{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DAJT5WY3MYRKBLYSXE5KZLWWJO","short_pith_number":"pith:DAJT5WY3","schema_version":"1.0","canonical_sha256":"18133edb1b6622a0af12b93aacaed64b9ef993b98a6e03e68d632cfde509d976","source":{"kind":"arxiv","id":"2411.00390","version":1},"attestation_state":"computed","paper":{"title":"MetaMetrics-MT: Tuning Meta-Metrics for Machine Translation via Human Preference Calibration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"David Anugraha, Derry Tanti Wijaya, Garry Kuwanto, Genta Indra Winata, Lucky Susanto","submitted_at":"2024-11-01T06:34:30Z","abstract_excerpt":"We present MetaMetrics-MT, an innovative metric designed to evaluate machine translation (MT) tasks by aligning closely with human preferences through Bayesian optimization with Gaussian Processes. MetaMetrics-MT enhances existing MT metrics by optimizing their correlation with human judgments. Our experiments on the WMT24 metric shared task dataset demonstrate that MetaMetrics-MT outperforms all existing baselines, setting a new benchmark for state-of-the-art performance in the reference-based setting. Furthermore, it achieves comparable results to leading metrics in the reference-free settin"},"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":"2411.00390","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-01T06:34:30Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f33b1bdae2ab9a5a028be0575f732cb3d55c03407b84c909fc567dc68a6fa3d2","abstract_canon_sha256":"4e81c944ba67cebbc4126ae7c20b1458abf51e3372ece38e94988d250f5d2cad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:41.769384Z","signature_b64":"kEEpbz9m4i+brjAuZ0196wsU8WTsaxSqd6M42YZNDSHLI8WnyCoAX+rHyEw4vXS91lgBXeRZKzG9XV4pV0uWDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18133edb1b6622a0af12b93aacaed64b9ef993b98a6e03e68d632cfde509d976","last_reissued_at":"2026-07-05T09:29:41.768951Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:41.768951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MetaMetrics-MT: Tuning Meta-Metrics for Machine Translation via Human Preference Calibration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"David Anugraha, Derry Tanti Wijaya, Garry Kuwanto, Genta Indra Winata, Lucky Susanto","submitted_at":"2024-11-01T06:34:30Z","abstract_excerpt":"We present MetaMetrics-MT, an innovative metric designed to evaluate machine translation (MT) tasks by aligning closely with human preferences through Bayesian optimization with Gaussian Processes. MetaMetrics-MT enhances existing MT metrics by optimizing their correlation with human judgments. Our experiments on the WMT24 metric shared task dataset demonstrate that MetaMetrics-MT outperforms all existing baselines, setting a new benchmark for state-of-the-art performance in the reference-based setting. Furthermore, it achieves comparable results to leading metrics in the reference-free settin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00390","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/2411.00390/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":"2411.00390","created_at":"2026-07-05T09:29:41.769010+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.00390v1","created_at":"2026-07-05T09:29:41.769010+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00390","created_at":"2026-07-05T09:29:41.769010+00:00"},{"alias_kind":"pith_short_12","alias_value":"DAJT5WY3MYRK","created_at":"2026-07-05T09:29:41.769010+00:00"},{"alias_kind":"pith_short_16","alias_value":"DAJT5WY3MYRKBLYS","created_at":"2026-07-05T09:29:41.769010+00:00"},{"alias_kind":"pith_short_8","alias_value":"DAJT5WY3","created_at":"2026-07-05T09:29:41.769010+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/DAJT5WY3MYRKBLYSXE5KZLWWJO","json":"https://pith.science/pith/DAJT5WY3MYRKBLYSXE5KZLWWJO.json","graph_json":"https://pith.science/api/pith-number/DAJT5WY3MYRKBLYSXE5KZLWWJO/graph.json","events_json":"https://pith.science/api/pith-number/DAJT5WY3MYRKBLYSXE5KZLWWJO/events.json","paper":"https://pith.science/paper/DAJT5WY3"},"agent_actions":{"view_html":"https://pith.science/pith/DAJT5WY3MYRKBLYSXE5KZLWWJO","download_json":"https://pith.science/pith/DAJT5WY3MYRKBLYSXE5KZLWWJO.json","view_paper":"https://pith.science/paper/DAJT5WY3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.00390&json=true","fetch_graph":"https://pith.science/api/pith-number/DAJT5WY3MYRKBLYSXE5KZLWWJO/graph.json","fetch_events":"https://pith.science/api/pith-number/DAJT5WY3MYRKBLYSXE5KZLWWJO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DAJT5WY3MYRKBLYSXE5KZLWWJO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DAJT5WY3MYRKBLYSXE5KZLWWJO/action/storage_attestation","attest_author":"https://pith.science/pith/DAJT5WY3MYRKBLYSXE5KZLWWJO/action/author_attestation","sign_citation":"https://pith.science/pith/DAJT5WY3MYRKBLYSXE5KZLWWJO/action/citation_signature","submit_replication":"https://pith.science/pith/DAJT5WY3MYRKBLYSXE5KZLWWJO/action/replication_record"}},"created_at":"2026-07-05T09:29:41.769010+00:00","updated_at":"2026-07-05T09:29:41.769010+00:00"}