{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MCTK5QOXYXX7CZZKV7JVROWAH2","short_pith_number":"pith:MCTK5QOX","schema_version":"1.0","canonical_sha256":"60a6aec1d7c5eff1672aafd358bac03ea49a52abf961faa733c121ed3d8804b0","source":{"kind":"arxiv","id":"2506.01808","version":1},"attestation_state":"computed","paper":{"title":"NAVER LABS Europe Submission to the Instruction-following Track","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Beomseok Lee, Ioan Calapodescu, Laurent Besacier, Marcely Zanon Boito","submitted_at":"2025-06-02T15:52:57Z","abstract_excerpt":"In this paper we describe NAVER LABS Europe submission to the instruction-following speech processing short track at IWSLT 2025. We participate in the constrained settings, developing systems that can simultaneously perform ASR, ST, and SQA tasks from English speech input into the following target languages: Chinese, Italian, and German. Our solution leverages two pretrained modules: (1) a speech-to-LLM embedding projector trained using representations from the SeamlessM4T-v2-large speech encoder; and (2) LoRA adapters trained on text data on top of a Llama-3.1-8B-Instruct. These modules are j"},"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":"2506.01808","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-02T15:52:57Z","cross_cats_sorted":[],"title_canon_sha256":"4df033296fd296027fb161acf2a660b94f95dc8504292ef7e5f17ab3c47df8a9","abstract_canon_sha256":"12179d51aebd3c881c4dcd305b94be42de5dd60c04d8435b7db6157bbe8ce21c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:19.710767Z","signature_b64":"1a5MP1mcNFj8XpTQybdnfZxgv4UXH9DoOF8WVswjoA0pIVqShDrsEb7vtT1Da8jcPA+QNBYOyBhYHKAkIZnOCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60a6aec1d7c5eff1672aafd358bac03ea49a52abf961faa733c121ed3d8804b0","last_reissued_at":"2026-07-05T11:14:19.710343Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:19.710343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NAVER LABS Europe Submission to the Instruction-following Track","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Beomseok Lee, Ioan Calapodescu, Laurent Besacier, Marcely Zanon Boito","submitted_at":"2025-06-02T15:52:57Z","abstract_excerpt":"In this paper we describe NAVER LABS Europe submission to the instruction-following speech processing short track at IWSLT 2025. We participate in the constrained settings, developing systems that can simultaneously perform ASR, ST, and SQA tasks from English speech input into the following target languages: Chinese, Italian, and German. Our solution leverages two pretrained modules: (1) a speech-to-LLM embedding projector trained using representations from the SeamlessM4T-v2-large speech encoder; and (2) LoRA adapters trained on text data on top of a Llama-3.1-8B-Instruct. These modules are j"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01808","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/2506.01808/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":"2506.01808","created_at":"2026-07-05T11:14:19.710412+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01808v1","created_at":"2026-07-05T11:14:19.710412+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01808","created_at":"2026-07-05T11:14:19.710412+00:00"},{"alias_kind":"pith_short_12","alias_value":"MCTK5QOXYXX7","created_at":"2026-07-05T11:14:19.710412+00:00"},{"alias_kind":"pith_short_16","alias_value":"MCTK5QOXYXX7CZZK","created_at":"2026-07-05T11:14:19.710412+00:00"},{"alias_kind":"pith_short_8","alias_value":"MCTK5QOX","created_at":"2026-07-05T11:14:19.710412+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/MCTK5QOXYXX7CZZKV7JVROWAH2","json":"https://pith.science/pith/MCTK5QOXYXX7CZZKV7JVROWAH2.json","graph_json":"https://pith.science/api/pith-number/MCTK5QOXYXX7CZZKV7JVROWAH2/graph.json","events_json":"https://pith.science/api/pith-number/MCTK5QOXYXX7CZZKV7JVROWAH2/events.json","paper":"https://pith.science/paper/MCTK5QOX"},"agent_actions":{"view_html":"https://pith.science/pith/MCTK5QOXYXX7CZZKV7JVROWAH2","download_json":"https://pith.science/pith/MCTK5QOXYXX7CZZKV7JVROWAH2.json","view_paper":"https://pith.science/paper/MCTK5QOX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01808&json=true","fetch_graph":"https://pith.science/api/pith-number/MCTK5QOXYXX7CZZKV7JVROWAH2/graph.json","fetch_events":"https://pith.science/api/pith-number/MCTK5QOXYXX7CZZKV7JVROWAH2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MCTK5QOXYXX7CZZKV7JVROWAH2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MCTK5QOXYXX7CZZKV7JVROWAH2/action/storage_attestation","attest_author":"https://pith.science/pith/MCTK5QOXYXX7CZZKV7JVROWAH2/action/author_attestation","sign_citation":"https://pith.science/pith/MCTK5QOXYXX7CZZKV7JVROWAH2/action/citation_signature","submit_replication":"https://pith.science/pith/MCTK5QOXYXX7CZZKV7JVROWAH2/action/replication_record"}},"created_at":"2026-07-05T11:14:19.710412+00:00","updated_at":"2026-07-05T11:14:19.710412+00:00"}