{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:L2DPIVJRA6FZ4WGSK62ISP4BP3","short_pith_number":"pith:L2DPIVJR","canonical_record":{"source":{"id":"2303.06286","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-03-11T02:45:55Z","cross_cats_sorted":[],"title_canon_sha256":"d4998239696db94b5dae8a62f95528aa86fe3e288014f3714063ed5db5d879da","abstract_canon_sha256":"a1f7124d331fb5a75f47db88e03fd2989e198ab3b46d93bba4bc4baa5a0ce342"},"schema_version":"1.0"},"canonical_sha256":"5e86f45531078b9e58d257b4893f817eeb7714ebdae632ec2ce1f1765e7086eb","source":{"kind":"arxiv","id":"2303.06286","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.06286","created_at":"2026-07-05T05:50:16Z"},{"alias_kind":"arxiv_version","alias_value":"2303.06286v1","created_at":"2026-07-05T05:50:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.06286","created_at":"2026-07-05T05:50:16Z"},{"alias_kind":"pith_short_12","alias_value":"L2DPIVJRA6FZ","created_at":"2026-07-05T05:50:16Z"},{"alias_kind":"pith_short_16","alias_value":"L2DPIVJRA6FZ4WGS","created_at":"2026-07-05T05:50:16Z"},{"alias_kind":"pith_short_8","alias_value":"L2DPIVJR","created_at":"2026-07-05T05:50:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:L2DPIVJRA6FZ4WGSK62ISP4BP3","target":"record","payload":{"canonical_record":{"source":{"id":"2303.06286","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-03-11T02:45:55Z","cross_cats_sorted":[],"title_canon_sha256":"d4998239696db94b5dae8a62f95528aa86fe3e288014f3714063ed5db5d879da","abstract_canon_sha256":"a1f7124d331fb5a75f47db88e03fd2989e198ab3b46d93bba4bc4baa5a0ce342"},"schema_version":"1.0"},"canonical_sha256":"5e86f45531078b9e58d257b4893f817eeb7714ebdae632ec2ce1f1765e7086eb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:50:16.808584Z","signature_b64":"IQGZeCsRgfsUC61KhJWNAo+I3WXkWlz1s9P1mNubrYlZaGcqg3mzCGsLjps7QsJj2onAEGV5J/7GQhgTX6v9DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e86f45531078b9e58d257b4893f817eeb7714ebdae632ec2ce1f1765e7086eb","last_reissued_at":"2026-07-05T05:50:16.808036Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:50:16.808036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.06286","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":"2026-07-05T05:50:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hU1sXV/9NY1T1B3buqa1vwBzqMBXc3hjYV+rTC4t51JGQNc2qP4kF2ZJoumE5fGEKZTScPTNHzP9klUr28ZQBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:48:27.285016Z"},"content_sha256":"fa9bece13a0b3cd473a4babe6752e6ee7e1a180c67f6c86bf84143366848e3d9","schema_version":"1.0","event_id":"sha256:fa9bece13a0b3cd473a4babe6752e6ee7e1a180c67f6c86bf84143366848e3d9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:L2DPIVJRA6FZ4WGSK62ISP4BP3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"NICHE: A Curated Dataset of Engineered Machine Learning Projects in Python","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Camellia Lok, Constance Tan, David Lo, Ferdian Thung, Fiona Wee, Haodi Qi, Jack Phan, Qijin Tay, Ratnadira Widyasari, Sheng Qin Sim, Zhou Yang","submitted_at":"2023-03-11T02:45:55Z","abstract_excerpt":"Machine learning (ML) has gained much attention and been incorporated into our daily lives. While there are numerous publicly available ML projects on open source platforms such as GitHub, there have been limited attempts in filtering those projects to curate ML projects of high quality. The limited availability of such a high-quality dataset poses an obstacle in understanding ML projects. To help clear this obstacle, we present NICHE, a manually labelled dataset consisting of 572 ML projects. Based on evidences of good software engineering practices, we label 441 of these projects as engineer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.06286","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/2303.06286/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":"2026-07-05T05:50:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bz99OFYFoo40EaFYIdOB1ojJwBhs9kDUq8ZnOZjpfKy2A5sl7/oP56VgunpywRE3+Tg9D0YmlCuxeoZzIdltDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:48:27.285659Z"},"content_sha256":"5cb43c9dec30be6e0830df318956b915b4fd3532cadbf6a95cdd75d24f77d9df","schema_version":"1.0","event_id":"sha256:5cb43c9dec30be6e0830df318956b915b4fd3532cadbf6a95cdd75d24f77d9df"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L2DPIVJRA6FZ4WGSK62ISP4BP3/bundle.json","state_url":"https://pith.science/pith/L2DPIVJRA6FZ4WGSK62ISP4BP3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L2DPIVJRA6FZ4WGSK62ISP4BP3/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":"2026-07-07T07:48:27Z","links":{"resolver":"https://pith.science/pith/L2DPIVJRA6FZ4WGSK62ISP4BP3","bundle":"https://pith.science/pith/L2DPIVJRA6FZ4WGSK62ISP4BP3/bundle.json","state":"https://pith.science/pith/L2DPIVJRA6FZ4WGSK62ISP4BP3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L2DPIVJRA6FZ4WGSK62ISP4BP3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:L2DPIVJRA6FZ4WGSK62ISP4BP3","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":"a1f7124d331fb5a75f47db88e03fd2989e198ab3b46d93bba4bc4baa5a0ce342","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-03-11T02:45:55Z","title_canon_sha256":"d4998239696db94b5dae8a62f95528aa86fe3e288014f3714063ed5db5d879da"},"schema_version":"1.0","source":{"id":"2303.06286","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.06286","created_at":"2026-07-05T05:50:16Z"},{"alias_kind":"arxiv_version","alias_value":"2303.06286v1","created_at":"2026-07-05T05:50:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.06286","created_at":"2026-07-05T05:50:16Z"},{"alias_kind":"pith_short_12","alias_value":"L2DPIVJRA6FZ","created_at":"2026-07-05T05:50:16Z"},{"alias_kind":"pith_short_16","alias_value":"L2DPIVJRA6FZ4WGS","created_at":"2026-07-05T05:50:16Z"},{"alias_kind":"pith_short_8","alias_value":"L2DPIVJR","created_at":"2026-07-05T05:50:16Z"}],"graph_snapshots":[{"event_id":"sha256:5cb43c9dec30be6e0830df318956b915b4fd3532cadbf6a95cdd75d24f77d9df","target":"graph","created_at":"2026-07-05T05:50:16Z","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/2303.06286/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Machine learning (ML) has gained much attention and been incorporated into our daily lives. While there are numerous publicly available ML projects on open source platforms such as GitHub, there have been limited attempts in filtering those projects to curate ML projects of high quality. The limited availability of such a high-quality dataset poses an obstacle in understanding ML projects. To help clear this obstacle, we present NICHE, a manually labelled dataset consisting of 572 ML projects. Based on evidences of good software engineering practices, we label 441 of these projects as engineer","authors_text":"Camellia Lok, Constance Tan, David Lo, Ferdian Thung, Fiona Wee, Haodi Qi, Jack Phan, Qijin Tay, Ratnadira Widyasari, Sheng Qin Sim, Zhou Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-03-11T02:45:55Z","title":"NICHE: A Curated Dataset of Engineered Machine Learning Projects in Python"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.06286","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:fa9bece13a0b3cd473a4babe6752e6ee7e1a180c67f6c86bf84143366848e3d9","target":"record","created_at":"2026-07-05T05:50:16Z","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":"a1f7124d331fb5a75f47db88e03fd2989e198ab3b46d93bba4bc4baa5a0ce342","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-03-11T02:45:55Z","title_canon_sha256":"d4998239696db94b5dae8a62f95528aa86fe3e288014f3714063ed5db5d879da"},"schema_version":"1.0","source":{"id":"2303.06286","kind":"arxiv","version":1}},"canonical_sha256":"5e86f45531078b9e58d257b4893f817eeb7714ebdae632ec2ce1f1765e7086eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e86f45531078b9e58d257b4893f817eeb7714ebdae632ec2ce1f1765e7086eb","first_computed_at":"2026-07-05T05:50:16.808036Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:50:16.808036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IQGZeCsRgfsUC61KhJWNAo+I3WXkWlz1s9P1mNubrYlZaGcqg3mzCGsLjps7QsJj2onAEGV5J/7GQhgTX6v9DA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:50:16.808584Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.06286","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fa9bece13a0b3cd473a4babe6752e6ee7e1a180c67f6c86bf84143366848e3d9","sha256:5cb43c9dec30be6e0830df318956b915b4fd3532cadbf6a95cdd75d24f77d9df"],"state_sha256":"87b14f15e871339cd26f913c7072b134c491bf5c458f460ab21e94ea6cb6f4e0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7WEaC5TE1+SIYDw0MRsiCRhtaPY1WR4VWcENDogIGv1MLPiHyMlBkCAhZL4WUzUu4q522dsm++K4Eem6xbOvBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:48:27.288777Z","bundle_sha256":"c53df6bd600e7efaa6b197f6cf770b8e15853ee34fd7885d8eb428080892d405"}}