{"_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_22e211a6f7548afc734057ec9864b25e811a88f31946a9fb0a1bb1407c2e3c8e","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_22e211a6f7548afc734057ec9864b25e811a88f31946a9fb0a1bb1407c2e3c8e","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"2b60d40f9104f6257a45453bc9fa882aa314651e5417f77dc583c4db571ae742","published":"Fri, 17 Jul 2026 00:00:00 -0400","receipt_hash":"2b60d40f9104f6257a45453bc9fa882aa314651e5417f77dc583c4db571ae742","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":"2b60d40f9104f6257a45453bc9fa882aa314651e5417f77dc583c4db571ae742","observed_at":"2026-07-17T04:43:38.280949Z","parent_run_hash":"113193614a8af99887180226d4e28a8b71d957da5fe3694f0e7a56807c145504","published":"Fri, 17 Jul 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:2607.14306v1 Announce Type: new \nAbstract: In this paper, we study the connection between an LLM's output distribution and the data used to train it. Specifically, we study the degree to which an LLM's next-token distribution agrees with the empirical next-token distribution (ENTD) given the context in the training data. The ENTD is an appealing target because it is the unrestricted global minimizer of the next-token cross entropy loss used for pretraining, as well as an easily interpretable function of the pretraining corpus. We find that for a significant fraction of inputs, the LLM's distribution agrees with the ENTD almost perfectly, and the average agreement increases with model scale and training compute. Nevertheless, there is a long tail of input sequences where the LLM and ENTD differ significantly, and we examine several possible sources of this discrepancy across the transformer architecture, training procedure, and finite-sample noise in the ENTD estimate itself. More","title":"Tracing LLM Behavior to the Training Data with Empirical Next-Token Distributions","url":"https://arxiv.org/abs/2607.14306","vendor":"arxiv_cs_ai"},"summary":"arXiv:2607.14306v1 Announce Type: new \nAbstract: In this paper, we study the connection between an LLM's output distribution and the data used to train it. Specifically, we study the degree to which an LLM's next-token distribution agrees with the empirical next-token distribution (ENTD) given the context in the training data. The ENTD is an appealing target because it is the unrestricted global minimizer of the next-token cross entropy loss used for pretraining, as well as an easily interpretable function of the pretraining corpus. We find that for a significant fraction of inputs, the LLM's distribution agrees with the ENTD almost perfectly, and the average agreement increases with model scale and training compute. Nevertheless, there is a long tail of input sequences where the LLM and ENTD differ significantly, and we examine several possible sources of this discrepancy across the transformer architecture, training procedure, and finite-sample noise in the ENTD estimate itself. More","title":"Tracing LLM Behavior to the Training Data with Empirical Next-Token Distributions","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-17T04:43:38Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2607.14306"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:9ac28bd5d052d6b60f1ca9003a31b267dc01661425e2f436b3d1581fb32fd2e45ebfcee79a82901f97f57853db4341a832eaf587c4f9f704d3bcd12c66abd109","signer":"crovia.substrate","subject":{"observed_at":"2026-07-17T04:43:38Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2607.14306"},"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":"e3aa82c30a7d9bc9152695e08b59d9e569fde36d920f189bcf66c5aa25a2c72e","leaf_index":322994,"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":"a3c8b4d8de74cbbc897ae7cd7cebe3326cf11c7b0887eb3637cca2d81b513bc0","side":"right"},{"sibling":"72f79d626ac97d426b38fc615cc3ce57a2512c092381cf031e1cc4f0d29d0c6f","side":"left"},{"sibling":"4e15c2815287ddd44e79b906c201470ff9cd1dd60e5ac87c2494f9be90c59e16","side":"right"},{"sibling":"a6946190d917531c46cad253f65c732fbc83fe5bf3ea516e90225393625547f7","side":"right"},{"sibling":"0b2f944173499411add847b7fcd367d1c619498edc710603e9c9aef6d209d1a1","side":"left"},{"sibling":"fef12197c3728f06d870239e723f414c7df9e8e044582778e065e3251b39c7ec","side":"left"},{"sibling":"e20baa8791119aeca771591615d2b5dda42707944e22980f8722d64fe8a20f4c","side":"right"},{"sibling":"5944e6d0988d989a4ae4330320fe2633624339ee8db50eaa0d3fe8981ac982cf","side":"left"},{"sibling":"e90a96bd60cc2aad32b2969366989aa5d4e0c71aeb240044c7778cca7188dc3f","side":"left"},{"sibling":"d7e66b08e4f129ea3ff266d25de4f974fe1f0d56e2fae2a6d3ae1e1565007da9","side":"right"},{"sibling":"05a09763743cdc09fc45cf454e4e3ea4a0d1cd74f9c8162b2a57e2c873160908","side":"left"},{"sibling":"de3120ef2488b8a791a686b47257da4e612256abdfcdda7519265e7edd47d041","side":"left"},{"sibling":"e86f56a4883492da5b5e7b0201324c52946e865e69b99ebb532f41fe3c658ee4","side":"right"},{"sibling":"34d85f6ad6cc7dfa79d90e2b9ff99a561bcdc75b0301bbbd3e83861f54535c1e","side":"left"},{"sibling":"f302542c38ba7c3aab7c9280dd60259ecec777dca6e6f71b6f0729b0b8791b72","side":"left"},{"sibling":"d8b9143917b539c543cf4448cec00131f8b807bd8004979c54ebe09798748c66","side":"left"},{"sibling":"9b11714124b9b951ff9450b0ee9d625a0b70b6da2cf388bd3df1475eec0b17ba","side":"right"},{"sibling":"a4523a9014d45df43e006e9210a73428c380d771f2c650a1b986910759b0cdf7","side":"right"},{"sibling":"1cecb7f447febd025aac272837c80de218aecc6485d2395a509b2a1f1b9c746e","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":323382,"merkle_root":"2f4d32419c80a9600aba5a480fc3fb7012ec0a695c91a1b055048e78760b65ca","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260717T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-17T05:38:31Z","sig_algorithm":"ed25519","signature":"495308c7bf004117807331d3f71d0b079f6bd7ed7737faa58c773b1b3e80ee84928d2d8519cc7d2b809506501aada1be6546f72c7ecda3dad5445cbb44502209","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_22e211a6f7548afc734057ec9864b25e811a88f31946a9fb0a1bb1407c2e3c8e"}}