{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3L23C4Y4REGKA2EYBNV33CGMTS","short_pith_number":"pith:3L23C4Y4","schema_version":"1.0","canonical_sha256":"daf5b1731c890ca068980b6bbd88cc9cbfa75f8b96cce975b48f749e75c5894d","source":{"kind":"arxiv","id":"2603.25640","version":2},"attestation_state":"computed","paper":{"title":"RenoBench: A Citation Parsing Benchmark","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.DL","authors_text":"Adam Buttrick, Dione Mentis, Juan Pablo Alperin, parth sarin","submitted_at":"2026-03-26T16:52:31Z","abstract_excerpt":"Accurate parsing of citations is necessary for machine-readable scholarly infrastructure. But, despite sustained interest in this problem, existing evaluation techniques are often not generalizable, based on synthetic data, or not publicly available. We introduce RenoBench, a public domain benchmark for citation parsing, sourced from PDFs released on four publishing ecosystems: SciELO, Redalyc, the Public Knowledge Project, and Open Research Europe. Starting from 161,000 annotated citations, we apply automated validation and feature-based sampling to produce a dataset of 10,000 citations spann"},"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":"2603.25640","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DL","submitted_at":"2026-03-26T16:52:31Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"337268dc336f4ba99299c8bcba50a2548a3d405f1874142aa3936a51a92388ec","abstract_canon_sha256":"3978f24684cc975e599b80bf1b5c0b20408658ddb844607921eb0bdce9171e61"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:16.709403Z","signature_b64":"WQUKOiNbQpvfWzUMg0iIHRioA21IW6CFmX+DhrnIP862Fz5IjhVrdzWg9bCywI6eS7spk5TMTi+IP5mxxhI4AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"daf5b1731c890ca068980b6bbd88cc9cbfa75f8b96cce975b48f749e75c5894d","last_reissued_at":"2026-06-02T02:04:16.708840Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:16.708840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RenoBench: A Citation Parsing Benchmark","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.DL","authors_text":"Adam Buttrick, Dione Mentis, Juan Pablo Alperin, parth sarin","submitted_at":"2026-03-26T16:52:31Z","abstract_excerpt":"Accurate parsing of citations is necessary for machine-readable scholarly infrastructure. But, despite sustained interest in this problem, existing evaluation techniques are often not generalizable, based on synthetic data, or not publicly available. We introduce RenoBench, a public domain benchmark for citation parsing, sourced from PDFs released on four publishing ecosystems: SciELO, Redalyc, the Public Knowledge Project, and Open Research Europe. Starting from 161,000 annotated citations, we apply automated validation and feature-based sampling to produce a dataset of 10,000 citations spann"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.25640","kind":"arxiv","version":2},"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/2603.25640/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":"2603.25640","created_at":"2026-06-02T02:04:16.708904+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.25640v2","created_at":"2026-06-02T02:04:16.708904+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.25640","created_at":"2026-06-02T02:04:16.708904+00:00"},{"alias_kind":"pith_short_12","alias_value":"3L23C4Y4REGK","created_at":"2026-06-02T02:04:16.708904+00:00"},{"alias_kind":"pith_short_16","alias_value":"3L23C4Y4REGKA2EY","created_at":"2026-06-02T02:04:16.708904+00:00"},{"alias_kind":"pith_short_8","alias_value":"3L23C4Y4","created_at":"2026-06-02T02:04:16.708904+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/3L23C4Y4REGKA2EYBNV33CGMTS","json":"https://pith.science/pith/3L23C4Y4REGKA2EYBNV33CGMTS.json","graph_json":"https://pith.science/api/pith-number/3L23C4Y4REGKA2EYBNV33CGMTS/graph.json","events_json":"https://pith.science/api/pith-number/3L23C4Y4REGKA2EYBNV33CGMTS/events.json","paper":"https://pith.science/paper/3L23C4Y4"},"agent_actions":{"view_html":"https://pith.science/pith/3L23C4Y4REGKA2EYBNV33CGMTS","download_json":"https://pith.science/pith/3L23C4Y4REGKA2EYBNV33CGMTS.json","view_paper":"https://pith.science/paper/3L23C4Y4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.25640&json=true","fetch_graph":"https://pith.science/api/pith-number/3L23C4Y4REGKA2EYBNV33CGMTS/graph.json","fetch_events":"https://pith.science/api/pith-number/3L23C4Y4REGKA2EYBNV33CGMTS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3L23C4Y4REGKA2EYBNV33CGMTS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3L23C4Y4REGKA2EYBNV33CGMTS/action/storage_attestation","attest_author":"https://pith.science/pith/3L23C4Y4REGKA2EYBNV33CGMTS/action/author_attestation","sign_citation":"https://pith.science/pith/3L23C4Y4REGKA2EYBNV33CGMTS/action/citation_signature","submit_replication":"https://pith.science/pith/3L23C4Y4REGKA2EYBNV33CGMTS/action/replication_record"}},"created_at":"2026-06-02T02:04:16.708904+00:00","updated_at":"2026-06-02T02:04:16.708904+00:00"}