{"_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_8ce7784b484c2239f2d8a3c09538e8e388108dd7f0595fcce5641b6f82c7a121","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_8ce7784b484c2239f2d8a3c09538e8e388108dd7f0595fcce5641b6f82c7a121","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"4351282b4e8d9015779113cb76432086a6027beefa33d86a34e93a2186121671","published":"Fri, 15 May 2026 00:00:00 -0400","receipt_hash":"4351282b4e8d9015779113cb76432086a6027beefa33d86a34e93a2186121671","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":"4351282b4e8d9015779113cb76432086a6027beefa33d86a34e93a2186121671","observed_at":"2026-05-15T04:43:17.611638Z","parent_run_hash":"5c64f85625fabd323e9c4a1cf068c012fb88a248deda9a9ac702fb2f9799f2e5","published":"Fri, 15 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:2605.14004v1 Announce Type: new \nAbstract: Generative models are often trained with a next-token prediction objective, yet many downstream applications require the ability to estimate or control sequence-level properties. Next-token prediction can lead to overfitting of local patterns during training, underfitting of global structure, and requires significant downstream modifications or expensive sampling to guide or predict the global attributes of generated samples at inference time. Here, we introduce Conditional Attribute Transformers, a novel method for jointly estimating the next-token probability and the value of an attribute conditional on each potential next token selection. This framework enables three critical capabilities within a single forward pass, without modification of the input sequence: (1) per-token credit assignment across an entire sequence, by identifying how each token in a sequence is associated with an attribute's value; (2) counterfactual analysis, by ","title":"Conditional Attribute Estimation with Autoregressive Sequence Models","url":"https://arxiv.org/abs/2605.14004","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.14004v1 Announce Type: new \nAbstract: Generative models are often trained with a next-token prediction objective, yet many downstream applications require the ability to estimate or control sequence-level properties. Next-token prediction can lead to overfitting of local patterns during training, underfitting of global structure, and requires significant downstream modifications or expensive sampling to guide or predict the global attributes of generated samples at inference time. Here, we introduce Conditional Attribute Transformers, a novel method for jointly estimating the next-token probability and the value of an attribute conditional on each potential next token selection. This framework enables three critical capabilities within a single forward pass, without modification of the input sequence: (1) per-token credit assignment across an entire sequence, by identifying how each token in a sequence is associated with an attribute's value; (2) counterfactual analysis, by ","title":"Conditional Attribute Estimation with Autoregressive Sequence Models","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-15T04:43:17Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2605.14004"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:720708d06bc8e5548845570bcda9e0c4343f891e69b5dd3b0acc6852332bd80cd50718a5f961e5d3f9a5e497b94f06614c75ff34c500a8eb215b9eff86b1b50b","signer":"crovia.substrate","subject":{"observed_at":"2026-05-15T04:43:17Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.14004"},"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":"a7deae500aa4ca50905e89fc0150f807ecde023effff5bda5259f814ab950fcd","leaf_index":134399,"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":"e2f0577284fa461ebef22c50ad68bb046fcfb37c9c38ccaa2f627f2ced6c700c","side":"left"},{"sibling":"f24ba82336d1815544718f2a0d1cd3169129590dc031d4ae5ba5b2a6fbf2272d","side":"left"},{"sibling":"08ede2cd6371332c189d80297e7cdc1e5b83ae3fedebe0b41c20f45b6c201a34","side":"left"},{"sibling":"73195ad1bca86de0948af40f72e47bd6c244b26fadc1d31e077b197c2f8e4491","side":"left"},{"sibling":"95451830009cdddd1b9b95aff2121d2564cf65d32b9ac3d4e25878a08bfada3b","side":"left"},{"sibling":"a5cef23cdbfc386e6595f0fc7d2161ffe5f2add05f222c8a3560ad75e3ed37eb","side":"left"},{"sibling":"53a5cc5dcdc9e1da3649ce7c8c0b4a6d16ea1501b5a4d93492fc820b2b9cd70d","side":"left"},{"sibling":"e40cac0dfbb3ab27201bef2b1e71e743452a833372a4cda94d905b517150ae7a","side":"left"},{"sibling":"410916313e5d1c589050a72956df796b55f0945d3e80d0ea57c0719283ba9f9f","side":"right"},{"sibling":"8ce2a4687a8ceb409df2e1cb10e44a610b21dc294e518a8550b6d1122335ca2b","side":"right"},{"sibling":"36672459e5ed50c64ee1842b69cb6d2eb682c2a04844555be8d124257571994a","side":"left"},{"sibling":"727783827652adfa99c455bd80a01bfb33836228e51068b4f654ef3da468ca69","side":"left"},{"sibling":"623194cd30880ed223e306737fdb111aa0d781751bfc47553c404a6af6aad2c4","side":"right"},{"sibling":"fc8f53ed42756907fb79ee19a4ed09f72c560e5302b3d98198b96bf1da635a4a","side":"right"},{"sibling":"d6607539da7ba39ec68be2d12f27ed6768766c745e3120fd915f88c5e288e07c","side":"right"},{"sibling":"b63408a424d27cd6a75e0fb155e69a58a328f41e9cb9dba1eddef9a5289cc7fd","side":"right"},{"sibling":"356fb36a4e188f03d7a05c54cd8789bdd40eda454b9bc9560f667acc08e6c4e0","side":"right"},{"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":134886,"merkle_root":"c6c7ae28c065bced89e7f844216b073f1a7cc4b378db0d41a98bcd21b28066db","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260515T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-15T05:37:26Z","sig_algorithm":"ed25519","signature":"5a3978c26017daf4104adbb3e1c3099c5750157acbfc7242ece1815dc6740fe08a690291ce0afe42011e20cc565b5ebe64ec016bf658b5bab563a63337985c05","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_8ce7784b484c2239f2d8a3c09538e8e388108dd7f0595fcce5641b6f82c7a121"}}