{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CQVMQLILCBTEYFH6YD7ZCDHDYO","short_pith_number":"pith:CQVMQLIL","schema_version":"1.0","canonical_sha256":"142ac82d0b10664c14fec0ff910ce3c3839bdb5c4e5025278217aaa867ac44b3","source":{"kind":"arxiv","id":"2608.09093","version":1},"attestation_state":"computed","paper":{"title":"The Announcement Carries the Cue: Markup, Boundaries, and the Notation of Pre-Training Corpora","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"E. M. Freeburg","submitted_at":"2026-08-10T03:43:30Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.09093","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-10T03:43:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"71cf19e1291c8a0aaaf24d7aeb0ce4d7893981d764cf7a1a2ea8987f49654074","abstract_canon_sha256":"fff2b8baca585de430f58c4cbe3c3299d58e12f0db453fac8084c6c1aba4bf47"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T02:21:46.685244Z","signature_b64":"PgPYpo0gRgEtRhTayCuIVwB+9tU5Q/xhzSDTcks89aIdfxPD5DNjBnOAA/447so5d5N91cx85CopAL54AvWqDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"142ac82d0b10664c14fec0ff910ce3c3839bdb5c4e5025278217aaa867ac44b3","last_reissued_at":"2026-08-11T02:21:46.683676Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T02:21:46.683676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Announcement Carries the Cue: Markup, Boundaries, and the Notation of Pre-Training Corpora","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"E. M. Freeburg","submitted_at":"2026-08-10T03:43:30Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.09093","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/2608.09093/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.09093","created_at":"2026-08-11T02:21:46.684281+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.09093v1","created_at":"2026-08-11T02:21:46.684281+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.09093","created_at":"2026-08-11T02:21:46.684281+00:00"},{"alias_kind":"pith_short_12","alias_value":"CQVMQLILCBTE","created_at":"2026-08-11T02:21:46.684281+00:00"},{"alias_kind":"pith_short_16","alias_value":"CQVMQLILCBTEYFH6","created_at":"2026-08-11T02:21:46.684281+00:00"},{"alias_kind":"pith_short_8","alias_value":"CQVMQLIL","created_at":"2026-08-11T02:21:46.684281+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CQVMQLILCBTEYFH6YD7ZCDHDYO","json":"https://pith.science/pith/CQVMQLILCBTEYFH6YD7ZCDHDYO.json","graph_json":"https://pith.science/api/pith-number/CQVMQLILCBTEYFH6YD7ZCDHDYO/graph.json","events_json":"https://pith.science/api/pith-number/CQVMQLILCBTEYFH6YD7ZCDHDYO/events.json","paper":"https://pith.science/paper/CQVMQLIL"},"agent_actions":{"view_html":"https://pith.science/pith/CQVMQLILCBTEYFH6YD7ZCDHDYO","download_json":"https://pith.science/pith/CQVMQLILCBTEYFH6YD7ZCDHDYO.json","view_paper":"https://pith.science/paper/CQVMQLIL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.09093&json=true","fetch_graph":"https://pith.science/api/pith-number/CQVMQLILCBTEYFH6YD7ZCDHDYO/graph.json","fetch_events":"https://pith.science/api/pith-number/CQVMQLILCBTEYFH6YD7ZCDHDYO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CQVMQLILCBTEYFH6YD7ZCDHDYO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CQVMQLILCBTEYFH6YD7ZCDHDYO/action/storage_attestation","attest_author":"https://pith.science/pith/CQVMQLILCBTEYFH6YD7ZCDHDYO/action/author_attestation","sign_citation":"https://pith.science/pith/CQVMQLILCBTEYFH6YD7ZCDHDYO/action/citation_signature","submit_replication":"https://pith.science/pith/CQVMQLILCBTEYFH6YD7ZCDHDYO/action/replication_record"}},"created_at":"2026-08-11T02:21:46.684281+00:00","updated_at":"2026-08-11T02:21:46.684281+00:00"}