{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:NWKPHIRAB7W3CDCDS2MWQF3QTS","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":"809b8958bbeaaf17882b2adb784f2f09d7ed255a767fb9e1228306dfb2b35346","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-03T04:15:36Z","title_canon_sha256":"1afb06f70a9f61b4d3a8a6203d80d4c50981b6432ef095d101d74512cc56f606"},"schema_version":"1.0","source":{"id":"2210.00705","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.00705","created_at":"2026-07-05T05:10:15Z"},{"alias_kind":"arxiv_version","alias_value":"2210.00705v2","created_at":"2026-07-05T05:10:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.00705","created_at":"2026-07-05T05:10:15Z"},{"alias_kind":"pith_short_12","alias_value":"NWKPHIRAB7W3","created_at":"2026-07-05T05:10:15Z"},{"alias_kind":"pith_short_16","alias_value":"NWKPHIRAB7W3CDCD","created_at":"2026-07-05T05:10:15Z"},{"alias_kind":"pith_short_8","alias_value":"NWKPHIRA","created_at":"2026-07-05T05:10:15Z"}],"graph_snapshots":[{"event_id":"sha256:0cab40ee46716333920eb91a85d6dac587f019232e66836da5f8f0798d61f634","target":"graph","created_at":"2026-07-05T05:10:15Z","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/2210.00705/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data-driven speech processing models usually perform well with a large amount of text supervision, but collecting transcribed speech data is costly. Therefore, we propose SpeechCLIP, a novel framework bridging speech and text through images to enhance speech models without transcriptions. We leverage state-of-the-art pre-trained HuBERT and CLIP, aligning them via paired images and spoken captions with minimal fine-tuning. SpeechCLIP outperforms prior state-of-the-art on image-speech retrieval and performs zero-shot speech-text retrieval without direct supervision from transcriptions. Moreover,","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":"2022-10-03T04:15:36Z","title":"SpeechCLIP: Integrating Speech with Pre-Trained Vision and Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.00705","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":"sha256:15140ccac445b328834bce7a6bd0a33a92ba60d5242fc522ef71e10befd82a7a","target":"record","created_at":"2026-07-05T05:10:15Z","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":"809b8958bbeaaf17882b2adb784f2f09d7ed255a767fb9e1228306dfb2b35346","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-03T04:15:36Z","title_canon_sha256":"1afb06f70a9f61b4d3a8a6203d80d4c50981b6432ef095d101d74512cc56f606"},"schema_version":"1.0","source":{"id":"2210.00705","kind":"arxiv","version":2}},"canonical_sha256":"6d94f3a2200fedb10c4396996817709cba1b82a68534afa120894bf9eabecb33","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6d94f3a2200fedb10c4396996817709cba1b82a68534afa120894bf9eabecb33","first_computed_at":"2026-07-05T05:10:15.790472Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:10:15.790472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W6+IKRu/3mUSQibU7mQVc0ckk/7xssMgggiaY+zHHLLHLylYrTKGQxMseZK2ZO8YD4BfE/ZDJiFg1jWRrDPcAw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:10:15.790866Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.00705","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:15140ccac445b328834bce7a6bd0a33a92ba60d5242fc522ef71e10befd82a7a","sha256:0cab40ee46716333920eb91a85d6dac587f019232e66836da5f8f0798d61f634"],"state_sha256":"1c6d8e0f3d9906415fab2b66203889da5deb3a923070527ef5918b539c4eaf99"}