{"_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_2c14849e8b4693aa1adbcb29e5efe6436ecd760808fc5d3407c8a3a371336890","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_2c14849e8b4693aa1adbcb29e5efe6436ecd760808fc5d3407c8a3a371336890","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"f09cc83163fcbac0b333758b0370afa239c35b46fde216635bd96fe1eb4979d9","published":"Wed, 10 Jun 2026 00:00:00 -0400","receipt_hash":"f09cc83163fcbac0b333758b0370afa239c35b46fde216635bd96fe1eb4979d9","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":"f09cc83163fcbac0b333758b0370afa239c35b46fde216635bd96fe1eb4979d9","observed_at":"2026-06-10T04:43:37.461885Z","parent_run_hash":"23aff1a6f676ba7ca33f70f4ddfae1dd282fb86104d577ce9be510d81a94c5dc","published":"Wed, 10 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:2606.09962v1 Announce Type: cross \nAbstract: Continuous diffusion for categorical data is a framework belonging to the diffusion family and aiming at generating discrete data. The scientific interest to such models has been constantly increasing these days because researchers try to achieve a challenging goal of finding reasonable alternatives to autoregressive large language models. In this paper, we study the properties of the structure of the latent space corresponding to discrete tokens expressed in terms of Kullback-Leibler divergence on diffusion path measures and accuracy of the correct token prediction by the optimally trained diffusion model. We find that FSQ tokenization scheme has the latent space structure with the properties that make it best suited for continuous diffusion for categorical data as verified through rigorous theoretical analysis and numerical experiments. To validate our findings in real-life scenario, we train several text-to-speech diffusion models h","title":"Optimality of FSQ Tokens for Continuous Diffusion for Categorical Data with Application to Text-to-Speech","url":"https://arxiv.org/abs/2606.09962","vendor":"arxiv_cs_ai"},"summary":"arXiv:2606.09962v1 Announce Type: cross \nAbstract: Continuous diffusion for categorical data is a framework belonging to the diffusion family and aiming at generating discrete data. The scientific interest to such models has been constantly increasing these days because researchers try to achieve a challenging goal of finding reasonable alternatives to autoregressive large language models. In this paper, we study the properties of the structure of the latent space corresponding to discrete tokens expressed in terms of Kullback-Leibler divergence on diffusion path measures and accuracy of the correct token prediction by the optimally trained diffusion model. We find that FSQ tokenization scheme has the latent space structure with the properties that make it best suited for continuous diffusion for categorical data as verified through rigorous theoretical analysis and numerical experiments. To validate our findings in real-life scenario, we train several text-to-speech diffusion models h","title":"Optimality of FSQ Tokens for Continuous Diffusion for Categorical Data with Application to Text-to-Speech","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-10T04:43:37Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2606.09962"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:8c6ed3eaadd638b3d940cf77b7d5499f8a4a058d6ec8f8a33147fadefcc0fe420399f61d0be158690ebfcdef86d4509250328f742065a08ffe09d15eaf04fc0d","signer":"crovia.substrate","subject":{"observed_at":"2026-06-10T04:43:37Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2606.09962"},"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":"fe36723bc6eaeffb4a513c2011a00256e0eea2f828acefdfb30f6f23cb0f71e8","leaf_index":225965,"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":"9a60cb1a71da718894f4f0709a9f3cb1577c158a08320a7f7c52e111d5898df1","side":"left"},{"sibling":"140668106f89fe51082aacc8fdee487e78d6d1ff5468079d02ae44243e902b00","side":"right"},{"sibling":"e751d5b164eccb169b69965ac937123ed1657285602877b9a82c38a6d0246584","side":"left"},{"sibling":"6a9d3504e13d6749b5f5a97e8d719fc0237dd8713e6ed6931d5283d10e281e11","side":"left"},{"sibling":"1db2cab8f6f86a281b99c5696b860779eff42ea5eb2e1889c523350ca4b150dd","side":"right"},{"sibling":"3abbe488889fe216f7992fdb1a7874579deeb56eb346f6223522c5e2d7f6761a","side":"left"},{"sibling":"4189fb616853b63efeccd8c98308b970a4444cb48cec9d4d57d47996103bbc76","side":"right"},{"sibling":"3d9f311f467db31ee1be2d9664daf3ef6547a3814a86217d383241d0655ab769","side":"left"},{"sibling":"ac698c3a6027f35b513fe892f166e70344e855625238cbb581d0bf06c131db80","side":"right"},{"sibling":"a4d17aefe58175050dc159af6246658fcf1c9f3ed57aacf1b350fc3261de4e69","side":"left"},{"sibling":"280b980aa0c7756b0b0cb22658f26466d36f0e70fbc3312cd2311d9898e30b8f","side":"right"},{"sibling":"c98954d4b658b1dda60fe52576fcf9bf21a2d49c67fb63f8c30f16ab5f721938","side":"right"},{"sibling":"cdb58f86163046d3b15f857b03372ec75e1ad9ea4548e086793d528b9eed364d","side":"left"},{"sibling":"533d82482604463aa4a281b9d8b85917b383b7c5f924b2b494039524c55e8797","side":"left"},{"sibling":"b2590791b920ca2a4ed39de126d2c0b1a10d9e7e62f572f12425f214e767b6e1","side":"left"},{"sibling":"6cea4964f32722eb370847c2f7c9d6a9f0622c239538b07e6815a59d6fd8d49c","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":228173,"merkle_root":"7e416202c0bfd759bd2eea4236713b403993d99793fe8badb5065040080bece3","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260611T143708Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-11T21:59:35Z","sig_algorithm":"ed25519","signature":"231c80024bc3982dd493c45b31af95097e97aabc6d712a4e5bad7d0cbdd3c08e01ff395b0f8e72754bac97016e0cd0eed88b8a13cb71edbbcb9b6d72c10a7b03","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_2c14849e8b4693aa1adbcb29e5efe6436ecd760808fc5d3407c8a3a371336890"}}