{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RGNPSAUCFQMDRES4M2YUQB35LX","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":"310b5bf513972f103de2f8eb1c87d059ea3259356dab2e4cbbe48d1415fe2f8a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DL","submitted_at":"2025-07-19T21:01:38Z","title_canon_sha256":"9c198c713fe12b1ecba31c90e5e5669dbf5cff603c3d8332c0c974b7882df4c8"},"schema_version":"1.0","source":{"id":"2507.14752","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.14752","created_at":"2026-07-05T11:40:12Z"},{"alias_kind":"arxiv_version","alias_value":"2507.14752v1","created_at":"2026-07-05T11:40:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.14752","created_at":"2026-07-05T11:40:12Z"},{"alias_kind":"pith_short_12","alias_value":"RGNPSAUCFQMD","created_at":"2026-07-05T11:40:12Z"},{"alias_kind":"pith_short_16","alias_value":"RGNPSAUCFQMDRES4","created_at":"2026-07-05T11:40:12Z"},{"alias_kind":"pith_short_8","alias_value":"RGNPSAUC","created_at":"2026-07-05T11:40:12Z"}],"graph_snapshots":[{"event_id":"sha256:1682a3f302a089ae4fe2aa63adc9e6fc496833d04302f8f70aca9d45da7a7f9c","target":"graph","created_at":"2026-07-05T11:40:12Z","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/2507.14752/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We document strategies and lessons learned from sampling the web by collecting 27.3 million URLs with 3.8 billion archived pages spanning 26 years (1996-2021) from the Internet Archive's (IA) Wayback Machine. Our goal is to revisit fundamental questions regarding the size, nature, and prevalence of the publicly archivable web, in particular, to reconsider the question: \"How long does a web page last?\" Addressing this question requires obtaining a sample of the web. We proposed several dimensions to sample URLs from the Wayback Machine's holdings: time of first archive, HTML vs. other MIME type","authors_text":"Dietrich Ayala, Kritika Garg, Mark Graham, Michael L. Nelson, Michele C. Weigle, Sawood Alam","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DL","submitted_at":"2025-07-19T21:01:38Z","title":"Longitudinal Sampling of URLs From the Wayback Machine"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.14752","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":"sha256:66472dd8a3c3576a5b453c993747da6b85541f8dd04799ac068defadb55b8840","target":"record","created_at":"2026-07-05T11:40:12Z","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":"310b5bf513972f103de2f8eb1c87d059ea3259356dab2e4cbbe48d1415fe2f8a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DL","submitted_at":"2025-07-19T21:01:38Z","title_canon_sha256":"9c198c713fe12b1ecba31c90e5e5669dbf5cff603c3d8332c0c974b7882df4c8"},"schema_version":"1.0","source":{"id":"2507.14752","kind":"arxiv","version":1}},"canonical_sha256":"899af902822c1838925c66b148077d5df3b97bbdadb3b9dc371cc7a5719c30dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"899af902822c1838925c66b148077d5df3b97bbdadb3b9dc371cc7a5719c30dd","first_computed_at":"2026-07-05T11:40:12.902130Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:40:12.902130Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Xz8zg1pafIWZu5DRExStlKoZzjRKNa2Dep5qma9FMkJt9WjpedDTHRyp5cbDEyiiH6LCA9Qe4l0/y/ujH/j9CA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:40:12.902625Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.14752","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:66472dd8a3c3576a5b453c993747da6b85541f8dd04799ac068defadb55b8840","sha256:1682a3f302a089ae4fe2aa63adc9e6fc496833d04302f8f70aca9d45da7a7f9c"],"state_sha256":"fbc73c6298577cae410e1b9a46e5607db84c6d5677f3b2d74c38152acadc5655"}