{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:UXAR66ONZJGV2UDWGCTIZIMC37","short_pith_number":"pith:UXAR66ON","canonical_record":{"source":{"id":"2110.01710","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2021-10-04T20:48:31Z","cross_cats_sorted":[],"title_canon_sha256":"96ebb259ace3d2a1bc74d70109980d372ef8203d5c4719ccfacfdffbf140e893","abstract_canon_sha256":"f2b6cb74b2b96d833d85cbfdb3a4538180d270bdba0a0601d9f429882d792bd9"},"schema_version":"1.0"},"canonical_sha256":"a5c11f79cdca4d5d507630a68ca182dfd031910cd388356a6b88c92c956e82d9","source":{"kind":"arxiv","id":"2110.01710","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.01710","created_at":"2026-07-05T03:20:05Z"},{"alias_kind":"arxiv_version","alias_value":"2110.01710v1","created_at":"2026-07-05T03:20:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.01710","created_at":"2026-07-05T03:20:05Z"},{"alias_kind":"pith_short_12","alias_value":"UXAR66ONZJGV","created_at":"2026-07-05T03:20:05Z"},{"alias_kind":"pith_short_16","alias_value":"UXAR66ONZJGV2UDW","created_at":"2026-07-05T03:20:05Z"},{"alias_kind":"pith_short_8","alias_value":"UXAR66ON","created_at":"2026-07-05T03:20:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:UXAR66ONZJGV2UDWGCTIZIMC37","target":"record","payload":{"canonical_record":{"source":{"id":"2110.01710","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2021-10-04T20:48:31Z","cross_cats_sorted":[],"title_canon_sha256":"96ebb259ace3d2a1bc74d70109980d372ef8203d5c4719ccfacfdffbf140e893","abstract_canon_sha256":"f2b6cb74b2b96d833d85cbfdb3a4538180d270bdba0a0601d9f429882d792bd9"},"schema_version":"1.0"},"canonical_sha256":"a5c11f79cdca4d5d507630a68ca182dfd031910cd388356a6b88c92c956e82d9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:20:05.347853Z","signature_b64":"FQVPitKjvtZyl9iSXJKIheoagL1Y3SLGATNsOlOi72Xqmbb9/8HtJdnMHc9s2tQlGIgJHlaAI+8TZyb1Q12OAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5c11f79cdca4d5d507630a68ca182dfd031910cd388356a6b88c92c956e82d9","last_reissued_at":"2026-07-05T03:20:05.347428Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:20:05.347428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.01710","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":"2026-07-05T03:20:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5Qwh1jw2R3zH/0VpW5Q45Aj+ce8V+bP86xPv3dBdx4bm0HrKDRNau7rwqYYyCSrGwf09npa4cESQC8WPARlMCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:32:55.957033Z"},"content_sha256":"d0bcad209382814767efcba3ee8067c02df14aca9a983539e108abf51a9761db","schema_version":"1.0","event_id":"sha256:d0bcad209382814767efcba3ee8067c02df14aca9a983539e108abf51a9761db"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:UXAR66ONZJGV2UDWGCTIZIMC37","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PyTorrent: A Python Library Corpus for Large-scale Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Kazuki Munakata, Lei Liu, Masahiro Fukuyori, Mehdi Bahrami, N.C. Shrikanth, Shade Ruangwan, Tim Menzies, Wei-Peng Chen, Yuji Mizobuchi","submitted_at":"2021-10-04T20:48:31Z","abstract_excerpt":"A large scale collection of both semantic and natural language resources is essential to leverage active Software Engineering research areas such as code reuse and code comprehensibility. Existing machine learning models ingest data from Open Source repositories (like GitHub projects) and forum discussions (like Stackoverflow.com), whereas, in this showcase, we took a step backward to orchestrate a corpus titled PyTorrent that contains 218,814 Python package libraries from PyPI and Anaconda environment. This is because earlier studies have shown that much of the code is redundant and Python pa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.01710","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/2110.01710/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":"2026-07-05T03:20:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R6Ar/e37kO1JnClrpKeoL8WXoAHVdvpBdCkCvFnPSuCDHQhC/xGTSGMgNNaF8dqPAnMX6M26PemUxpZBWSOzAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:32:55.957519Z"},"content_sha256":"9c02ecaedc0f26256bf4b96a9273a62ed16744e557cac94a7f6498d4c9811427","schema_version":"1.0","event_id":"sha256:9c02ecaedc0f26256bf4b96a9273a62ed16744e557cac94a7f6498d4c9811427"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UXAR66ONZJGV2UDWGCTIZIMC37/bundle.json","state_url":"https://pith.science/pith/UXAR66ONZJGV2UDWGCTIZIMC37/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UXAR66ONZJGV2UDWGCTIZIMC37/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":"2026-08-07T23:32:55Z","links":{"resolver":"https://pith.science/pith/UXAR66ONZJGV2UDWGCTIZIMC37","bundle":"https://pith.science/pith/UXAR66ONZJGV2UDWGCTIZIMC37/bundle.json","state":"https://pith.science/pith/UXAR66ONZJGV2UDWGCTIZIMC37/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UXAR66ONZJGV2UDWGCTIZIMC37/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:UXAR66ONZJGV2UDWGCTIZIMC37","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":"f2b6cb74b2b96d833d85cbfdb3a4538180d270bdba0a0601d9f429882d792bd9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2021-10-04T20:48:31Z","title_canon_sha256":"96ebb259ace3d2a1bc74d70109980d372ef8203d5c4719ccfacfdffbf140e893"},"schema_version":"1.0","source":{"id":"2110.01710","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.01710","created_at":"2026-07-05T03:20:05Z"},{"alias_kind":"arxiv_version","alias_value":"2110.01710v1","created_at":"2026-07-05T03:20:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.01710","created_at":"2026-07-05T03:20:05Z"},{"alias_kind":"pith_short_12","alias_value":"UXAR66ONZJGV","created_at":"2026-07-05T03:20:05Z"},{"alias_kind":"pith_short_16","alias_value":"UXAR66ONZJGV2UDW","created_at":"2026-07-05T03:20:05Z"},{"alias_kind":"pith_short_8","alias_value":"UXAR66ON","created_at":"2026-07-05T03:20:05Z"}],"graph_snapshots":[{"event_id":"sha256:9c02ecaedc0f26256bf4b96a9273a62ed16744e557cac94a7f6498d4c9811427","target":"graph","created_at":"2026-07-05T03:20:05Z","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/2110.01710/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A large scale collection of both semantic and natural language resources is essential to leverage active Software Engineering research areas such as code reuse and code comprehensibility. Existing machine learning models ingest data from Open Source repositories (like GitHub projects) and forum discussions (like Stackoverflow.com), whereas, in this showcase, we took a step backward to orchestrate a corpus titled PyTorrent that contains 218,814 Python package libraries from PyPI and Anaconda environment. This is because earlier studies have shown that much of the code is redundant and Python pa","authors_text":"Kazuki Munakata, Lei Liu, Masahiro Fukuyori, Mehdi Bahrami, N.C. Shrikanth, Shade Ruangwan, Tim Menzies, Wei-Peng Chen, Yuji Mizobuchi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2021-10-04T20:48:31Z","title":"PyTorrent: A Python Library Corpus for Large-scale Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.01710","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:d0bcad209382814767efcba3ee8067c02df14aca9a983539e108abf51a9761db","target":"record","created_at":"2026-07-05T03:20:05Z","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":"f2b6cb74b2b96d833d85cbfdb3a4538180d270bdba0a0601d9f429882d792bd9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2021-10-04T20:48:31Z","title_canon_sha256":"96ebb259ace3d2a1bc74d70109980d372ef8203d5c4719ccfacfdffbf140e893"},"schema_version":"1.0","source":{"id":"2110.01710","kind":"arxiv","version":1}},"canonical_sha256":"a5c11f79cdca4d5d507630a68ca182dfd031910cd388356a6b88c92c956e82d9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a5c11f79cdca4d5d507630a68ca182dfd031910cd388356a6b88c92c956e82d9","first_computed_at":"2026-07-05T03:20:05.347428Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:20:05.347428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FQVPitKjvtZyl9iSXJKIheoagL1Y3SLGATNsOlOi72Xqmbb9/8HtJdnMHc9s2tQlGIgJHlaAI+8TZyb1Q12OAg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:20:05.347853Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.01710","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d0bcad209382814767efcba3ee8067c02df14aca9a983539e108abf51a9761db","sha256:9c02ecaedc0f26256bf4b96a9273a62ed16744e557cac94a7f6498d4c9811427"],"state_sha256":"7701d7caa90911a4997b6c9153df5bd41664aa313593ee81f16b2b091e9060be"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pmm7jxKFoeusBKJieEM5Y8+EAqkq102nAPZ7PZe+OzjPl3rl4AuF6Q/uuZEU7Hiiuj6zrgXXyHb9uTGKeaFoCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T23:32:55.961796Z","bundle_sha256":"afdb1f7b866d197d980152c3addfe3e8d0ea12196f95ad27e7a73a5721f39b0b"}}