{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:A3HK4XLVCVSZB3CX2FT4SDQ7LL","short_pith_number":"pith:A3HK4XLV","canonical_record":{"source":{"id":"2605.13310","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2026-05-13T10:25:43Z","cross_cats_sorted":["cs.DB","cs.IR"],"title_canon_sha256":"1f10344179848d48fd0478d8fb0c6c91b0f83c8c040a0603adc49f4d43409b76","abstract_canon_sha256":"2eef9f9235f69367e27d5caaf2f61474d26b2fbc1a2d16f198234f743d922893"},"schema_version":"1.0"},"canonical_sha256":"06ceae5d75156590ec57d167c90e1f5acf425f677f761673e1c506049efe9d67","source":{"kind":"arxiv","id":"2605.13310","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13310","created_at":"2026-05-18T02:44:48Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13310v1","created_at":"2026-05-18T02:44:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13310","created_at":"2026-05-18T02:44:48Z"},{"alias_kind":"pith_short_12","alias_value":"A3HK4XLVCVSZ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"A3HK4XLVCVSZB3CX","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"A3HK4XLV","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:A3HK4XLVCVSZB3CX2FT4SDQ7LL","target":"record","payload":{"canonical_record":{"source":{"id":"2605.13310","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2026-05-13T10:25:43Z","cross_cats_sorted":["cs.DB","cs.IR"],"title_canon_sha256":"1f10344179848d48fd0478d8fb0c6c91b0f83c8c040a0603adc49f4d43409b76","abstract_canon_sha256":"2eef9f9235f69367e27d5caaf2f61474d26b2fbc1a2d16f198234f743d922893"},"schema_version":"1.0"},"canonical_sha256":"06ceae5d75156590ec57d167c90e1f5acf425f677f761673e1c506049efe9d67","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:48.885117Z","signature_b64":"ilBrRIHF6Z0MrpaVEU1BYPuIijy5QfqjqjZsFe/+JpAClsi/ikLlIoHKiphhLmjr981NRnRv3iCZkiGUjYobCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06ceae5d75156590ec57d167c90e1f5acf425f677f761673e1c506049efe9d67","last_reissued_at":"2026-05-18T02:44:48.884665Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:48.884665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.13310","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5bFQ1qArpNA8ijI4ic8XYNLB8wNVLXsv7hp/GkNlVryAWTU3KPheW/maVXnb1pOkPYdx4J3iEyqGRea0MlWBCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T00:56:35.150853Z"},"content_sha256":"018d290a57a04abd78f6670021d0c39d7c7968f63c2aa2b9e766d68ce11e74c0","schema_version":"1.0","event_id":"sha256:018d290a57a04abd78f6670021d0c39d7c7968f63c2aa2b9e766d68ce11e74c0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:A3HK4XLVCVSZB3CX2FT4SDQ7LL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SemRepo: A Knowledge Graph for Research Software and Its Scholarly Ecosystem","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"SemRepo creates a knowledge graph linking nearly 200,000 research GitHub repositories to publications, authors, and artifacts.","cross_cats":["cs.DB","cs.IR"],"primary_cat":"cs.DL","authors_text":"Abdul Rafay, David Lamprecht, Michael F\\\"arber, Yuni Susanti","submitted_at":"2026-05-13T10:25:43Z","abstract_excerpt":"We present SemRepo, an RDF knowledge graph comprising over 81 million triples describing nearly 200,000 GitHub repositories associated with scientific research. SemRepo captures repository-level metadata, such as contributors, issues, and programming languages, and interlinks this information with external scholarly knowledge graphs. In particular, repository authors are linked to their profiles in SemOpenAlex, repositories are connected to scholarly publications in LPWC, and research artifacts, such as datasets and experiments, are linked via MLSea-KG. This integration enables queries that sp"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"By unifying research software with its scholarly context in a single graph, SemRepo provides an important infrastructure for large-scale analysis of software within the broader scientific research ecosystem.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The interlinks between GitHub repositories, SemOpenAlex author profiles, LPWC publications, and MLSea-KG artifacts are sufficiently accurate and complete to support reliable provenance reconstruction and systematic identification of reproducibility risks.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SemRepo is a new RDF knowledge graph integrating GitHub research repositories with scholarly knowledge graphs to enable cross-platform queries on software, publications, and artifacts.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"SemRepo creates a knowledge graph linking nearly 200,000 research GitHub repositories to publications, authors, and artifacts.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"157f65272997a0c7ec44117c5cf573f82cc40db2386a80abcca9a82b2767efa0"},"source":{"id":"2605.13310","kind":"arxiv","version":1},"verdict":{"id":"ab58ee1b-525b-4ca9-84ab-aee9a112e8e2","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T18:59:21.983377Z","strongest_claim":"By unifying research software with its scholarly context in a single graph, SemRepo provides an important infrastructure for large-scale analysis of software within the broader scientific research ecosystem.","one_line_summary":"SemRepo is a new RDF knowledge graph integrating GitHub research repositories with scholarly knowledge graphs to enable cross-platform queries on software, publications, and artifacts.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The interlinks between GitHub repositories, SemOpenAlex author profiles, LPWC publications, and MLSea-KG artifacts are sufficiently accurate and complete to support reliable provenance reconstruction and systematic identification of reproducibility risks.","pith_extraction_headline":"SemRepo creates a knowledge graph linking nearly 200,000 research GitHub repositories to publications, authors, and artifacts."},"references":{"count":28,"sample":[{"doi":"","year":2020,"title":"Bibliothek Forschung und Praxis44(3), 516–529 (2020)","work_id":"d6b480cf-6d9b-4238-895b-36406965986e","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1109/icsme.2018.00018","year":2018,"title":"Gilpin, David Bau, Ben Z","work_id":"077db98f-219d-4554-8b2c-f2ce190811a6","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1109/icsme.2016.31","year":2016,"title":"In: 2016 IEEE International Conference on Software Maintenance and Evolution (ICSME)","work_id":"16c59a7b-9f39-4c00-818c-70d706428caa","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2016,"title":"PLOS ONE11(4), e0152976 (2016).https://doi.org/10.1371/ journal.pone.0152976","work_id":"d3cc9619-17ff-45f2-85fe-1e1738a687ed","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2017,"title":"Kyoto, Japan (Sep 2017),https://www.softwareheritage","work_id":"188fff2d-dc9e-4828-ac06-1d9ffdcd476b","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":28,"snapshot_sha256":"a780205ec7f38edb286b5c7c46834ca2bf333571273934fa5505fd74ee51c4be","internal_anchors":0},"formal_canon":{"evidence_count":1,"snapshot_sha256":"99db0011f39f734f79849d455099a284afa0c5574a21f612880600cbf0f3dae4"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"ab58ee1b-525b-4ca9-84ab-aee9a112e8e2"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7dkUB0ERp7h83E61NtxnnGScdfbSkuFjr/AmFqSO448KzKSKCiWTFpChhhyWfL9v2fPK+zBNZ/ooafcNPx4QBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T00:56:35.152034Z"},"content_sha256":"eccb9e5bb9e28248e29ee193860155a3a1d1d4381356afffc15282361edd2961","schema_version":"1.0","event_id":"sha256:eccb9e5bb9e28248e29ee193860155a3a1d1d4381356afffc15282361edd2961"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A3HK4XLVCVSZB3CX2FT4SDQ7LL/bundle.json","state_url":"https://pith.science/pith/A3HK4XLVCVSZB3CX2FT4SDQ7LL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A3HK4XLVCVSZB3CX2FT4SDQ7LL/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-22T00:56:35Z","links":{"resolver":"https://pith.science/pith/A3HK4XLVCVSZB3CX2FT4SDQ7LL","bundle":"https://pith.science/pith/A3HK4XLVCVSZB3CX2FT4SDQ7LL/bundle.json","state":"https://pith.science/pith/A3HK4XLVCVSZB3CX2FT4SDQ7LL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A3HK4XLVCVSZB3CX2FT4SDQ7LL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:A3HK4XLVCVSZB3CX2FT4SDQ7LL","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":"2eef9f9235f69367e27d5caaf2f61474d26b2fbc1a2d16f198234f743d922893","cross_cats_sorted":["cs.DB","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2026-05-13T10:25:43Z","title_canon_sha256":"1f10344179848d48fd0478d8fb0c6c91b0f83c8c040a0603adc49f4d43409b76"},"schema_version":"1.0","source":{"id":"2605.13310","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13310","created_at":"2026-05-18T02:44:48Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13310v1","created_at":"2026-05-18T02:44:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13310","created_at":"2026-05-18T02:44:48Z"},{"alias_kind":"pith_short_12","alias_value":"A3HK4XLVCVSZ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"A3HK4XLVCVSZB3CX","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"A3HK4XLV","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:eccb9e5bb9e28248e29ee193860155a3a1d1d4381356afffc15282361edd2961","target":"graph","created_at":"2026-05-18T02:44:48Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"By unifying research software with its scholarly context in a single graph, SemRepo provides an important infrastructure for large-scale analysis of software within the broader scientific research ecosystem."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The interlinks between GitHub repositories, SemOpenAlex author profiles, LPWC publications, and MLSea-KG artifacts are sufficiently accurate and complete to support reliable provenance reconstruction and systematic identification of reproducibility risks."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"SemRepo is a new RDF knowledge graph integrating GitHub research repositories with scholarly knowledge graphs to enable cross-platform queries on software, publications, and artifacts."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"SemRepo creates a knowledge graph linking nearly 200,000 research GitHub repositories to publications, authors, and artifacts."}],"snapshot_sha256":"157f65272997a0c7ec44117c5cf573f82cc40db2386a80abcca9a82b2767efa0"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"99db0011f39f734f79849d455099a284afa0c5574a21f612880600cbf0f3dae4"},"paper":{"abstract_excerpt":"We present SemRepo, an RDF knowledge graph comprising over 81 million triples describing nearly 200,000 GitHub repositories associated with scientific research. SemRepo captures repository-level metadata, such as contributors, issues, and programming languages, and interlinks this information with external scholarly knowledge graphs. In particular, repository authors are linked to their profiles in SemOpenAlex, repositories are connected to scholarly publications in LPWC, and research artifacts, such as datasets and experiments, are linked via MLSea-KG. This integration enables queries that sp","authors_text":"Abdul Rafay, David Lamprecht, Michael F\\\"arber, Yuni Susanti","cross_cats":["cs.DB","cs.IR"],"headline":"SemRepo creates a knowledge graph linking nearly 200,000 research GitHub repositories to publications, authors, and artifacts.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2026-05-13T10:25:43Z","title":"SemRepo: A Knowledge Graph for Research Software and Its Scholarly Ecosystem"},"references":{"count":28,"internal_anchors":0,"resolved_work":28,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Bibliothek Forschung und Praxis44(3), 516–529 (2020)","work_id":"d6b480cf-6d9b-4238-895b-36406965986e","year":2020},{"cited_arxiv_id":"","doi":"10.1109/icsme.2018.00018","is_internal_anchor":false,"ref_index":2,"title":"Gilpin, David Bau, Ben Z","work_id":"077db98f-219d-4554-8b2c-f2ce190811a6","year":2018},{"cited_arxiv_id":"","doi":"10.1109/icsme.2016.31","is_internal_anchor":false,"ref_index":3,"title":"In: 2016 IEEE International Conference on Software Maintenance and Evolution (ICSME)","work_id":"16c59a7b-9f39-4c00-818c-70d706428caa","year":2016},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"PLOS ONE11(4), e0152976 (2016).https://doi.org/10.1371/ journal.pone.0152976","work_id":"d3cc9619-17ff-45f2-85fe-1e1738a687ed","year":2016},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Kyoto, Japan (Sep 2017),https://www.softwareheritage","work_id":"188fff2d-dc9e-4828-ac06-1d9ffdcd476b","year":2017}],"snapshot_sha256":"a780205ec7f38edb286b5c7c46834ca2bf333571273934fa5505fd74ee51c4be"},"source":{"id":"2605.13310","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T18:59:21.983377Z","id":"ab58ee1b-525b-4ca9-84ab-aee9a112e8e2","model_set":{"reader":"grok-4.3"},"one_line_summary":"SemRepo is a new RDF knowledge graph integrating GitHub research repositories with scholarly knowledge graphs to enable cross-platform queries on software, publications, and artifacts.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"SemRepo creates a knowledge graph linking nearly 200,000 research GitHub repositories to publications, authors, and artifacts.","strongest_claim":"By unifying research software with its scholarly context in a single graph, SemRepo provides an important infrastructure for large-scale analysis of software within the broader scientific research ecosystem.","weakest_assumption":"The interlinks between GitHub repositories, SemOpenAlex author profiles, LPWC publications, and MLSea-KG artifacts are sufficiently accurate and complete to support reliable provenance reconstruction and systematic identification of reproducibility risks."}},"verdict_id":"ab58ee1b-525b-4ca9-84ab-aee9a112e8e2"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:018d290a57a04abd78f6670021d0c39d7c7968f63c2aa2b9e766d68ce11e74c0","target":"record","created_at":"2026-05-18T02:44:48Z","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":"2eef9f9235f69367e27d5caaf2f61474d26b2fbc1a2d16f198234f743d922893","cross_cats_sorted":["cs.DB","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2026-05-13T10:25:43Z","title_canon_sha256":"1f10344179848d48fd0478d8fb0c6c91b0f83c8c040a0603adc49f4d43409b76"},"schema_version":"1.0","source":{"id":"2605.13310","kind":"arxiv","version":1}},"canonical_sha256":"06ceae5d75156590ec57d167c90e1f5acf425f677f761673e1c506049efe9d67","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"06ceae5d75156590ec57d167c90e1f5acf425f677f761673e1c506049efe9d67","first_computed_at":"2026-05-18T02:44:48.884665Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:48.884665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ilBrRIHF6Z0MrpaVEU1BYPuIijy5QfqjqjZsFe/+JpAClsi/ikLlIoHKiphhLmjr981NRnRv3iCZkiGUjYobCg==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:48.885117Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13310","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:018d290a57a04abd78f6670021d0c39d7c7968f63c2aa2b9e766d68ce11e74c0","sha256:eccb9e5bb9e28248e29ee193860155a3a1d1d4381356afffc15282361edd2961"],"state_sha256":"9f740e1b15575d52fe325b47e804cdacf356b27cf81a665c5e6bb482e9bdb82b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cBwsKNkTFzt+juyhqRO+RS10MwECmYiNSU9UxLjkLAcpMzycKiPL7krKNZ8QGAiNjfdDAYrNRa16b4wgdB2aAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-22T00:56:35.156629Z","bundle_sha256":"7e577822bd4f407219e86b3e0da79c5cae38c58b443cffdb5202d5a4f028ae90"}}