{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4CRQR54WMEI4MF7RBIC7LMHJJU","short_pith_number":"pith:4CRQR54W","schema_version":"1.0","canonical_sha256":"e0a308f7966111c617f10a05f5b0e94d1104e3f25141b9e422cb916227d66bbc","source":{"kind":"arxiv","id":"2410.03983","version":1},"attestation_state":"computed","paper":{"title":"MetricX-24: The Google Submission to the WMT 2024 Metrics Shared Task","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniel Deutsch, Juraj Juraska, Mara Finkelstein, Markus Freitag","submitted_at":"2024-10-04T23:52:28Z","abstract_excerpt":"In this paper, we present the MetricX-24 submissions to the WMT24 Metrics Shared Task and provide details on the improvements we made over the previous version of MetricX. Our primary submission is a hybrid reference-based/-free metric, which can score a translation irrespective of whether it is given the source segment, the reference, or both. The metric is trained on previous WMT data in a two-stage fashion, first on the DA ratings only, then on a mixture of MQM and DA ratings. The training set in both stages is augmented with synthetic examples that we created to make the metric more robust"},"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":"2410.03983","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-04T23:52:28Z","cross_cats_sorted":[],"title_canon_sha256":"53e34362d3b1c19f3744d6f5b53be8b6cb21225af12a8b53eebeb366f23a90b4","abstract_canon_sha256":"738fe8547e433cda51b6b6737ddd4afb5a9a905930b629d965f52a434a5d9b56"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:27.331461Z","signature_b64":"KXqK2LUi1NBeqazAQUfBtA9N4Cqf4ufmqfZNxfJ9PQbZcJQkGcRO4lhg1s/px+/wlWiyPidwMK+V+SUgrWpVCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0a308f7966111c617f10a05f5b0e94d1104e3f25141b9e422cb916227d66bbc","last_reissued_at":"2026-07-05T09:16:27.330992Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:27.330992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MetricX-24: The Google Submission to the WMT 2024 Metrics Shared Task","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniel Deutsch, Juraj Juraska, Mara Finkelstein, Markus Freitag","submitted_at":"2024-10-04T23:52:28Z","abstract_excerpt":"In this paper, we present the MetricX-24 submissions to the WMT24 Metrics Shared Task and provide details on the improvements we made over the previous version of MetricX. Our primary submission is a hybrid reference-based/-free metric, which can score a translation irrespective of whether it is given the source segment, the reference, or both. The metric is trained on previous WMT data in a two-stage fashion, first on the DA ratings only, then on a mixture of MQM and DA ratings. The training set in both stages is augmented with synthetic examples that we created to make the metric more robust"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03983","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/2410.03983/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":"2410.03983","created_at":"2026-07-05T09:16:27.331053+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.03983v1","created_at":"2026-07-05T09:16:27.331053+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03983","created_at":"2026-07-05T09:16:27.331053+00:00"},{"alias_kind":"pith_short_12","alias_value":"4CRQR54WMEI4","created_at":"2026-07-05T09:16:27.331053+00:00"},{"alias_kind":"pith_short_16","alias_value":"4CRQR54WMEI4MF7R","created_at":"2026-07-05T09:16:27.331053+00:00"},{"alias_kind":"pith_short_8","alias_value":"4CRQR54W","created_at":"2026-07-05T09:16:27.331053+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.12376","citing_title":"ConsistencyChecker: Tree-based Evaluation of LLM Generalization Capabilities","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4CRQR54WMEI4MF7RBIC7LMHJJU","json":"https://pith.science/pith/4CRQR54WMEI4MF7RBIC7LMHJJU.json","graph_json":"https://pith.science/api/pith-number/4CRQR54WMEI4MF7RBIC7LMHJJU/graph.json","events_json":"https://pith.science/api/pith-number/4CRQR54WMEI4MF7RBIC7LMHJJU/events.json","paper":"https://pith.science/paper/4CRQR54W"},"agent_actions":{"view_html":"https://pith.science/pith/4CRQR54WMEI4MF7RBIC7LMHJJU","download_json":"https://pith.science/pith/4CRQR54WMEI4MF7RBIC7LMHJJU.json","view_paper":"https://pith.science/paper/4CRQR54W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.03983&json=true","fetch_graph":"https://pith.science/api/pith-number/4CRQR54WMEI4MF7RBIC7LMHJJU/graph.json","fetch_events":"https://pith.science/api/pith-number/4CRQR54WMEI4MF7RBIC7LMHJJU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4CRQR54WMEI4MF7RBIC7LMHJJU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4CRQR54WMEI4MF7RBIC7LMHJJU/action/storage_attestation","attest_author":"https://pith.science/pith/4CRQR54WMEI4MF7RBIC7LMHJJU/action/author_attestation","sign_citation":"https://pith.science/pith/4CRQR54WMEI4MF7RBIC7LMHJJU/action/citation_signature","submit_replication":"https://pith.science/pith/4CRQR54WMEI4MF7RBIC7LMHJJU/action/replication_record"}},"created_at":"2026-07-05T09:16:27.331053+00:00","updated_at":"2026-07-05T09:16:27.331053+00:00"}