{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MWTZ376KEED44ONWVOMB5YTXH6","short_pith_number":"pith:MWTZ376K","canonical_record":{"source":{"id":"2402.06959","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-10T14:26:42Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"c6b039b4356ed74f7f91cc821ad92af6ed6a99bb7b3a39f4476049dc47bcfb67","abstract_canon_sha256":"cb8ab0105bdb2a214ac50df0f0cd187941f08d613abcc5307f18ff3b69df697b"},"schema_version":"1.0"},"canonical_sha256":"65a79dffca2107ce39b6ab981ee2773fb2fd9b536fa94562659ec4dc7acc0a53","source":{"kind":"arxiv","id":"2402.06959","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.06959","created_at":"2026-07-05T07:43:41Z"},{"alias_kind":"arxiv_version","alias_value":"2402.06959v1","created_at":"2026-07-05T07:43:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.06959","created_at":"2026-07-05T07:43:41Z"},{"alias_kind":"pith_short_12","alias_value":"MWTZ376KEED4","created_at":"2026-07-05T07:43:41Z"},{"alias_kind":"pith_short_16","alias_value":"MWTZ376KEED44ONW","created_at":"2026-07-05T07:43:41Z"},{"alias_kind":"pith_short_8","alias_value":"MWTZ376K","created_at":"2026-07-05T07:43:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MWTZ376KEED44ONWVOMB5YTXH6","target":"record","payload":{"canonical_record":{"source":{"id":"2402.06959","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-10T14:26:42Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"c6b039b4356ed74f7f91cc821ad92af6ed6a99bb7b3a39f4476049dc47bcfb67","abstract_canon_sha256":"cb8ab0105bdb2a214ac50df0f0cd187941f08d613abcc5307f18ff3b69df697b"},"schema_version":"1.0"},"canonical_sha256":"65a79dffca2107ce39b6ab981ee2773fb2fd9b536fa94562659ec4dc7acc0a53","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:43:41.047079Z","signature_b64":"uhzQZcgzM/emtA+eAyKWE6zSyPONL4X+5+dFarmoVuUrEING/MDWL7Enn8Tk9IwPd++oRFtjIVfVZmIDi4RrDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65a79dffca2107ce39b6ab981ee2773fb2fd9b536fa94562659ec4dc7acc0a53","last_reissued_at":"2026-07-05T07:43:41.046527Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:43:41.046527Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.06959","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:43:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xWF4x+aO23qfRzqdAJ+RcfNTby5ABDWnMrF/bZO1ez/CIPcRB5BiYwKo9S+SXD7zVa/ywacsCaqOWhcUKhJdBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T13:40:31.794245Z"},"content_sha256":"ea624db259535058a88ba80a906be6539b3b68971f79749f5c500163de10a1de","schema_version":"1.0","event_id":"sha256:ea624db259535058a88ba80a906be6539b3b68971f79749f5c500163de10a1de"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MWTZ376KEED44ONWVOMB5YTXH6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SpeechCLIP+: Self-supervised multi-task representation learning for speech via CLIP and speech-image data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"David Harwath, Heng-Jui Chang, Hsin-Min Wang, Hsuan-Fu Wang, Hung-yi Lee, Layne Berry, Puyuan Peng, Yi-Jen Shih","submitted_at":"2024-02-10T14:26:42Z","abstract_excerpt":"The recently proposed visually grounded speech model SpeechCLIP is an innovative framework that bridges speech and text through images via CLIP without relying on text transcription. On this basis, this paper introduces two extensions to SpeechCLIP. First, we apply the Continuous Integrate-and-Fire (CIF) module to replace a fixed number of CLS tokens in the cascaded architecture. Second, we propose a new hybrid architecture that merges the cascaded and parallel architectures of SpeechCLIP into a multi-task learning framework. Our experimental evaluation is performed on the Flickr8k and SpokenC"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.06959","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/2402.06959/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:43:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ra38oyp5cl0FkTT0Tpt36rd1ca6dNni5k5UriRfaQ4RmOtDcZtxpCV+y82GQoSgRkXEE/DPUn27YrQlZnMHsCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T13:40:31.794838Z"},"content_sha256":"c8bcf9c1955fa4279b3c06fcdc874ba00cf4700d466ca64b54cb7d2ac80314e3","schema_version":"1.0","event_id":"sha256:c8bcf9c1955fa4279b3c06fcdc874ba00cf4700d466ca64b54cb7d2ac80314e3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MWTZ376KEED44ONWVOMB5YTXH6/bundle.json","state_url":"https://pith.science/pith/MWTZ376KEED44ONWVOMB5YTXH6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MWTZ376KEED44ONWVOMB5YTXH6/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-23T13:40:31Z","links":{"resolver":"https://pith.science/pith/MWTZ376KEED44ONWVOMB5YTXH6","bundle":"https://pith.science/pith/MWTZ376KEED44ONWVOMB5YTXH6/bundle.json","state":"https://pith.science/pith/MWTZ376KEED44ONWVOMB5YTXH6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MWTZ376KEED44ONWVOMB5YTXH6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MWTZ376KEED44ONWVOMB5YTXH6","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":"cb8ab0105bdb2a214ac50df0f0cd187941f08d613abcc5307f18ff3b69df697b","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-10T14:26:42Z","title_canon_sha256":"c6b039b4356ed74f7f91cc821ad92af6ed6a99bb7b3a39f4476049dc47bcfb67"},"schema_version":"1.0","source":{"id":"2402.06959","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.06959","created_at":"2026-07-05T07:43:41Z"},{"alias_kind":"arxiv_version","alias_value":"2402.06959v1","created_at":"2026-07-05T07:43:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.06959","created_at":"2026-07-05T07:43:41Z"},{"alias_kind":"pith_short_12","alias_value":"MWTZ376KEED4","created_at":"2026-07-05T07:43:41Z"},{"alias_kind":"pith_short_16","alias_value":"MWTZ376KEED44ONW","created_at":"2026-07-05T07:43:41Z"},{"alias_kind":"pith_short_8","alias_value":"MWTZ376K","created_at":"2026-07-05T07:43:41Z"}],"graph_snapshots":[{"event_id":"sha256:c8bcf9c1955fa4279b3c06fcdc874ba00cf4700d466ca64b54cb7d2ac80314e3","target":"graph","created_at":"2026-07-05T07:43:41Z","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/2402.06959/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recently proposed visually grounded speech model SpeechCLIP is an innovative framework that bridges speech and text through images via CLIP without relying on text transcription. On this basis, this paper introduces two extensions to SpeechCLIP. First, we apply the Continuous Integrate-and-Fire (CIF) module to replace a fixed number of CLS tokens in the cascaded architecture. Second, we propose a new hybrid architecture that merges the cascaded and parallel architectures of SpeechCLIP into a multi-task learning framework. Our experimental evaluation is performed on the Flickr8k and SpokenC","authors_text":"David Harwath, Heng-Jui Chang, Hsin-Min Wang, Hsuan-Fu Wang, Hung-yi Lee, Layne Berry, Puyuan Peng, Yi-Jen Shih","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-10T14:26:42Z","title":"SpeechCLIP+: Self-supervised multi-task representation learning for speech via CLIP and speech-image data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.06959","kind":"arxiv","version":1},"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:ea624db259535058a88ba80a906be6539b3b68971f79749f5c500163de10a1de","target":"record","created_at":"2026-07-05T07:43:41Z","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":"cb8ab0105bdb2a214ac50df0f0cd187941f08d613abcc5307f18ff3b69df697b","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-10T14:26:42Z","title_canon_sha256":"c6b039b4356ed74f7f91cc821ad92af6ed6a99bb7b3a39f4476049dc47bcfb67"},"schema_version":"1.0","source":{"id":"2402.06959","kind":"arxiv","version":1}},"canonical_sha256":"65a79dffca2107ce39b6ab981ee2773fb2fd9b536fa94562659ec4dc7acc0a53","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"65a79dffca2107ce39b6ab981ee2773fb2fd9b536fa94562659ec4dc7acc0a53","first_computed_at":"2026-07-05T07:43:41.046527Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:43:41.046527Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uhzQZcgzM/emtA+eAyKWE6zSyPONL4X+5+dFarmoVuUrEING/MDWL7Enn8Tk9IwPd++oRFtjIVfVZmIDi4RrDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:43:41.047079Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.06959","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea624db259535058a88ba80a906be6539b3b68971f79749f5c500163de10a1de","sha256:c8bcf9c1955fa4279b3c06fcdc874ba00cf4700d466ca64b54cb7d2ac80314e3"],"state_sha256":"f066dd09ec73d90bc18433518df84a94615f45b3446d420962c432dc4df88130"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QWywg6VrO/BkJS4Dp4q5s2VFdVE9uA5HDwk5qMP+1mS8RxauEcM7SWoVr0fn7XVHP8fF/Wkhz2amNIvpI5J6Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T13:40:31.800185Z","bundle_sha256":"6c3fec05114111ed1dc93ceeb6d056d17b5c7f4dbd8a301bb6b1f77abe3ba518"}}