{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RGETLFTZLLCZUAKQFMNVCUJ5SA","short_pith_number":"pith:RGETLFTZ","schema_version":"1.0","canonical_sha256":"89893596795ac59a01502b1b51513d902d86d9002dd903b4db47c20a44355f64","source":{"kind":"arxiv","id":"2606.29550","version":1},"attestation_state":"computed","paper":{"title":"Deforking the World of Code: A Project-Provenance Map that Recovers Cross-Forge Fork Families that Platform Graphs Cannot See","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Audris Mockus","submitted_at":"2026-06-28T18:25:17Z","abstract_excerpt":"Forks share git history, so a commit surfaces in many repositories and any spread- or popularity-based measure over raw repositories is inflated by orders of magnitude. We release a curated deforking map for the World of Code (WoC) version V2604: p2PFull, which collapses every raw repository p into the deforked project P to which it belongs, built from the global shared-commit relation (51.79M shared-commit groups) via a hub-node star encoding and parallel Louvain clustering, plus capped variants (cap250/cap500) that bound mega-cluster size. The naive shared-history union over-merges: the proj"},"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":"2606.29550","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-28T18:25:17Z","cross_cats_sorted":[],"title_canon_sha256":"4c731724c15d55c4dc71f3cd1637a055d16f447eacd0033ca02fcb25cf478344","abstract_canon_sha256":"a92071cbe29b0ea163e2c657b24048a8a43d9aba4458de3566ed99a04e807238"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:18:11.464929Z","signature_b64":"0U0+gO8d0dDVGOUBPuwIlKroT4VpCjo6id2JcC1OeqYA+HzNpDGcHBQsG1xRUrO+4UJZytfkiTwIgkFyTv08Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89893596795ac59a01502b1b51513d902d86d9002dd903b4db47c20a44355f64","last_reissued_at":"2026-06-30T01:18:11.464484Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:18:11.464484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deforking the World of Code: A Project-Provenance Map that Recovers Cross-Forge Fork Families that Platform Graphs Cannot See","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Audris Mockus","submitted_at":"2026-06-28T18:25:17Z","abstract_excerpt":"Forks share git history, so a commit surfaces in many repositories and any spread- or popularity-based measure over raw repositories is inflated by orders of magnitude. We release a curated deforking map for the World of Code (WoC) version V2604: p2PFull, which collapses every raw repository p into the deforked project P to which it belongs, built from the global shared-commit relation (51.79M shared-commit groups) via a hub-node star encoding and parallel Louvain clustering, plus capped variants (cap250/cap500) that bound mega-cluster size. The naive shared-history union over-merges: the proj"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29550","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/2606.29550/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":"2606.29550","created_at":"2026-06-30T01:18:11.464549+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.29550v1","created_at":"2026-06-30T01:18:11.464549+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29550","created_at":"2026-06-30T01:18:11.464549+00:00"},{"alias_kind":"pith_short_12","alias_value":"RGETLFTZLLCZ","created_at":"2026-06-30T01:18:11.464549+00:00"},{"alias_kind":"pith_short_16","alias_value":"RGETLFTZLLCZUAKQ","created_at":"2026-06-30T01:18:11.464549+00:00"},{"alias_kind":"pith_short_8","alias_value":"RGETLFTZ","created_at":"2026-06-30T01:18:11.464549+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/RGETLFTZLLCZUAKQFMNVCUJ5SA","json":"https://pith.science/pith/RGETLFTZLLCZUAKQFMNVCUJ5SA.json","graph_json":"https://pith.science/api/pith-number/RGETLFTZLLCZUAKQFMNVCUJ5SA/graph.json","events_json":"https://pith.science/api/pith-number/RGETLFTZLLCZUAKQFMNVCUJ5SA/events.json","paper":"https://pith.science/paper/RGETLFTZ"},"agent_actions":{"view_html":"https://pith.science/pith/RGETLFTZLLCZUAKQFMNVCUJ5SA","download_json":"https://pith.science/pith/RGETLFTZLLCZUAKQFMNVCUJ5SA.json","view_paper":"https://pith.science/paper/RGETLFTZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.29550&json=true","fetch_graph":"https://pith.science/api/pith-number/RGETLFTZLLCZUAKQFMNVCUJ5SA/graph.json","fetch_events":"https://pith.science/api/pith-number/RGETLFTZLLCZUAKQFMNVCUJ5SA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RGETLFTZLLCZUAKQFMNVCUJ5SA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RGETLFTZLLCZUAKQFMNVCUJ5SA/action/storage_attestation","attest_author":"https://pith.science/pith/RGETLFTZLLCZUAKQFMNVCUJ5SA/action/author_attestation","sign_citation":"https://pith.science/pith/RGETLFTZLLCZUAKQFMNVCUJ5SA/action/citation_signature","submit_replication":"https://pith.science/pith/RGETLFTZLLCZUAKQFMNVCUJ5SA/action/replication_record"}},"created_at":"2026-06-30T01:18:11.464549+00:00","updated_at":"2026-06-30T01:18:11.464549+00:00"}