{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:AZOBLHRMAXWUUCUV3LZHZ4EEEC","short_pith_number":"pith:AZOBLHRM","canonical_record":{"source":{"id":"2504.17038","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-23T18:36:38Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"742c177688c3c2bb852a7804c610e2db1ac39e883812ea49e5962573874588a4","abstract_canon_sha256":"0f3c63ea4a018b656431080b24b293b3cfa26a0ce141b7cdf295f2973aaaf0c6"},"schema_version":"1.0"},"canonical_sha256":"065c159e2c05ed4a0a95daf27cf0842093dcf4f80aa5ec040d9eed58fbec16fd","source":{"kind":"arxiv","id":"2504.17038","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.17038","created_at":"2026-07-05T10:53:21Z"},{"alias_kind":"arxiv_version","alias_value":"2504.17038v1","created_at":"2026-07-05T10:53:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.17038","created_at":"2026-07-05T10:53:21Z"},{"alias_kind":"pith_short_12","alias_value":"AZOBLHRMAXWU","created_at":"2026-07-05T10:53:21Z"},{"alias_kind":"pith_short_16","alias_value":"AZOBLHRMAXWUUCUV","created_at":"2026-07-05T10:53:21Z"},{"alias_kind":"pith_short_8","alias_value":"AZOBLHRM","created_at":"2026-07-05T10:53:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:AZOBLHRMAXWUUCUV3LZHZ4EEEC","target":"record","payload":{"canonical_record":{"source":{"id":"2504.17038","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-23T18:36:38Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"742c177688c3c2bb852a7804c610e2db1ac39e883812ea49e5962573874588a4","abstract_canon_sha256":"0f3c63ea4a018b656431080b24b293b3cfa26a0ce141b7cdf295f2973aaaf0c6"},"schema_version":"1.0"},"canonical_sha256":"065c159e2c05ed4a0a95daf27cf0842093dcf4f80aa5ec040d9eed58fbec16fd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:21.069436Z","signature_b64":"V46Ztx04Vgo8Mj+fSq8ssb5gcb7MQOajUQlHf3ocX6uHwXX5j11Oqtz/t/DVzXjEIwDorVXJL+DPtRE4tySRDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"065c159e2c05ed4a0a95daf27cf0842093dcf4f80aa5ec040d9eed58fbec16fd","last_reissued_at":"2026-07-05T10:53:21.068938Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:21.068938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.17038","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":"2026-07-05T10:53:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qia0bhL1lreoLVgFawxf5g/NxM2jgRt3S4YWZtrSQinxmukc4Q/bmQZBdCyKZHmTLklTgB6gqN1vBdvfIrliAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T06:22:14.143376Z"},"content_sha256":"280ea8a99e87151e0a47e936a5f8ecf256a546612f914f894d2ab8191d8fa26b","schema_version":"1.0","event_id":"sha256:280ea8a99e87151e0a47e936a5f8ecf256a546612f914f894d2ab8191d8fa26b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:AZOBLHRMAXWUUCUV3LZHZ4EEEC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SCALAR: A Part-of-speech Tagger for Identifiers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Anthony Peruma, Brandon Scholten, Christian D. Newman, Eman Abdullah AlOmar, Jonathan I. Maletic, Joshua A. C. Behler, Marcos Zampieri, Michael J. Decker, Michael L. Collard, Mohamed Wiem Mkaouer, Reem Alsuhaibani, Sophia Testa, Syreen Banabilah","submitted_at":"2025-04-23T18:36:38Z","abstract_excerpt":"The paper presents the Source Code Analysis and Lexical Annotation Runtime (SCALAR), a tool specialized for mapping (annotating) source code identifier names to their corresponding part-of-speech tag sequence (grammar pattern). SCALAR's internal model is trained using scikit-learn's GradientBoostingClassifier in conjunction with a manually-curated oracle of identifier names and their grammar patterns. This specializes the tagger to recognize the unique structure of the natural language used by developers to create all types of identifiers (e.g., function names, variable names etc.). SCALAR's o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.17038","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/2504.17038/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":"2026-07-05T10:53:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EwqzMpIU/NbwdFSM/gk9VzEI0L7j8+ZLi4zT8xtNJKLWdPgXHO+Sk3rBrLqUxTSOxJffMzuKqnKuf40/aR6CCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T06:22:14.144322Z"},"content_sha256":"026327f4d82e2dd58be68159f12d0809b9d5572d59c1838a0ff31578a7337466","schema_version":"1.0","event_id":"sha256:026327f4d82e2dd58be68159f12d0809b9d5572d59c1838a0ff31578a7337466"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AZOBLHRMAXWUUCUV3LZHZ4EEEC/bundle.json","state_url":"https://pith.science/pith/AZOBLHRMAXWUUCUV3LZHZ4EEEC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AZOBLHRMAXWUUCUV3LZHZ4EEEC/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":"2026-08-20T06:22:14Z","links":{"resolver":"https://pith.science/pith/AZOBLHRMAXWUUCUV3LZHZ4EEEC","bundle":"https://pith.science/pith/AZOBLHRMAXWUUCUV3LZHZ4EEEC/bundle.json","state":"https://pith.science/pith/AZOBLHRMAXWUUCUV3LZHZ4EEEC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AZOBLHRMAXWUUCUV3LZHZ4EEEC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AZOBLHRMAXWUUCUV3LZHZ4EEEC","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":"0f3c63ea4a018b656431080b24b293b3cfa26a0ce141b7cdf295f2973aaaf0c6","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-23T18:36:38Z","title_canon_sha256":"742c177688c3c2bb852a7804c610e2db1ac39e883812ea49e5962573874588a4"},"schema_version":"1.0","source":{"id":"2504.17038","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.17038","created_at":"2026-07-05T10:53:21Z"},{"alias_kind":"arxiv_version","alias_value":"2504.17038v1","created_at":"2026-07-05T10:53:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.17038","created_at":"2026-07-05T10:53:21Z"},{"alias_kind":"pith_short_12","alias_value":"AZOBLHRMAXWU","created_at":"2026-07-05T10:53:21Z"},{"alias_kind":"pith_short_16","alias_value":"AZOBLHRMAXWUUCUV","created_at":"2026-07-05T10:53:21Z"},{"alias_kind":"pith_short_8","alias_value":"AZOBLHRM","created_at":"2026-07-05T10:53:21Z"}],"graph_snapshots":[{"event_id":"sha256:026327f4d82e2dd58be68159f12d0809b9d5572d59c1838a0ff31578a7337466","target":"graph","created_at":"2026-07-05T10:53:21Z","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/2504.17038/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The paper presents the Source Code Analysis and Lexical Annotation Runtime (SCALAR), a tool specialized for mapping (annotating) source code identifier names to their corresponding part-of-speech tag sequence (grammar pattern). SCALAR's internal model is trained using scikit-learn's GradientBoostingClassifier in conjunction with a manually-curated oracle of identifier names and their grammar patterns. This specializes the tagger to recognize the unique structure of the natural language used by developers to create all types of identifiers (e.g., function names, variable names etc.). SCALAR's o","authors_text":"Anthony Peruma, Brandon Scholten, Christian D. Newman, Eman Abdullah AlOmar, Jonathan I. Maletic, Joshua A. C. Behler, Marcos Zampieri, Michael J. Decker, Michael L. Collard, Mohamed Wiem Mkaouer, Reem Alsuhaibani, Sophia Testa, Syreen Banabilah","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-23T18:36:38Z","title":"SCALAR: A Part-of-speech Tagger for Identifiers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.17038","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":"sha256:280ea8a99e87151e0a47e936a5f8ecf256a546612f914f894d2ab8191d8fa26b","target":"record","created_at":"2026-07-05T10:53:21Z","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":"0f3c63ea4a018b656431080b24b293b3cfa26a0ce141b7cdf295f2973aaaf0c6","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-23T18:36:38Z","title_canon_sha256":"742c177688c3c2bb852a7804c610e2db1ac39e883812ea49e5962573874588a4"},"schema_version":"1.0","source":{"id":"2504.17038","kind":"arxiv","version":1}},"canonical_sha256":"065c159e2c05ed4a0a95daf27cf0842093dcf4f80aa5ec040d9eed58fbec16fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"065c159e2c05ed4a0a95daf27cf0842093dcf4f80aa5ec040d9eed58fbec16fd","first_computed_at":"2026-07-05T10:53:21.068938Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:53:21.068938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V46Ztx04Vgo8Mj+fSq8ssb5gcb7MQOajUQlHf3ocX6uHwXX5j11Oqtz/t/DVzXjEIwDorVXJL+DPtRE4tySRDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:53:21.069436Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.17038","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:280ea8a99e87151e0a47e936a5f8ecf256a546612f914f894d2ab8191d8fa26b","sha256:026327f4d82e2dd58be68159f12d0809b9d5572d59c1838a0ff31578a7337466"],"state_sha256":"f2ff354dd3973e07bb010611bb930531a685f107e23ec8933d479fb381192354"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zi8O/T9FgemQ2gebTOacmkPNtl5EVBuZfGK6XZ9JEsicu58ytWfJfmm3sqdTMJ4J7ui0c1YFbQwHJs9XC4EvBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T06:22:14.150161Z","bundle_sha256":"f5b9cb2fff2a5ad1919646af696d5543880a1259ddf53200859fd79d44823d64"}}