{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:XTMCFEUL7INJPUQZ6OJQIWHFKA","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":"54a68fb45e8596cb4145090739231ae26dd3b99ad39519e44f2953d4879f7a11","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2021-09-01T21:49:32Z","title_canon_sha256":"1eed03f1bc451634fd506af81b2be6cc9a7d1769c4607a0c7432a72a9dba2147"},"schema_version":"1.0","source":{"id":"2109.00629","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.00629","created_at":"2026-07-05T03:11:15Z"},{"alias_kind":"arxiv_version","alias_value":"2109.00629v1","created_at":"2026-07-05T03:11:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.00629","created_at":"2026-07-05T03:11:15Z"},{"alias_kind":"pith_short_12","alias_value":"XTMCFEUL7INJ","created_at":"2026-07-05T03:11:15Z"},{"alias_kind":"pith_short_16","alias_value":"XTMCFEUL7INJPUQZ","created_at":"2026-07-05T03:11:15Z"},{"alias_kind":"pith_short_8","alias_value":"XTMCFEUL","created_at":"2026-07-05T03:11:15Z"}],"graph_snapshots":[{"event_id":"sha256:d082830db30c44780c6dcd33a701ef76e9b1b0325f1fad1285a02be019a6b8d5","target":"graph","created_at":"2026-07-05T03:11:15Z","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/2109.00629/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents an ensemble part-of-speech tagging approach for source code identifiers. Ensemble tagging is a technique that uses machine-learning and the output from multiple part-of-speech taggers to annotate natural language text at a higher quality than the part-of-speech taggers are able to obtain independently. Our ensemble uses three state-of-the-art part-of-speech taggers: SWUM, POSSE, and Stanford. We study the quality of the ensemble's annotations on five different types of identifier names: function, class, attribute, parameter, and declaration statement at the level of both in","authors_text":"Anthony Peruma, Christian D. Newman, Emily Hill, Marcos Zampieri, Michael J. Decker, Mohamed W. Mkaouer, Reem S. AlSuhaibani, Satyajit Mohapatra, Tejal Vishnoi, Timothy J. Sheldon","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2021-09-01T21:49:32Z","title":"An Ensemble Approach for Annotating Source Code Identifiers with Part-of-speech Tags"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.00629","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":"sha256:1f79261ce96a2c45c71d71502558840ca41b146eb3fa6c56bddf6ed4044275f1","target":"record","created_at":"2026-07-05T03:11:15Z","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":"54a68fb45e8596cb4145090739231ae26dd3b99ad39519e44f2953d4879f7a11","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2021-09-01T21:49:32Z","title_canon_sha256":"1eed03f1bc451634fd506af81b2be6cc9a7d1769c4607a0c7432a72a9dba2147"},"schema_version":"1.0","source":{"id":"2109.00629","kind":"arxiv","version":1}},"canonical_sha256":"bcd822928bfa1a97d219f3930458e55008c5021168cea35d5c750b59e3fdfb1e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bcd822928bfa1a97d219f3930458e55008c5021168cea35d5c750b59e3fdfb1e","first_computed_at":"2026-07-05T03:11:15.122556Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:11:15.122556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4o6R9FLV6/4M3UywEq6WTPRybCfTiwpqWWy4m059F9VlaEMplXwZJvfpwa8J0zRj0tsvI+j3NRRzEIz3oiHEDw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:11:15.122943Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.00629","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f79261ce96a2c45c71d71502558840ca41b146eb3fa6c56bddf6ed4044275f1","sha256:d082830db30c44780c6dcd33a701ef76e9b1b0325f1fad1285a02be019a6b8d5"],"state_sha256":"fbcdf54853a31985a9680bd8cba05da46a6b4f75805ca3dca82aeb25c048f9ff"}