{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7YD3LL2XEQ3A7QPEUAFVDRVELX","short_pith_number":"pith:7YD3LL2X","schema_version":"1.0","canonical_sha256":"fe07b5af5724360fc1e4a00b51c6a45df491e970eff97f343f4a13caf73a5af1","source":{"kind":"arxiv","id":"2605.28218","version":1},"attestation_state":"computed","paper":{"title":"IFMTBench: A Comprehensive Benchmark for Multilingual Translation Instruction Following","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mao Zheng, Mingrui Sun, Mingyang Song, Zheng Li","submitted_at":"2026-05-27T09:35:27Z","abstract_excerpt":"Modern translation workflows demand more than semantic equivalence. Users routinely require models to preserve JSON or HTML schemas, honor curated glossaries, disambiguate with provided context, and match prescribed registers, often several at once. Conventional metrics such as BLEU and xCOMET capture semantic fidelity but provide little signal on constraint adherence, while general instruction following benchmarks ignore the cross-lingual nature of translation. We introduce \\bench, a benchmark for multilingual translation instruction following covering seven languages, with 4,506 single-const"},"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":"2605.28218","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T09:35:27Z","cross_cats_sorted":[],"title_canon_sha256":"9632a36eea0a5398b8a198683dd03c8c732b6c4bb03303121a29e1c2d790a071","abstract_canon_sha256":"7ef81e0bd196fb25fa5976e412d0cd8f14552b718ebf1e040ee6370d2ba3ce0b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:05:02.971091Z","signature_b64":"pyHjJlAExNT+VX+l6DMwA5AdMfLavnMZxebN6cNuR6CX0Ad5Qdx+o6UnILfAYhKB34Y5jhFZMkvoZGph5naKDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe07b5af5724360fc1e4a00b51c6a45df491e970eff97f343f4a13caf73a5af1","last_reissued_at":"2026-05-28T01:05:02.970599Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:05:02.970599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IFMTBench: A Comprehensive Benchmark for Multilingual Translation Instruction Following","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mao Zheng, Mingrui Sun, Mingyang Song, Zheng Li","submitted_at":"2026-05-27T09:35:27Z","abstract_excerpt":"Modern translation workflows demand more than semantic equivalence. Users routinely require models to preserve JSON or HTML schemas, honor curated glossaries, disambiguate with provided context, and match prescribed registers, often several at once. Conventional metrics such as BLEU and xCOMET capture semantic fidelity but provide little signal on constraint adherence, while general instruction following benchmarks ignore the cross-lingual nature of translation. We introduce \\bench, a benchmark for multilingual translation instruction following covering seven languages, with 4,506 single-const"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28218","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/2605.28218/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":"2605.28218","created_at":"2026-05-28T01:05:02.970669+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28218v1","created_at":"2026-05-28T01:05:02.970669+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28218","created_at":"2026-05-28T01:05:02.970669+00:00"},{"alias_kind":"pith_short_12","alias_value":"7YD3LL2XEQ3A","created_at":"2026-05-28T01:05:02.970669+00:00"},{"alias_kind":"pith_short_16","alias_value":"7YD3LL2XEQ3A7QPE","created_at":"2026-05-28T01:05:02.970669+00:00"},{"alias_kind":"pith_short_8","alias_value":"7YD3LL2X","created_at":"2026-05-28T01:05:02.970669+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/7YD3LL2XEQ3A7QPEUAFVDRVELX","json":"https://pith.science/pith/7YD3LL2XEQ3A7QPEUAFVDRVELX.json","graph_json":"https://pith.science/api/pith-number/7YD3LL2XEQ3A7QPEUAFVDRVELX/graph.json","events_json":"https://pith.science/api/pith-number/7YD3LL2XEQ3A7QPEUAFVDRVELX/events.json","paper":"https://pith.science/paper/7YD3LL2X"},"agent_actions":{"view_html":"https://pith.science/pith/7YD3LL2XEQ3A7QPEUAFVDRVELX","download_json":"https://pith.science/pith/7YD3LL2XEQ3A7QPEUAFVDRVELX.json","view_paper":"https://pith.science/paper/7YD3LL2X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28218&json=true","fetch_graph":"https://pith.science/api/pith-number/7YD3LL2XEQ3A7QPEUAFVDRVELX/graph.json","fetch_events":"https://pith.science/api/pith-number/7YD3LL2XEQ3A7QPEUAFVDRVELX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7YD3LL2XEQ3A7QPEUAFVDRVELX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7YD3LL2XEQ3A7QPEUAFVDRVELX/action/storage_attestation","attest_author":"https://pith.science/pith/7YD3LL2XEQ3A7QPEUAFVDRVELX/action/author_attestation","sign_citation":"https://pith.science/pith/7YD3LL2XEQ3A7QPEUAFVDRVELX/action/citation_signature","submit_replication":"https://pith.science/pith/7YD3LL2XEQ3A7QPEUAFVDRVELX/action/replication_record"}},"created_at":"2026-05-28T01:05:02.970669+00:00","updated_at":"2026-05-28T01:05:02.970669+00:00"}