{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CQVMQLILCBTEYFH6YD7ZCDHDYO","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":"fff2b8baca585de430f58c4cbe3c3299d58e12f0db453fac8084c6c1aba4bf47","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-10T03:43:30Z","title_canon_sha256":"71cf19e1291c8a0aaaf24d7aeb0ce4d7893981d764cf7a1a2ea8987f49654074"},"schema_version":"1.0","source":{"id":"2608.09093","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.09093","created_at":"2026-08-11T02:21:46Z"},{"alias_kind":"arxiv_version","alias_value":"2608.09093v1","created_at":"2026-08-11T02:21:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.09093","created_at":"2026-08-11T02:21:46Z"},{"alias_kind":"pith_short_12","alias_value":"CQVMQLILCBTE","created_at":"2026-08-11T02:21:46Z"},{"alias_kind":"pith_short_16","alias_value":"CQVMQLILCBTEYFH6","created_at":"2026-08-11T02:21:46Z"},{"alias_kind":"pith_short_8","alias_value":"CQVMQLIL","created_at":"2026-08-11T02:21:46Z"}],"graph_snapshots":[{"event_id":"sha256:a9c16f2c655832001b80e212cc4b673682833aac0afe46314c3e7eb9a9b30b23","target":"graph","created_at":"2026-08-11T02:21:46Z","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/2608.09093/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"How a document's arrangement is written down, its notation, is a training variable that no dataset card records. The field has established that text-extraction choices change model behaviour, and has never once measured the notation of what those choices put into the corpus. We define clean-window survival, a deterministic count of how much of a stream still demands the boundary inference, and measure notation on three fronts. What corpora carry: a census of thirteen public corpora, where survival falls to 0.153 in a vision-converted PDF slice against 0.889 in C4; the scarce resource is not un","authors_text":"E. M. Freeburg","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-10T03:43:30Z","title":"The Announcement Carries the Cue: Markup, Boundaries, and the Notation of Pre-Training Corpora"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.09093","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":"sha256:37bfd7f55145e819a7daec86e7e35048538165481a1ea14d9da8cddae8b46f68","target":"record","created_at":"2026-08-11T02:21:46Z","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":"fff2b8baca585de430f58c4cbe3c3299d58e12f0db453fac8084c6c1aba4bf47","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-10T03:43:30Z","title_canon_sha256":"71cf19e1291c8a0aaaf24d7aeb0ce4d7893981d764cf7a1a2ea8987f49654074"},"schema_version":"1.0","source":{"id":"2608.09093","kind":"arxiv","version":1}},"canonical_sha256":"142ac82d0b10664c14fec0ff910ce3c3839bdb5c4e5025278217aaa867ac44b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"142ac82d0b10664c14fec0ff910ce3c3839bdb5c4e5025278217aaa867ac44b3","first_computed_at":"2026-08-11T02:21:46.683676Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T02:21:46.683676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PgPYpo0gRgEtRhTayCuIVwB+9tU5Q/xhzSDTcks89aIdfxPD5DNjBnOAA/447so5d5N91cx85CopAL54AvWqDQ==","signature_status":"signed_v1","signed_at":"2026-08-11T02:21:46.685244Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.09093","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:37bfd7f55145e819a7daec86e7e35048538165481a1ea14d9da8cddae8b46f68","sha256:a9c16f2c655832001b80e212cc4b673682833aac0afe46314c3e7eb9a9b30b23"],"state_sha256":"cc698f1e42ad2989ab0feec8fc7ef29eaa5f07ef9c65aee592a1f79337a0799e"}