{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VFSQ3CSGSKNVNAVWDCUCUOBNLS","short_pith_number":"pith:VFSQ3CSG","schema_version":"1.0","canonical_sha256":"a9650d8a46929b5682b618a82a382d5cba5ff4fb6b270332bd47d6c0cb435a23","source":{"kind":"arxiv","id":"2602.12206","version":3},"attestation_state":"computed","paper":{"title":"Making the complete OpenAIRE citation graph easily accessible through compact data representation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"The full OpenAIRE citation graph is reduced to a 16 GB dataset while preserving every publication and citation.","cross_cats":["cs.DL"],"primary_cat":"cs.SI","authors_text":"Joakim Skarding, Pavel Sanda","submitted_at":"2026-02-12T17:44:36Z","abstract_excerpt":"The OpenAIRE graph contains a large citation graph dataset, with over 200 million publications and over 2 billion citations. The current graph is available as a dump with metadata which, when uncompressed, totals $\\sim$2.5 TB. This makes it hard to process on conventional computers. To make this network more accessible for the community, we provide a processed OpenAIRE graph which is downscaled to 16 GB RAM, while preserving the full graph structure. Apart from this we offer the processed data in a very simple format, which allows for further straightforward manipulation. We also provide (1) a"},"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":"2602.12206","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SI","submitted_at":"2026-02-12T17:44:36Z","cross_cats_sorted":["cs.DL"],"title_canon_sha256":"540a017b8b3e109a6c7a6a24a211cb6ceb831c1d4a5547d08eedd4f942907a2f","abstract_canon_sha256":"c2c6ecc0056cd8893292c7912931a2831b763459cdf99256172705ab1d823dd7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:42.117680Z","signature_b64":"eKPAM+blNsCnjGWflAnHyGQHtTwv7kFAUnFPPx9MSW+RuIJjlI2YFY6zh2joxeKCUzPy8J9/fttnlfSGPMepCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9650d8a46929b5682b618a82a382d5cba5ff4fb6b270332bd47d6c0cb435a23","last_reissued_at":"2026-05-20T00:05:42.117180Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:42.117180Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Making the complete OpenAIRE citation graph easily accessible through compact data representation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"The full OpenAIRE citation graph is reduced to a 16 GB dataset while preserving every publication and citation.","cross_cats":["cs.DL"],"primary_cat":"cs.SI","authors_text":"Joakim Skarding, Pavel Sanda","submitted_at":"2026-02-12T17:44:36Z","abstract_excerpt":"The OpenAIRE graph contains a large citation graph dataset, with over 200 million publications and over 2 billion citations. The current graph is available as a dump with metadata which, when uncompressed, totals $\\sim$2.5 TB. This makes it hard to process on conventional computers. To make this network more accessible for the community, we provide a processed OpenAIRE graph which is downscaled to 16 GB RAM, while preserving the full graph structure. Apart from this we offer the processed data in a very simple format, which allows for further straightforward manipulation. We also provide (1) a"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"we provide a processed OpenAIRE graph which is downscaled to 16 GB RAM, while preserving the full graph structure","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the chosen compact representation and simple format retain all information needed for the majority of downstream citation-graph analyses without introducing hidden losses or requiring users to re-derive missing fields.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A 16 GB version of the complete OpenAIRE citation graph is released together with processing code, keeping every node and edge while fitting on ordinary machines.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"The full OpenAIRE citation graph is reduced to a 16 GB dataset while preserving every publication and citation.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"1a454789240abb421ae8698ab1b3153122a842d981fec84298346a9d11405108"},"source":{"id":"2602.12206","kind":"arxiv","version":3},"verdict":{"id":"d1df8cde-9341-4069-a2e4-65eaffd6a9b6","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T05:28:12.931267Z","strongest_claim":"we provide a processed OpenAIRE graph which is downscaled to 16 GB RAM, while preserving the full graph structure","one_line_summary":"A 16 GB version of the complete OpenAIRE citation graph is released together with processing code, keeping every node and edge while fitting on ordinary machines.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the chosen compact representation and simple format retain all information needed for the majority of downstream citation-graph analyses without introducing hidden losses or requiring users to re-derive missing fields.","pith_extraction_headline":"The full OpenAIRE citation graph is reduced to a 16 GB dataset while preserving every publication and citation."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2602.12206/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":"2602.12206","created_at":"2026-05-20T00:05:42.117258+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.12206v3","created_at":"2026-05-20T00:05:42.117258+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.12206","created_at":"2026-05-20T00:05:42.117258+00:00"},{"alias_kind":"pith_short_12","alias_value":"VFSQ3CSGSKNV","created_at":"2026-05-20T00:05:42.117258+00:00"},{"alias_kind":"pith_short_16","alias_value":"VFSQ3CSGSKNVNAVW","created_at":"2026-05-20T00:05:42.117258+00:00"},{"alias_kind":"pith_short_8","alias_value":"VFSQ3CSG","created_at":"2026-05-20T00:05:42.117258+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/VFSQ3CSGSKNVNAVWDCUCUOBNLS","json":"https://pith.science/pith/VFSQ3CSGSKNVNAVWDCUCUOBNLS.json","graph_json":"https://pith.science/api/pith-number/VFSQ3CSGSKNVNAVWDCUCUOBNLS/graph.json","events_json":"https://pith.science/api/pith-number/VFSQ3CSGSKNVNAVWDCUCUOBNLS/events.json","paper":"https://pith.science/paper/VFSQ3CSG"},"agent_actions":{"view_html":"https://pith.science/pith/VFSQ3CSGSKNVNAVWDCUCUOBNLS","download_json":"https://pith.science/pith/VFSQ3CSGSKNVNAVWDCUCUOBNLS.json","view_paper":"https://pith.science/paper/VFSQ3CSG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.12206&json=true","fetch_graph":"https://pith.science/api/pith-number/VFSQ3CSGSKNVNAVWDCUCUOBNLS/graph.json","fetch_events":"https://pith.science/api/pith-number/VFSQ3CSGSKNVNAVWDCUCUOBNLS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VFSQ3CSGSKNVNAVWDCUCUOBNLS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VFSQ3CSGSKNVNAVWDCUCUOBNLS/action/storage_attestation","attest_author":"https://pith.science/pith/VFSQ3CSGSKNVNAVWDCUCUOBNLS/action/author_attestation","sign_citation":"https://pith.science/pith/VFSQ3CSGSKNVNAVWDCUCUOBNLS/action/citation_signature","submit_replication":"https://pith.science/pith/VFSQ3CSGSKNVNAVWDCUCUOBNLS/action/replication_record"}},"created_at":"2026-05-20T00:05:42.117258+00:00","updated_at":"2026-05-20T00:05:42.117258+00:00"}