{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SS3QO6AGL33UBC5JMLSJXFEMR2","short_pith_number":"pith:SS3QO6AG","canonical_record":{"source":{"id":"2410.14509","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-18T14:43:34Z","cross_cats_sorted":[],"title_canon_sha256":"1d66787ea1bbece6afdf1e691726a55ca27a5d154094016d641d3a8497976bdd","abstract_canon_sha256":"9421bb6908fee87c45e0bc73fa2a4679239ec399e34ccf6bc9df677f796e4fd6"},"schema_version":"1.0"},"canonical_sha256":"94b70778065ef7408ba962e49b948c8e9d0da6745c9008f19a5ea27af04c5c72","source":{"kind":"arxiv","id":"2410.14509","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.14509","created_at":"2026-07-05T09:22:33Z"},{"alias_kind":"arxiv_version","alias_value":"2410.14509v1","created_at":"2026-07-05T09:22:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.14509","created_at":"2026-07-05T09:22:33Z"},{"alias_kind":"pith_short_12","alias_value":"SS3QO6AGL33U","created_at":"2026-07-05T09:22:33Z"},{"alias_kind":"pith_short_16","alias_value":"SS3QO6AGL33UBC5J","created_at":"2026-07-05T09:22:33Z"},{"alias_kind":"pith_short_8","alias_value":"SS3QO6AG","created_at":"2026-07-05T09:22:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SS3QO6AGL33UBC5JMLSJXFEMR2","target":"record","payload":{"canonical_record":{"source":{"id":"2410.14509","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-18T14:43:34Z","cross_cats_sorted":[],"title_canon_sha256":"1d66787ea1bbece6afdf1e691726a55ca27a5d154094016d641d3a8497976bdd","abstract_canon_sha256":"9421bb6908fee87c45e0bc73fa2a4679239ec399e34ccf6bc9df677f796e4fd6"},"schema_version":"1.0"},"canonical_sha256":"94b70778065ef7408ba962e49b948c8e9d0da6745c9008f19a5ea27af04c5c72","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:22:33.339679Z","signature_b64":"67RbUCLZMztUnInG0FqjlShgmY64mAMnM0en9xPUXjXWEqFd1zwMW5nx9xCXa6xqYunqX6/GC0r8m0PnBa6YBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94b70778065ef7408ba962e49b948c8e9d0da6745c9008f19a5ea27af04c5c72","last_reissued_at":"2026-07-05T09:22:33.339192Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:22:33.339192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.14509","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":"2026-07-05T09:22:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k52vg+CFhd8A2BF3trvrVhm54RXZo+NkT/jrfe+IImZ8zRz04ndE6VqkbwwkmTlgLz3ffueX80s8s5NPFx9rDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:22:51.405941Z"},"content_sha256":"3f84c68c19d700367f041f5cced73e80dec4cc350241190acd0d5fd77d6220b5","schema_version":"1.0","event_id":"sha256:3f84c68c19d700367f041f5cced73e80dec4cc350241190acd0d5fd77d6220b5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SS3QO6AGL33UBC5JMLSJXFEMR2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CLIP-VAD: Exploiting Vision-Language Models for Voice Activity Detection","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Appiani, Cigdem Beyan","submitted_at":"2024-10-18T14:43:34Z","abstract_excerpt":"Voice Activity Detection (VAD) is the process of automatically determining whether a person is speaking and identifying the timing of their speech in an audiovisual data. Traditionally, this task has been tackled by processing either audio signals or visual data, or by combining both modalities through fusion or joint learning. In our study, drawing inspiration from recent advancements in visual-language models, we introduce a novel approach leveraging Contrastive Language-Image Pretraining (CLIP) models. The CLIP visual encoder analyzes video segments composed of the upper body of an individu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.14509","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/2410.14509/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":"2026-07-05T09:22:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fIGtRpnDgSZDBQb9TwDYOsNPmuyj5vAcL0ZX5eFmGGLQ7lgnI7IwAy5iPLVzMNipRHEvTpqlnwUoqQHMSR9FDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:22:51.406448Z"},"content_sha256":"70fd32f723e65198a7e38b91ea8c96d231d37816aed1e4112efc35714e4a9836","schema_version":"1.0","event_id":"sha256:70fd32f723e65198a7e38b91ea8c96d231d37816aed1e4112efc35714e4a9836"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SS3QO6AGL33UBC5JMLSJXFEMR2/bundle.json","state_url":"https://pith.science/pith/SS3QO6AGL33UBC5JMLSJXFEMR2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SS3QO6AGL33UBC5JMLSJXFEMR2/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":"2026-08-06T06:22:51Z","links":{"resolver":"https://pith.science/pith/SS3QO6AGL33UBC5JMLSJXFEMR2","bundle":"https://pith.science/pith/SS3QO6AGL33UBC5JMLSJXFEMR2/bundle.json","state":"https://pith.science/pith/SS3QO6AGL33UBC5JMLSJXFEMR2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SS3QO6AGL33UBC5JMLSJXFEMR2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SS3QO6AGL33UBC5JMLSJXFEMR2","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":"9421bb6908fee87c45e0bc73fa2a4679239ec399e34ccf6bc9df677f796e4fd6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-18T14:43:34Z","title_canon_sha256":"1d66787ea1bbece6afdf1e691726a55ca27a5d154094016d641d3a8497976bdd"},"schema_version":"1.0","source":{"id":"2410.14509","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.14509","created_at":"2026-07-05T09:22:33Z"},{"alias_kind":"arxiv_version","alias_value":"2410.14509v1","created_at":"2026-07-05T09:22:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.14509","created_at":"2026-07-05T09:22:33Z"},{"alias_kind":"pith_short_12","alias_value":"SS3QO6AGL33U","created_at":"2026-07-05T09:22:33Z"},{"alias_kind":"pith_short_16","alias_value":"SS3QO6AGL33UBC5J","created_at":"2026-07-05T09:22:33Z"},{"alias_kind":"pith_short_8","alias_value":"SS3QO6AG","created_at":"2026-07-05T09:22:33Z"}],"graph_snapshots":[{"event_id":"sha256:70fd32f723e65198a7e38b91ea8c96d231d37816aed1e4112efc35714e4a9836","target":"graph","created_at":"2026-07-05T09:22:33Z","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/2410.14509/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Voice Activity Detection (VAD) is the process of automatically determining whether a person is speaking and identifying the timing of their speech in an audiovisual data. Traditionally, this task has been tackled by processing either audio signals or visual data, or by combining both modalities through fusion or joint learning. In our study, drawing inspiration from recent advancements in visual-language models, we introduce a novel approach leveraging Contrastive Language-Image Pretraining (CLIP) models. The CLIP visual encoder analyzes video segments composed of the upper body of an individu","authors_text":"Andrea Appiani, Cigdem Beyan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-18T14:43:34Z","title":"CLIP-VAD: Exploiting Vision-Language Models for Voice Activity Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.14509","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":"sha256:3f84c68c19d700367f041f5cced73e80dec4cc350241190acd0d5fd77d6220b5","target":"record","created_at":"2026-07-05T09:22:33Z","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":"9421bb6908fee87c45e0bc73fa2a4679239ec399e34ccf6bc9df677f796e4fd6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-18T14:43:34Z","title_canon_sha256":"1d66787ea1bbece6afdf1e691726a55ca27a5d154094016d641d3a8497976bdd"},"schema_version":"1.0","source":{"id":"2410.14509","kind":"arxiv","version":1}},"canonical_sha256":"94b70778065ef7408ba962e49b948c8e9d0da6745c9008f19a5ea27af04c5c72","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"94b70778065ef7408ba962e49b948c8e9d0da6745c9008f19a5ea27af04c5c72","first_computed_at":"2026-07-05T09:22:33.339192Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:22:33.339192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"67RbUCLZMztUnInG0FqjlShgmY64mAMnM0en9xPUXjXWEqFd1zwMW5nx9xCXa6xqYunqX6/GC0r8m0PnBa6YBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:22:33.339679Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.14509","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3f84c68c19d700367f041f5cced73e80dec4cc350241190acd0d5fd77d6220b5","sha256:70fd32f723e65198a7e38b91ea8c96d231d37816aed1e4112efc35714e4a9836"],"state_sha256":"656fbd0916dd4449dbb2e8b0681c9831d28abcefa49f9de3361e759cd32a4c18"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d2Uxiff98tFY2HL3UuaSCHQPmikHQCNUvtgBLQaSTpH6AUe9sRi/LOes1z6U9IP4B6juzw93Xa6TT9PGlrJZAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T06:22:51.410536Z","bundle_sha256":"a0fbc701c03285826c9aefed3126e876510395b1e4a186aadb7e87e7d566f9d9"}}