{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CVMPUVO3RZWKPEUBBVUM656HDX","short_pith_number":"pith:CVMPUVO3","schema_version":"1.0","canonical_sha256":"1558fa55db8e6ca792810d68cf77c71de16f771fb647d37b19c81296a6bf7fae","source":{"kind":"arxiv","id":"2607.29557","version":1},"attestation_state":"computed","paper":{"title":"Alteron: A Tool for Behavioral Regression Testing Across NLP Classifier Versions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Mridha Md. Nafis Fuad (University of Dhaka), Proma Chowdhury (University of Dhaka), Shazzad Hossain (University of Dhaka)","submitted_at":"2026-07-31T15:48:31Z","abstract_excerpt":"Evaluating evolving Natural Language Processing (NLP) models is important for ensuring reliable behavior across updates, but standard benchmark metrics do not fully capture how model behavior changes across versions. Existing work has focused mainly on testing models in isolation rather than comparing successive versions in continuous integration workflows. We present Alteron, a tool for detecting behavioral regressions across NLP model versions with metamorphic testing. Alteron constructs a test corpus from labeled source examples and compares model versions on metamorphically transformed inp"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.29557","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-07-31T15:48:31Z","cross_cats_sorted":[],"title_canon_sha256":"e5ceb99c66169641a107f1a5ffc1ba305b145a95564b30b81d14d74bd5ab63fb","abstract_canon_sha256":"a66c8b4f43970eb0b44495b2016043b8bc622c7919ec36dfc0bda7a4103fc9a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-03T01:38:28.257072Z","signature_b64":"GH8rSRdAAxpa/rL6TnoqKWFKVvU02E7//EUFE++2AW3hxYoSn5K4gF1lqmkIiTBKPsmlON8z102AYU08+McJDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1558fa55db8e6ca792810d68cf77c71de16f771fb647d37b19c81296a6bf7fae","last_reissued_at":"2026-08-03T01:38:28.255577Z","signature_status":"signed_v1","first_computed_at":"2026-08-03T01:38:28.255577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Alteron: A Tool for Behavioral Regression Testing Across NLP Classifier Versions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Mridha Md. Nafis Fuad (University of Dhaka), Proma Chowdhury (University of Dhaka), Shazzad Hossain (University of Dhaka)","submitted_at":"2026-07-31T15:48:31Z","abstract_excerpt":"Evaluating evolving Natural Language Processing (NLP) models is important for ensuring reliable behavior across updates, but standard benchmark metrics do not fully capture how model behavior changes across versions. Existing work has focused mainly on testing models in isolation rather than comparing successive versions in continuous integration workflows. We present Alteron, a tool for detecting behavioral regressions across NLP model versions with metamorphic testing. Alteron constructs a test corpus from labeled source examples and compares model versions on metamorphically transformed inp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.29557","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/2607.29557/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.29557","created_at":"2026-08-03T01:38:28.256472+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.29557v1","created_at":"2026-08-03T01:38:28.256472+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.29557","created_at":"2026-08-03T01:38:28.256472+00:00"},{"alias_kind":"pith_short_12","alias_value":"CVMPUVO3RZWK","created_at":"2026-08-03T01:38:28.256472+00:00"},{"alias_kind":"pith_short_16","alias_value":"CVMPUVO3RZWKPEUB","created_at":"2026-08-03T01:38:28.256472+00:00"},{"alias_kind":"pith_short_8","alias_value":"CVMPUVO3","created_at":"2026-08-03T01:38:28.256472+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CVMPUVO3RZWKPEUBBVUM656HDX","json":"https://pith.science/pith/CVMPUVO3RZWKPEUBBVUM656HDX.json","graph_json":"https://pith.science/api/pith-number/CVMPUVO3RZWKPEUBBVUM656HDX/graph.json","events_json":"https://pith.science/api/pith-number/CVMPUVO3RZWKPEUBBVUM656HDX/events.json","paper":"https://pith.science/paper/CVMPUVO3"},"agent_actions":{"view_html":"https://pith.science/pith/CVMPUVO3RZWKPEUBBVUM656HDX","download_json":"https://pith.science/pith/CVMPUVO3RZWKPEUBBVUM656HDX.json","view_paper":"https://pith.science/paper/CVMPUVO3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.29557&json=true","fetch_graph":"https://pith.science/api/pith-number/CVMPUVO3RZWKPEUBBVUM656HDX/graph.json","fetch_events":"https://pith.science/api/pith-number/CVMPUVO3RZWKPEUBBVUM656HDX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CVMPUVO3RZWKPEUBBVUM656HDX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CVMPUVO3RZWKPEUBBVUM656HDX/action/storage_attestation","attest_author":"https://pith.science/pith/CVMPUVO3RZWKPEUBBVUM656HDX/action/author_attestation","sign_citation":"https://pith.science/pith/CVMPUVO3RZWKPEUBBVUM656HDX/action/citation_signature","submit_replication":"https://pith.science/pith/CVMPUVO3RZWKPEUBBVUM656HDX/action/replication_record"}},"created_at":"2026-08-03T01:38:28.256472+00:00","updated_at":"2026-08-03T01:38:28.256472+00:00"}