{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2SNQVDKBPMGBRVQFG72N2Q4BG2","short_pith_number":"pith:2SNQVDKB","schema_version":"1.0","canonical_sha256":"d49b0a8d417b0c18d60537f4dd4381368d0f5f3ccc766cfccb1d61beecfcdf20","source":{"kind":"arxiv","id":"2406.03893","version":1},"attestation_state":"computed","paper":{"title":"How Good is Zero-Shot MT Evaluation for Low Resource Indian Languages?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ananya B. Sai, Anoop Kunchukuttan, Anushka Singh, Mitesh M Khapra, Raj Dabre, Ratish Puduppully","submitted_at":"2024-06-06T09:28:08Z","abstract_excerpt":"While machine translation evaluation has been studied primarily for high-resource languages, there has been a recent interest in evaluation for low-resource languages due to the increasing availability of data and models. In this paper, we focus on a zero-shot evaluation setting focusing on low-resource Indian languages, namely Assamese, Kannada, Maithili, and Punjabi. We collect sufficient Multi-Dimensional Quality Metrics (MQM) and Direct Assessment (DA) annotations to create test sets and meta-evaluate a plethora of automatic evaluation metrics. We observe that even for learned metrics, whi"},"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":"2406.03893","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-06T09:28:08Z","cross_cats_sorted":[],"title_canon_sha256":"99217e3ef21c4ff1779622ff4e8e103f9ccf435f26e64d0b45a4a043c05adf0b","abstract_canon_sha256":"a6bb9be0e0098e7afb76e0f509846fbd7a03e5149ec7d51fb73eee6b87287fe9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:17.519835Z","signature_b64":"0u3oER7MfcspxJuQwQzQ19+wmcPg0HX+5djEepaA1NkxuatW7AhnZ/N+voST8fzX51dGmFrZxQ9fAnWHhaNqDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d49b0a8d417b0c18d60537f4dd4381368d0f5f3ccc766cfccb1d61beecfcdf20","last_reissued_at":"2026-07-05T08:28:17.519404Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:17.519404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How Good is Zero-Shot MT Evaluation for Low Resource Indian Languages?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ananya B. Sai, Anoop Kunchukuttan, Anushka Singh, Mitesh M Khapra, Raj Dabre, Ratish Puduppully","submitted_at":"2024-06-06T09:28:08Z","abstract_excerpt":"While machine translation evaluation has been studied primarily for high-resource languages, there has been a recent interest in evaluation for low-resource languages due to the increasing availability of data and models. In this paper, we focus on a zero-shot evaluation setting focusing on low-resource Indian languages, namely Assamese, Kannada, Maithili, and Punjabi. We collect sufficient Multi-Dimensional Quality Metrics (MQM) and Direct Assessment (DA) annotations to create test sets and meta-evaluate a plethora of automatic evaluation metrics. We observe that even for learned metrics, whi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03893","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/2406.03893/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":"2406.03893","created_at":"2026-07-05T08:28:17.519460+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.03893v1","created_at":"2026-07-05T08:28:17.519460+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03893","created_at":"2026-07-05T08:28:17.519460+00:00"},{"alias_kind":"pith_short_12","alias_value":"2SNQVDKBPMGB","created_at":"2026-07-05T08:28:17.519460+00:00"},{"alias_kind":"pith_short_16","alias_value":"2SNQVDKBPMGBRVQF","created_at":"2026-07-05T08:28:17.519460+00:00"},{"alias_kind":"pith_short_8","alias_value":"2SNQVDKB","created_at":"2026-07-05T08:28:17.519460+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/2SNQVDKBPMGBRVQFG72N2Q4BG2","json":"https://pith.science/pith/2SNQVDKBPMGBRVQFG72N2Q4BG2.json","graph_json":"https://pith.science/api/pith-number/2SNQVDKBPMGBRVQFG72N2Q4BG2/graph.json","events_json":"https://pith.science/api/pith-number/2SNQVDKBPMGBRVQFG72N2Q4BG2/events.json","paper":"https://pith.science/paper/2SNQVDKB"},"agent_actions":{"view_html":"https://pith.science/pith/2SNQVDKBPMGBRVQFG72N2Q4BG2","download_json":"https://pith.science/pith/2SNQVDKBPMGBRVQFG72N2Q4BG2.json","view_paper":"https://pith.science/paper/2SNQVDKB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.03893&json=true","fetch_graph":"https://pith.science/api/pith-number/2SNQVDKBPMGBRVQFG72N2Q4BG2/graph.json","fetch_events":"https://pith.science/api/pith-number/2SNQVDKBPMGBRVQFG72N2Q4BG2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2SNQVDKBPMGBRVQFG72N2Q4BG2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2SNQVDKBPMGBRVQFG72N2Q4BG2/action/storage_attestation","attest_author":"https://pith.science/pith/2SNQVDKBPMGBRVQFG72N2Q4BG2/action/author_attestation","sign_citation":"https://pith.science/pith/2SNQVDKBPMGBRVQFG72N2Q4BG2/action/citation_signature","submit_replication":"https://pith.science/pith/2SNQVDKBPMGBRVQFG72N2Q4BG2/action/replication_record"}},"created_at":"2026-07-05T08:28:17.519460+00:00","updated_at":"2026-07-05T08:28:17.519460+00:00"}