{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:SC3RRNXF7CV5LDSIW2FSNW3OWR","short_pith_number":"pith:SC3RRNXF","canonical_record":{"source":{"id":"2208.00269","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2022-07-30T16:27:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"398c7be82aa2b150cc62018d07a8053c2a41ac16abf31faaf7b70509256e0b79","abstract_canon_sha256":"25afa80e1a5a121c867b29b2f56585d9f99ea349db9fb40ade3b879248f76a88"},"schema_version":"1.0"},"canonical_sha256":"90b718b6e5f8abd58e48b68b26db6eb4445310b6d5aeee72ac2c2cd16840f908","source":{"kind":"arxiv","id":"2208.00269","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.00269","created_at":"2026-07-05T04:44:49Z"},{"alias_kind":"arxiv_version","alias_value":"2208.00269v1","created_at":"2026-07-05T04:44:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.00269","created_at":"2026-07-05T04:44:49Z"},{"alias_kind":"pith_short_12","alias_value":"SC3RRNXF7CV5","created_at":"2026-07-05T04:44:49Z"},{"alias_kind":"pith_short_16","alias_value":"SC3RRNXF7CV5LDSI","created_at":"2026-07-05T04:44:49Z"},{"alias_kind":"pith_short_8","alias_value":"SC3RRNXF","created_at":"2026-07-05T04:44:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:SC3RRNXF7CV5LDSIW2FSNW3OWR","target":"record","payload":{"canonical_record":{"source":{"id":"2208.00269","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2022-07-30T16:27:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"398c7be82aa2b150cc62018d07a8053c2a41ac16abf31faaf7b70509256e0b79","abstract_canon_sha256":"25afa80e1a5a121c867b29b2f56585d9f99ea349db9fb40ade3b879248f76a88"},"schema_version":"1.0"},"canonical_sha256":"90b718b6e5f8abd58e48b68b26db6eb4445310b6d5aeee72ac2c2cd16840f908","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:44:49.690190Z","signature_b64":"pe2ZrLcv41hCv+H+wAoHB7hv5Spqrnu932eqo3mZdIpxeOmmTV83+YVjLoGvsE4wkK0jIVdx6UsX+KuNUJYrCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90b718b6e5f8abd58e48b68b26db6eb4445310b6d5aeee72ac2c2cd16840f908","last_reissued_at":"2026-07-05T04:44:49.689754Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:44:49.689754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2208.00269","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":"2026-07-05T04:44:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w5onrpWsESMRDRuFI66YVoYmaovKPePCO6jb2y3rI0sXE5JkMu2PdXz4Mo7ErSa02/G3kbjjga106hfzzCKIAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T16:20:18.997258Z"},"content_sha256":"b5c2f6fd2b787e29566809786d5e67a3d97d413958a5327cf813fade358dad57","schema_version":"1.0","event_id":"sha256:b5c2f6fd2b787e29566809786d5e67a3d97d413958a5327cf813fade358dad57"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:SC3RRNXF7CV5LDSIW2FSNW3OWR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Automatically Categorising GitHub Repositories by Application Domain","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Bruno Cartaxo, Christoph Treude, Francisco Zanartu, Gustavo Pinto, Hudson Silva Borges, Markus Wagner, Pedro Moura","submitted_at":"2022-07-30T16:27:16Z","abstract_excerpt":"GitHub is the largest host of open source software on the Internet. This large, freely accessible database has attracted the attention of practitioners and researchers alike. But as GitHub's growth continues, it is becoming increasingly hard to navigate the plethora of repositories which span a wide range of domains. Past work has shown that taking the application domain into account is crucial for tasks such as predicting the popularity of a repository and reasoning about project quality. In this work, we build on a previously annotated dataset of 5,000 GitHub repositories to design an automa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.00269","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/2208.00269/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":"2026-07-05T04:44:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y1ZkDItBPX4MxFS/eUNg9UUZzq2rmXxeBweHvTnkxdOCQGSHgaPhPMVsynfGV+xYf9qLwwEnpZjeIRZNibsxDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T16:20:18.997658Z"},"content_sha256":"29652e4a1e04f6f53002a13d8ad16f297e8efed3a883c235778b8527b57d4974","schema_version":"1.0","event_id":"sha256:29652e4a1e04f6f53002a13d8ad16f297e8efed3a883c235778b8527b57d4974"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SC3RRNXF7CV5LDSIW2FSNW3OWR/bundle.json","state_url":"https://pith.science/pith/SC3RRNXF7CV5LDSIW2FSNW3OWR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SC3RRNXF7CV5LDSIW2FSNW3OWR/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":"2026-07-08T16:20:18Z","links":{"resolver":"https://pith.science/pith/SC3RRNXF7CV5LDSIW2FSNW3OWR","bundle":"https://pith.science/pith/SC3RRNXF7CV5LDSIW2FSNW3OWR/bundle.json","state":"https://pith.science/pith/SC3RRNXF7CV5LDSIW2FSNW3OWR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SC3RRNXF7CV5LDSIW2FSNW3OWR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:SC3RRNXF7CV5LDSIW2FSNW3OWR","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":"25afa80e1a5a121c867b29b2f56585d9f99ea349db9fb40ade3b879248f76a88","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2022-07-30T16:27:16Z","title_canon_sha256":"398c7be82aa2b150cc62018d07a8053c2a41ac16abf31faaf7b70509256e0b79"},"schema_version":"1.0","source":{"id":"2208.00269","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.00269","created_at":"2026-07-05T04:44:49Z"},{"alias_kind":"arxiv_version","alias_value":"2208.00269v1","created_at":"2026-07-05T04:44:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.00269","created_at":"2026-07-05T04:44:49Z"},{"alias_kind":"pith_short_12","alias_value":"SC3RRNXF7CV5","created_at":"2026-07-05T04:44:49Z"},{"alias_kind":"pith_short_16","alias_value":"SC3RRNXF7CV5LDSI","created_at":"2026-07-05T04:44:49Z"},{"alias_kind":"pith_short_8","alias_value":"SC3RRNXF","created_at":"2026-07-05T04:44:49Z"}],"graph_snapshots":[{"event_id":"sha256:29652e4a1e04f6f53002a13d8ad16f297e8efed3a883c235778b8527b57d4974","target":"graph","created_at":"2026-07-05T04:44:49Z","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/2208.00269/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"GitHub is the largest host of open source software on the Internet. This large, freely accessible database has attracted the attention of practitioners and researchers alike. But as GitHub's growth continues, it is becoming increasingly hard to navigate the plethora of repositories which span a wide range of domains. Past work has shown that taking the application domain into account is crucial for tasks such as predicting the popularity of a repository and reasoning about project quality. In this work, we build on a previously annotated dataset of 5,000 GitHub repositories to design an automa","authors_text":"Bruno Cartaxo, Christoph Treude, Francisco Zanartu, Gustavo Pinto, Hudson Silva Borges, Markus Wagner, Pedro Moura","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2022-07-30T16:27:16Z","title":"Automatically Categorising GitHub Repositories by Application Domain"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.00269","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:b5c2f6fd2b787e29566809786d5e67a3d97d413958a5327cf813fade358dad57","target":"record","created_at":"2026-07-05T04:44:49Z","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":"25afa80e1a5a121c867b29b2f56585d9f99ea349db9fb40ade3b879248f76a88","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2022-07-30T16:27:16Z","title_canon_sha256":"398c7be82aa2b150cc62018d07a8053c2a41ac16abf31faaf7b70509256e0b79"},"schema_version":"1.0","source":{"id":"2208.00269","kind":"arxiv","version":1}},"canonical_sha256":"90b718b6e5f8abd58e48b68b26db6eb4445310b6d5aeee72ac2c2cd16840f908","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"90b718b6e5f8abd58e48b68b26db6eb4445310b6d5aeee72ac2c2cd16840f908","first_computed_at":"2026-07-05T04:44:49.689754Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:44:49.689754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pe2ZrLcv41hCv+H+wAoHB7hv5Spqrnu932eqo3mZdIpxeOmmTV83+YVjLoGvsE4wkK0jIVdx6UsX+KuNUJYrCA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:44:49.690190Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.00269","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5c2f6fd2b787e29566809786d5e67a3d97d413958a5327cf813fade358dad57","sha256:29652e4a1e04f6f53002a13d8ad16f297e8efed3a883c235778b8527b57d4974"],"state_sha256":"e7895990681c1bf26bdf20b74d508d66cbcbc8ef4a9c5b4e5d522f203305381e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6LLuyfdLQIOCxgM5/1kpfg73DVpt3hQLobnnF3gOQjeieV/3vyXxjbi/287KMe9MrXHz/gjdoDUWIHuWxVQSBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T16:20:18.999733Z","bundle_sha256":"00d2b324705533c003b48e25cfe79d20df61eb20739bf16471fb6acdd0605665"}}