{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TU5M47ZYNTTUPS72IXJYZAZ3MP","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":"b90a7e614cbebd6b869828482f4ef473c38a0f519f15b596aa29d7b1c941b39e","cross_cats_sorted":["cs.IR","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T16:38:10Z","title_canon_sha256":"9365d6cdad0e0cae96f5935bc133e45a94b0c9d48d6bef85565b339b20b99795"},"schema_version":"1.0","source":{"id":"2412.13071","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.13071","created_at":"2026-07-05T10:37:40Z"},{"alias_kind":"arxiv_version","alias_value":"2412.13071v2","created_at":"2026-07-05T10:37:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13071","created_at":"2026-07-05T10:37:40Z"},{"alias_kind":"pith_short_12","alias_value":"TU5M47ZYNTTU","created_at":"2026-07-05T10:37:40Z"},{"alias_kind":"pith_short_16","alias_value":"TU5M47ZYNTTUPS72","created_at":"2026-07-05T10:37:40Z"},{"alias_kind":"pith_short_8","alias_value":"TU5M47ZY","created_at":"2026-07-05T10:37:40Z"}],"graph_snapshots":[{"event_id":"sha256:2bf2335faad1555998a44f9bfe2934a37deb3a4fea0dbfe06f569d0648f1d2fd","target":"graph","created_at":"2026-07-05T10:37:40Z","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/2412.13071/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This study introduces CLASP (Contrastive Language-Speech Pretraining), a multilingual, multimodal representation tailored for audio-text information retrieval. CLASP leverages the synergy between spoken content and textual data. During training, we utilize our newly introduced speech-text dataset, which encompasses 15 diverse categories ranging from fiction to religion. CLASP's audio component integrates audio spectrograms with a pre-trained self-supervised speech model, while its language encoding counterpart employs a sentence encoder pre-trained on over 100 languages. This unified lightweig","authors_text":"Ehsaneddin Asgari, Mohammad Mahdi Abootorabi","cross_cats":["cs.IR","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T16:38:10Z","title":"CLASP: Contrastive Language-Speech Pretraining for Multilingual Multimodal Information Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13071","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":"sha256:3a6e0f635e471a4df10acd60711e1f3c666dfc529a10f92c80204781d6ed43be","target":"record","created_at":"2026-07-05T10:37:40Z","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":"b90a7e614cbebd6b869828482f4ef473c38a0f519f15b596aa29d7b1c941b39e","cross_cats_sorted":["cs.IR","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T16:38:10Z","title_canon_sha256":"9365d6cdad0e0cae96f5935bc133e45a94b0c9d48d6bef85565b339b20b99795"},"schema_version":"1.0","source":{"id":"2412.13071","kind":"arxiv","version":2}},"canonical_sha256":"9d3ace7f386ce747cbfa45d38c833b63f3f2d4ebe6cb64f7044dd41935689c95","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d3ace7f386ce747cbfa45d38c833b63f3f2d4ebe6cb64f7044dd41935689c95","first_computed_at":"2026-07-05T10:37:40.602579Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:37:40.602579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pD44+mrCFFRgGjldnXmU4gkcXa7Karr1LZvltHIWE2LfQQwpSXxuQBuI4uQR3qP5zI7MxdNaPwc8JW1tD+27DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:37:40.603134Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.13071","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3a6e0f635e471a4df10acd60711e1f3c666dfc529a10f92c80204781d6ed43be","sha256:2bf2335faad1555998a44f9bfe2934a37deb3a4fea0dbfe06f569d0648f1d2fd"],"state_sha256":"e13e1a5416838ad98228ff9f2b099004453a22ccc92ec139d0bc077a5fd1cb21"}