{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IBUHD7XVQXD2BEUFBZMX6ORSES","short_pith_number":"pith:IBUHD7XV","schema_version":"1.0","canonical_sha256":"406871fef585c7a092850e597f3a322495e52bc846fd47318cf775427afb7779","source":{"kind":"arxiv","id":"2408.15366","version":3},"attestation_state":"computed","paper":{"title":"Pitfalls and Outlooks in Using COMET","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Barry Haddow, Nikita Moghe, Pinzhen Chen, Tsz Kin Lam, Vil\\'em Zouhar","submitted_at":"2024-08-27T19:03:11Z","abstract_excerpt":"The COMET metric has blazed a trail in the machine translation community, given its strong correlation with human judgements of translation quality. Its success stems from being a modified pre-trained multilingual model finetuned for quality assessment. However, it being a machine learning model also gives rise to a new set of pitfalls that may not be widely known. We investigate these unexpected behaviours from three aspects: 1) technical: obsolete software versions and compute precision; 2) data: empty content, language mismatch, and translationese at test time as well as distribution and do"},"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":"2408.15366","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-27T19:03:11Z","cross_cats_sorted":[],"title_canon_sha256":"5906a06639537eda17f305bceba45f06db4b05f58dde2f727ab8b26b680876ba","abstract_canon_sha256":"9a72ea3ced3ee2cdf5fdbb53859b634fafc7e3a6f0e3060d7167f542aa389995"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:13:38.343243Z","signature_b64":"iqxOyCcTYG4dycE/5nNymJV6PZ5Se3kNlm+2rF3/Puzj+I8VOeN7wIT7cgrd/QMMSjJl9ouF51BuEZO3RTntAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"406871fef585c7a092850e597f3a322495e52bc846fd47318cf775427afb7779","last_reissued_at":"2026-07-05T09:13:38.342754Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:13:38.342754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pitfalls and Outlooks in Using COMET","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Barry Haddow, Nikita Moghe, Pinzhen Chen, Tsz Kin Lam, Vil\\'em Zouhar","submitted_at":"2024-08-27T19:03:11Z","abstract_excerpt":"The COMET metric has blazed a trail in the machine translation community, given its strong correlation with human judgements of translation quality. Its success stems from being a modified pre-trained multilingual model finetuned for quality assessment. However, it being a machine learning model also gives rise to a new set of pitfalls that may not be widely known. We investigate these unexpected behaviours from three aspects: 1) technical: obsolete software versions and compute precision; 2) data: empty content, language mismatch, and translationese at test time as well as distribution and do"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.15366","kind":"arxiv","version":3},"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/2408.15366/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":"2408.15366","created_at":"2026-07-05T09:13:38.342812+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.15366v3","created_at":"2026-07-05T09:13:38.342812+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.15366","created_at":"2026-07-05T09:13:38.342812+00:00"},{"alias_kind":"pith_short_12","alias_value":"IBUHD7XVQXD2","created_at":"2026-07-05T09:13:38.342812+00:00"},{"alias_kind":"pith_short_16","alias_value":"IBUHD7XVQXD2BEUF","created_at":"2026-07-05T09:13:38.342812+00:00"},{"alias_kind":"pith_short_8","alias_value":"IBUHD7XV","created_at":"2026-07-05T09:13:38.342812+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.04929","citing_title":"ConECT Dataset: Overcoming Data Scarcity in Context-Aware E-Commerce MT","ref_index":44,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IBUHD7XVQXD2BEUFBZMX6ORSES","json":"https://pith.science/pith/IBUHD7XVQXD2BEUFBZMX6ORSES.json","graph_json":"https://pith.science/api/pith-number/IBUHD7XVQXD2BEUFBZMX6ORSES/graph.json","events_json":"https://pith.science/api/pith-number/IBUHD7XVQXD2BEUFBZMX6ORSES/events.json","paper":"https://pith.science/paper/IBUHD7XV"},"agent_actions":{"view_html":"https://pith.science/pith/IBUHD7XVQXD2BEUFBZMX6ORSES","download_json":"https://pith.science/pith/IBUHD7XVQXD2BEUFBZMX6ORSES.json","view_paper":"https://pith.science/paper/IBUHD7XV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.15366&json=true","fetch_graph":"https://pith.science/api/pith-number/IBUHD7XVQXD2BEUFBZMX6ORSES/graph.json","fetch_events":"https://pith.science/api/pith-number/IBUHD7XVQXD2BEUFBZMX6ORSES/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IBUHD7XVQXD2BEUFBZMX6ORSES/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IBUHD7XVQXD2BEUFBZMX6ORSES/action/storage_attestation","attest_author":"https://pith.science/pith/IBUHD7XVQXD2BEUFBZMX6ORSES/action/author_attestation","sign_citation":"https://pith.science/pith/IBUHD7XVQXD2BEUFBZMX6ORSES/action/citation_signature","submit_replication":"https://pith.science/pith/IBUHD7XVQXD2BEUFBZMX6ORSES/action/replication_record"}},"created_at":"2026-07-05T09:13:38.342812+00:00","updated_at":"2026-07-05T09:13:38.342812+00:00"}