{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:SJG722IUBK64WYYUWT5IMVR72I","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"cc9e2cbb692da95da7cfe1b74dc0e493d37bdfeccb7ab87e362ac686c2aeb9ec","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-02T14:54:45Z","title_canon_sha256":"9e23aba69c55279e4269db0e875f0f02c22a7e7a9b06813205bec67884c9f24e"},"schema_version":"1.0","source":{"id":"2211.01180","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.01180","created_at":"2026-07-05T05:59:21Z"},{"alias_kind":"arxiv_version","alias_value":"2211.01180v2","created_at":"2026-07-05T05:59:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.01180","created_at":"2026-07-05T05:59:21Z"},{"alias_kind":"pith_short_12","alias_value":"SJG722IUBK64","created_at":"2026-07-05T05:59:21Z"},{"alias_kind":"pith_short_16","alias_value":"SJG722IUBK64WYYU","created_at":"2026-07-05T05:59:21Z"},{"alias_kind":"pith_short_8","alias_value":"SJG722IU","created_at":"2026-07-05T05:59:21Z"}],"graph_snapshots":[{"event_id":"sha256:106a776a6486926730f3509691ff5fcdba578fc1cccccefadde0d269ad96f0a9","target":"graph","created_at":"2026-07-05T05:59:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2211.01180/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work investigates the use of large-scale, English-only pre-trained models (CLIP and HuBERT) for multilingual image-speech retrieval. For non-English image-speech retrieval, we outperform the current state-of-the-art performance by a wide margin both when training separate models for each language, and with a single model which processes speech in all three languages. We identify key differences in model behavior and performance between English and non-English settings, attributable to the English-only pre-training of CLIP and HuBERT, and investigate how fine-tuning the pre-trained models ","authors_text":"David Harwath, Heng-Jui Chang, Hsuan-Fu Wang, Hung-yi Lee, Layne Berry, Yi-Jen Shih","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-02T14:54:45Z","title":"M-SpeechCLIP: Leveraging Large-Scale, Pre-Trained Models for Multilingual Speech to Image Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.01180","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:646dc51df84e9e94ccdf26bcd3b5df3c0eb6d4eedd5d947251ce6038549aac3d","target":"record","created_at":"2026-07-05T05:59:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"cc9e2cbb692da95da7cfe1b74dc0e493d37bdfeccb7ab87e362ac686c2aeb9ec","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-02T14:54:45Z","title_canon_sha256":"9e23aba69c55279e4269db0e875f0f02c22a7e7a9b06813205bec67884c9f24e"},"schema_version":"1.0","source":{"id":"2211.01180","kind":"arxiv","version":2}},"canonical_sha256":"924dfd69140abdcb6314b4fa86563fd235dd6ad383fa97657d7e19afc9e9c65b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"924dfd69140abdcb6314b4fa86563fd235dd6ad383fa97657d7e19afc9e9c65b","first_computed_at":"2026-07-05T05:59:21.811006Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:59:21.811006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rtrY5we/UCtlEoZwpy8F7sTlxliLOlOL51oUqh7a762MM3WdIAuFnUhw+lOmrBwWFmMhdIJVhwVsS7VoIOSFCg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:59:21.811424Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.01180","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:646dc51df84e9e94ccdf26bcd3b5df3c0eb6d4eedd5d947251ce6038549aac3d","sha256:106a776a6486926730f3509691ff5fcdba578fc1cccccefadde0d269ad96f0a9"],"state_sha256":"4a900b7f14af1f01389b70317c6b8fe42ddea414a328877eb78ec995a67e0803"}