{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ZDD6TL7EY4WMDIDPJSE5YTYIFU","short_pith_number":"pith:ZDD6TL7E","canonical_record":{"source":{"id":"2605.23278","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-22T06:34:17Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"abd2721ab9f4b4d1f196d178e46cc0169cf31295fd1d6c6b000c709c01c37427","abstract_canon_sha256":"5206f62f1dfeed5769fff0b566902ed76da51b759ce81dea45e5e0c742b06b62"},"schema_version":"1.0"},"canonical_sha256":"c8c7e9afe4c72cc1a06f4c89dc4f082d30ac6b5e3d40d71983df0a8f8b1e582a","source":{"kind":"arxiv","id":"2605.23278","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.23278","created_at":"2026-05-25T02:01:47Z"},{"alias_kind":"arxiv_version","alias_value":"2605.23278v1","created_at":"2026-05-25T02:01:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23278","created_at":"2026-05-25T02:01:47Z"},{"alias_kind":"pith_short_12","alias_value":"ZDD6TL7EY4WM","created_at":"2026-05-25T02:01:47Z"},{"alias_kind":"pith_short_16","alias_value":"ZDD6TL7EY4WMDIDP","created_at":"2026-05-25T02:01:47Z"},{"alias_kind":"pith_short_8","alias_value":"ZDD6TL7E","created_at":"2026-05-25T02:01:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ZDD6TL7EY4WMDIDPJSE5YTYIFU","target":"record","payload":{"canonical_record":{"source":{"id":"2605.23278","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-22T06:34:17Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"abd2721ab9f4b4d1f196d178e46cc0169cf31295fd1d6c6b000c709c01c37427","abstract_canon_sha256":"5206f62f1dfeed5769fff0b566902ed76da51b759ce81dea45e5e0c742b06b62"},"schema_version":"1.0"},"canonical_sha256":"c8c7e9afe4c72cc1a06f4c89dc4f082d30ac6b5e3d40d71983df0a8f8b1e582a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:47.003865Z","signature_b64":"nuLeL1nOZJ/ErJyS1SLO/WB8mKxErngjABfltKNnAV1KXuvZzfkzDhRHo/F8nh3CwPGBx45u6121J45B2bvsCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8c7e9afe4c72cc1a06f4c89dc4f082d30ac6b5e3d40d71983df0a8f8b1e582a","last_reissued_at":"2026-05-25T02:01:47.003366Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:47.003366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.23278","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-25T02:01:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ADQhbETPGFTNS3Fu1t/4SATyVLa302H7jvaIXUEbl/4aC/M5yfuopoVmR3selOcs6c/uKfOMyFzmizPWWpEuBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T16:04:54.390063Z"},"content_sha256":"7d3686cf7b32bf3acd732470c30989b4dbf562a39dd3ce2bd3c97d2fb596c030","schema_version":"1.0","event_id":"sha256:7d3686cf7b32bf3acd732470c30989b4dbf562a39dd3ce2bd3c97d2fb596c030"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ZDD6TL7EY4WMDIDPJSE5YTYIFU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"When Is Next-Token Prediction Useful? Marginalization, Ergodicity, Mixture Identifiability, Local Sufficiency, RAG, Tools, and Programming","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CL","authors_text":"Francesco Corielli","submitted_at":"2026-05-22T06:34:17Z","abstract_excerpt":"Language models trained on observed sequences are often described as learning the conditional distribution of the next token given previous tokens. This description is only conditionally correct. A model trained on realized token trajectories does not observe full conditional laws; it receives sampled continuations. Moreover, real language generation is conditioned not only on previous words but also on non-textual circumstances: facts, events, intentions, goals, beliefs, social context, and task-specific constraints. This paper distinguishes three objects that are often conflated: the full co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23278","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.23278/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-25T02:01:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ynOCLUfzyggk99stKLZQ3+qPqIBdtdkUqVL2VK8oQZvgyb4G6PRqfXiFqcJzXLITzXHyhBL2xvwxBhvetV8KDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T16:04:54.390850Z"},"content_sha256":"34d41311f94b4bb2bd2770f7e4362c6f0ad65d0c00d45e37755cb199f53fb332","schema_version":"1.0","event_id":"sha256:34d41311f94b4bb2bd2770f7e4362c6f0ad65d0c00d45e37755cb199f53fb332"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZDD6TL7EY4WMDIDPJSE5YTYIFU/bundle.json","state_url":"https://pith.science/pith/ZDD6TL7EY4WMDIDPJSE5YTYIFU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZDD6TL7EY4WMDIDPJSE5YTYIFU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-25T16:04:54Z","links":{"resolver":"https://pith.science/pith/ZDD6TL7EY4WMDIDPJSE5YTYIFU","bundle":"https://pith.science/pith/ZDD6TL7EY4WMDIDPJSE5YTYIFU/bundle.json","state":"https://pith.science/pith/ZDD6TL7EY4WMDIDPJSE5YTYIFU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZDD6TL7EY4WMDIDPJSE5YTYIFU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZDD6TL7EY4WMDIDPJSE5YTYIFU","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5206f62f1dfeed5769fff0b566902ed76da51b759ce81dea45e5e0c742b06b62","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-22T06:34:17Z","title_canon_sha256":"abd2721ab9f4b4d1f196d178e46cc0169cf31295fd1d6c6b000c709c01c37427"},"schema_version":"1.0","source":{"id":"2605.23278","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.23278","created_at":"2026-05-25T02:01:47Z"},{"alias_kind":"arxiv_version","alias_value":"2605.23278v1","created_at":"2026-05-25T02:01:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23278","created_at":"2026-05-25T02:01:47Z"},{"alias_kind":"pith_short_12","alias_value":"ZDD6TL7EY4WM","created_at":"2026-05-25T02:01:47Z"},{"alias_kind":"pith_short_16","alias_value":"ZDD6TL7EY4WMDIDP","created_at":"2026-05-25T02:01:47Z"},{"alias_kind":"pith_short_8","alias_value":"ZDD6TL7E","created_at":"2026-05-25T02:01:47Z"}],"graph_snapshots":[{"event_id":"sha256:34d41311f94b4bb2bd2770f7e4362c6f0ad65d0c00d45e37755cb199f53fb332","target":"graph","created_at":"2026-05-25T02:01:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.23278/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models trained on observed sequences are often described as learning the conditional distribution of the next token given previous tokens. This description is only conditionally correct. A model trained on realized token trajectories does not observe full conditional laws; it receives sampled continuations. Moreover, real language generation is conditioned not only on previous words but also on non-textual circumstances: facts, events, intentions, goals, beliefs, social context, and task-specific constraints. This paper distinguishes three objects that are often conflated: the full co","authors_text":"Francesco Corielli","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-22T06:34:17Z","title":"When Is Next-Token Prediction Useful? Marginalization, Ergodicity, Mixture Identifiability, Local Sufficiency, RAG, Tools, and Programming"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23278","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7d3686cf7b32bf3acd732470c30989b4dbf562a39dd3ce2bd3c97d2fb596c030","target":"record","created_at":"2026-05-25T02:01:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5206f62f1dfeed5769fff0b566902ed76da51b759ce81dea45e5e0c742b06b62","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-22T06:34:17Z","title_canon_sha256":"abd2721ab9f4b4d1f196d178e46cc0169cf31295fd1d6c6b000c709c01c37427"},"schema_version":"1.0","source":{"id":"2605.23278","kind":"arxiv","version":1}},"canonical_sha256":"c8c7e9afe4c72cc1a06f4c89dc4f082d30ac6b5e3d40d71983df0a8f8b1e582a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c8c7e9afe4c72cc1a06f4c89dc4f082d30ac6b5e3d40d71983df0a8f8b1e582a","first_computed_at":"2026-05-25T02:01:47.003366Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:01:47.003366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nuLeL1nOZJ/ErJyS1SLO/WB8mKxErngjABfltKNnAV1KXuvZzfkzDhRHo/F8nh3CwPGBx45u6121J45B2bvsCA==","signature_status":"signed_v1","signed_at":"2026-05-25T02:01:47.003865Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.23278","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7d3686cf7b32bf3acd732470c30989b4dbf562a39dd3ce2bd3c97d2fb596c030","sha256:34d41311f94b4bb2bd2770f7e4362c6f0ad65d0c00d45e37755cb199f53fb332"],"state_sha256":"c1b1b2c9fbf9170ad5a808cff40da50cffb3b11bc8368eab2db84d26a21d1c33"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Sca/H3Aw0m8enWMl6D2NMXO++bFUgTwf8xVPfv9mesToEQaFoVkCa4coEJGRUjygnXiQND0+6ejN4Jxl3sowAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T16:04:54.394905Z","bundle_sha256":"3fa31d7db712fd2c606b7e184bf2e91d8be147e814211041c596c95cd9a412e8"}}