicit biases in diffusion training, but its fundamental origins remain poorly understood. We show that reward hacking arises from an approximation made in most practical implementations of reward-guided diffusion -- finite-particle plug-in estimation of the Doob h-function -- even in the simplest non-trivial settings of Gaussian and Gaussian mixture targets with quadratic rewards. In closed form, we isolate two distinct failure modes of the plug-in estimator: it leads to reward hacking within each mode and it cannot select high-reward modes. We propose a closed-form reward dampin","title":"Are we really tilting? The mechanics of reward guidance in flow and diffusion models","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-03T04:43:57Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2606.02884"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:6a97abce263c5aa5e3c06304d14025b638ab898fd403df37c05a4230198deaa780ab8b73d68e8736af5edc557c0670f1034f366852a6298f224e6a0bc204cd05","signer":"crovia.substrate","subject":{"observed_at":"2026-06-03T04:43:57Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2606.02884"},"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":"43d27e418da3d4754e69a3f9145c582fddfc89c723821e62a6415b39fafe4211","leaf_index":209149,"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":"7c4c540260ac7d2cef4c7d124d3c7fef736afe8b70bcc9e33cb3580d1c7cbef2","side":"left"},{"sibling":"df595fc6382f8fd20e70df0c0b6a041a895ea2e8d39c2387bef0610151f9a031","side":"right"},{"sibling":"7d870db0a6f9027ea5a58752e2955f9a4fa14edf4608097e62a3fec18c1a01db","side":"left"},{"sibling":"3de3f15703bbdd01e22ab12c778b77247962555aaebf86b06191af43b5044c61","side":"left"},{"sibling":"780e52b9b97eca5b027e60944f9f576eef165e08c6693e9a7de9c63fe2ef2631","side":"left"},{"sibling":"1c05f66d2a592849a25035cde7f8459dbe4669c39e5cd77a4ca06548e4f7234b","side":"left"},{"sibling":"58746d6e8d96ba37e0b9e1ddb999eb39960ac9fbb6fc73c81cf5ab9ec0405d1e","side":"left"},{"sibling":"eae7f3d160253f87d5f2b594663f65cef3187784faa6d32d0ec2a662c29c4d98","side":"left"},{"sibling":"9924ce3405008f0c3a3b79e9066c574929b10c2965e0cc083262d3ac8aae2cb3","side":"right"},{"sibling":"2abcec6d14b256f82b270a3141886de6129141dec525543607b760f02588a877","side":"right"},{"sibling":"2b6b45743f97ac502854e489ac38a3366f8ae7ede58a2728b45daadbf29e9d03","side":"right"},{"sibling":"a81babbd79ea0da9e030dd7f43bffb6519d214317decd50727bea4e78189d970","side":"right"},{"sibling":"2dca509b3eb767a47cf215d4315f230ce9103a76264412008ae23a349b519ef1","side":"left"},{"sibling":"24d1bb4b13e0e46131b27b70a48e65fcf4e2e14b95e3bb83ade821e9df530f6b","side":"left"},{"sibling":"8d3baa674a45fd8bc6d3e8d25298f4bec86c72fa8259d576c330d12955c7b4f7","side":"right"},{"sibling":"e32819d1eff909db08066d1703f2db3f091cddac19378b2c0c625ab11e3fdbc0","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":209569,"merkle_root":"c852efc8ad7dfffc196c71380f79e6398bcaf566974cbae7c9950b0f600d5bc8","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260603T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-03T05:37:57Z","sig_algorithm":"ed25519","signature":"1ca417607effc813341721cfdade0a2d2d4ba96a90d361dbc3e864b6991b90abc326ec41d9ba3e7110cc04adb29d7b8d95abea7ff2ab8c591b2f864ed7270c03","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_786261cba1d4e237a6958967d3829039f03f5a3ca08932e3d576982fba399a80"}}