{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:NDHIZ2TZFJUTXWKLYLCEFWN3WE","short_pith_number":"pith:NDHIZ2TZ","canonical_record":{"source":{"id":"2606.08096","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-06T10:48:28Z","cross_cats_sorted":[],"title_canon_sha256":"1803ca436033c1a293351d5084287a8c3dba977e7ea723b4758d9be303788fa3","abstract_canon_sha256":"cb3d431b28dae66aaf1a9752b6f7e7995dc8d26db3ddb39e181ae0c580e28e8e"},"schema_version":"1.0"},"canonical_sha256":"68ce8cea792a693bd94bc2c442d9bbb10a74ff0ca9d6c6a0b389a839a2592615","source":{"kind":"arxiv","id":"2606.08096","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08096","created_at":"2026-06-09T01:05:26Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08096v1","created_at":"2026-06-09T01:05:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08096","created_at":"2026-06-09T01:05:26Z"},{"alias_kind":"pith_short_12","alias_value":"NDHIZ2TZFJUT","created_at":"2026-06-09T01:05:26Z"},{"alias_kind":"pith_short_16","alias_value":"NDHIZ2TZFJUTXWKL","created_at":"2026-06-09T01:05:26Z"},{"alias_kind":"pith_short_8","alias_value":"NDHIZ2TZ","created_at":"2026-06-09T01:05:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:NDHIZ2TZFJUTXWKLYLCEFWN3WE","target":"record","payload":{"canonical_record":{"source":{"id":"2606.08096","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-06T10:48:28Z","cross_cats_sorted":[],"title_canon_sha256":"1803ca436033c1a293351d5084287a8c3dba977e7ea723b4758d9be303788fa3","abstract_canon_sha256":"cb3d431b28dae66aaf1a9752b6f7e7995dc8d26db3ddb39e181ae0c580e28e8e"},"schema_version":"1.0"},"canonical_sha256":"68ce8cea792a693bd94bc2c442d9bbb10a74ff0ca9d6c6a0b389a839a2592615","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:26.282084Z","signature_b64":"Qd6jsg088pzVFqH3cpZaG9T3Dm21ScIr/l6vQPIM5HUgxfm2KSoPggYiUFKo1c9O4MejQVblCdLtC96gm5YKDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68ce8cea792a693bd94bc2c442d9bbb10a74ff0ca9d6c6a0b389a839a2592615","last_reissued_at":"2026-06-09T01:05:26.281624Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:26.281624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.08096","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":"2026-06-09T01:05:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GdVDsdD5ChD2gkt7usjbWCofnCP9A+4vfTA2dRJnVEyUBwL+yZBZW9rWGXx2h++LqGIwHu+T5wKPHHXHX5PZCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T10:49:15.683242Z"},"content_sha256":"ead81042f33fd57afdbd7cf21c87f5fb1549ae155c5424b584d89819a307af25","schema_version":"1.0","event_id":"sha256:ead81042f33fd57afdbd7cf21c87f5fb1549ae155c5424b584d89819a307af25"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:NDHIZ2TZFJUTXWKLYLCEFWN3WE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Identifying unique developers in OSS projects: A family of models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Alexander Bakhtin, Davide Taibi, Matteo Esposito, Ruoyu Su, Valentina Lenarduzzi","submitted_at":"2026-06-06T10:48:28Z","abstract_excerpt":"Organizational and logical coupling metrics require reliable identification of unique developers. In OSS, commit metadata is limited to names and emails, and the same developer may appear under multiple aliases, which can distort coupling measurements if de-duplication is missing. We aim to build a scalable and accurate pipeline for OSS developer de-duplication and to provide guidance on choosing a model based on precision vs. computational effort. We use Indel similarity as a baseline, then run an LLM-assisted matching process with manual validation to create a large dataset of duplicate iden"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08096","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/2606.08096/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-09T01:05:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AY2k3xBe4k96zDIPPvadgQhCsZmyZy5i6sY3dsx9U9g81qnozKTjuZQBCx7DDoVxWJ+XVCnelrDLzyyRpXueAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T10:49:15.683622Z"},"content_sha256":"cd7c910e1a8871220d38489ae04c0b4fb0db15ad621e6c4e02eb7158032ee175","schema_version":"1.0","event_id":"sha256:cd7c910e1a8871220d38489ae04c0b4fb0db15ad621e6c4e02eb7158032ee175"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NDHIZ2TZFJUTXWKLYLCEFWN3WE/bundle.json","state_url":"https://pith.science/pith/NDHIZ2TZFJUTXWKLYLCEFWN3WE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NDHIZ2TZFJUTXWKLYLCEFWN3WE/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":"2026-06-30T10:49:15Z","links":{"resolver":"https://pith.science/pith/NDHIZ2TZFJUTXWKLYLCEFWN3WE","bundle":"https://pith.science/pith/NDHIZ2TZFJUTXWKLYLCEFWN3WE/bundle.json","state":"https://pith.science/pith/NDHIZ2TZFJUTXWKLYLCEFWN3WE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NDHIZ2TZFJUTXWKLYLCEFWN3WE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NDHIZ2TZFJUTXWKLYLCEFWN3WE","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":"cb3d431b28dae66aaf1a9752b6f7e7995dc8d26db3ddb39e181ae0c580e28e8e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-06T10:48:28Z","title_canon_sha256":"1803ca436033c1a293351d5084287a8c3dba977e7ea723b4758d9be303788fa3"},"schema_version":"1.0","source":{"id":"2606.08096","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08096","created_at":"2026-06-09T01:05:26Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08096v1","created_at":"2026-06-09T01:05:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08096","created_at":"2026-06-09T01:05:26Z"},{"alias_kind":"pith_short_12","alias_value":"NDHIZ2TZFJUT","created_at":"2026-06-09T01:05:26Z"},{"alias_kind":"pith_short_16","alias_value":"NDHIZ2TZFJUTXWKL","created_at":"2026-06-09T01:05:26Z"},{"alias_kind":"pith_short_8","alias_value":"NDHIZ2TZ","created_at":"2026-06-09T01:05:26Z"}],"graph_snapshots":[{"event_id":"sha256:cd7c910e1a8871220d38489ae04c0b4fb0db15ad621e6c4e02eb7158032ee175","target":"graph","created_at":"2026-06-09T01:05:26Z","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/2606.08096/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Organizational and logical coupling metrics require reliable identification of unique developers. In OSS, commit metadata is limited to names and emails, and the same developer may appear under multiple aliases, which can distort coupling measurements if de-duplication is missing. We aim to build a scalable and accurate pipeline for OSS developer de-duplication and to provide guidance on choosing a model based on precision vs. computational effort. We use Indel similarity as a baseline, then run an LLM-assisted matching process with manual validation to create a large dataset of duplicate iden","authors_text":"Alexander Bakhtin, Davide Taibi, Matteo Esposito, Ruoyu Su, Valentina Lenarduzzi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-06T10:48:28Z","title":"Identifying unique developers in OSS projects: A family of models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08096","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:ead81042f33fd57afdbd7cf21c87f5fb1549ae155c5424b584d89819a307af25","target":"record","created_at":"2026-06-09T01:05:26Z","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":"cb3d431b28dae66aaf1a9752b6f7e7995dc8d26db3ddb39e181ae0c580e28e8e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-06T10:48:28Z","title_canon_sha256":"1803ca436033c1a293351d5084287a8c3dba977e7ea723b4758d9be303788fa3"},"schema_version":"1.0","source":{"id":"2606.08096","kind":"arxiv","version":1}},"canonical_sha256":"68ce8cea792a693bd94bc2c442d9bbb10a74ff0ca9d6c6a0b389a839a2592615","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"68ce8cea792a693bd94bc2c442d9bbb10a74ff0ca9d6c6a0b389a839a2592615","first_computed_at":"2026-06-09T01:05:26.281624Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:05:26.281624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Qd6jsg088pzVFqH3cpZaG9T3Dm21ScIr/l6vQPIM5HUgxfm2KSoPggYiUFKo1c9O4MejQVblCdLtC96gm5YKDg==","signature_status":"signed_v1","signed_at":"2026-06-09T01:05:26.282084Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.08096","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ead81042f33fd57afdbd7cf21c87f5fb1549ae155c5424b584d89819a307af25","sha256:cd7c910e1a8871220d38489ae04c0b4fb0db15ad621e6c4e02eb7158032ee175"],"state_sha256":"08210862b56ddacaa4bec73cf67ff0871d5eb749d00952623db4a57904387551"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z7Ij5gNiTMXmqBLv2ejtIRisYccUdqNHfnV/GxgfG8PjKrzv8gXyVuksfMexnWtzMQeBc8IpXia6FgOERScCAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T10:49:15.685704Z","bundle_sha256":"dc7ce7537ae8e09be4b3effa284b7648b4869bd9470434844d0fcfc371b05492"}}