{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AWVX77V3NMJFKOC75QECJV4OTC","short_pith_number":"pith:AWVX77V3","schema_version":"1.0","canonical_sha256":"05ab7ffebb6b1255385fec0824d78e98b3c14da8551bc203d023c2c5d8cc3cb6","source":{"kind":"arxiv","id":"2607.07294","version":1},"attestation_state":"computed","paper":{"title":"Multimodal Voice Activity Projection for Turn-Taking in Social Robots with Voice-Activity-Related Pretrained Encoders","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.RO","authors_text":"Antonio Cano, Guillermo P\\'erez, Luis Merino, Randy Gomez","submitted_at":"2026-07-08T11:34:00Z","abstract_excerpt":"Turn-taking prediction is a key requirement for social robots involved in human-human interaction, particularly in mediator settings, where the robot must anticipate conversational dynamics rather than merely react to pauses. This work presents a Multimodal Voice Activity Projection (MM-VAP) framework that extends the original audio-only VAP formulation to synchronized audio-visual inputs while preserving its self-supervised future-projection objective. The proposed approach builds on pretrained audio-visual backbones originally optimized for speech-related tasks and adapts them through Low-Ra"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.07294","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-08T11:34:00Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"cb26a2abfa926fe5447ecf0dee9fbfc4f6e7cd1db27a6c732a37353d28e4b009","abstract_canon_sha256":"7c1e22e2fc28caaf59ec43340e57e5a12ac81d42254b42955850e23d50d4438b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-09T01:20:20.192504Z","signature_b64":"FModrq/iS8OeKtO+JYcPQ3EXQgny1YMkxNyORPVZqQEoswMmKuXlYEpB6F2HvvSKdQVsvy9depbgUSoxMYpyDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05ab7ffebb6b1255385fec0824d78e98b3c14da8551bc203d023c2c5d8cc3cb6","last_reissued_at":"2026-07-09T01:20:20.191907Z","signature_status":"signed_v1","first_computed_at":"2026-07-09T01:20:20.191907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal Voice Activity Projection for Turn-Taking in Social Robots with Voice-Activity-Related Pretrained Encoders","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.RO","authors_text":"Antonio Cano, Guillermo P\\'erez, Luis Merino, Randy Gomez","submitted_at":"2026-07-08T11:34:00Z","abstract_excerpt":"Turn-taking prediction is a key requirement for social robots involved in human-human interaction, particularly in mediator settings, where the robot must anticipate conversational dynamics rather than merely react to pauses. This work presents a Multimodal Voice Activity Projection (MM-VAP) framework that extends the original audio-only VAP formulation to synchronized audio-visual inputs while preserving its self-supervised future-projection objective. The proposed approach builds on pretrained audio-visual backbones originally optimized for speech-related tasks and adapts them through Low-Ra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.07294","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/2607.07294/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.07294","created_at":"2026-07-09T01:20:20.192004+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.07294v1","created_at":"2026-07-09T01:20:20.192004+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.07294","created_at":"2026-07-09T01:20:20.192004+00:00"},{"alias_kind":"pith_short_12","alias_value":"AWVX77V3NMJF","created_at":"2026-07-09T01:20:20.192004+00:00"},{"alias_kind":"pith_short_16","alias_value":"AWVX77V3NMJFKOC7","created_at":"2026-07-09T01:20:20.192004+00:00"},{"alias_kind":"pith_short_8","alias_value":"AWVX77V3","created_at":"2026-07-09T01:20:20.192004+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AWVX77V3NMJFKOC75QECJV4OTC","json":"https://pith.science/pith/AWVX77V3NMJFKOC75QECJV4OTC.json","graph_json":"https://pith.science/api/pith-number/AWVX77V3NMJFKOC75QECJV4OTC/graph.json","events_json":"https://pith.science/api/pith-number/AWVX77V3NMJFKOC75QECJV4OTC/events.json","paper":"https://pith.science/paper/AWVX77V3"},"agent_actions":{"view_html":"https://pith.science/pith/AWVX77V3NMJFKOC75QECJV4OTC","download_json":"https://pith.science/pith/AWVX77V3NMJFKOC75QECJV4OTC.json","view_paper":"https://pith.science/paper/AWVX77V3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.07294&json=true","fetch_graph":"https://pith.science/api/pith-number/AWVX77V3NMJFKOC75QECJV4OTC/graph.json","fetch_events":"https://pith.science/api/pith-number/AWVX77V3NMJFKOC75QECJV4OTC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AWVX77V3NMJFKOC75QECJV4OTC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AWVX77V3NMJFKOC75QECJV4OTC/action/storage_attestation","attest_author":"https://pith.science/pith/AWVX77V3NMJFKOC75QECJV4OTC/action/author_attestation","sign_citation":"https://pith.science/pith/AWVX77V3NMJFKOC75QECJV4OTC/action/citation_signature","submit_replication":"https://pith.science/pith/AWVX77V3NMJFKOC75QECJV4OTC/action/replication_record"}},"created_at":"2026-07-09T01:20:20.192004+00:00","updated_at":"2026-07-09T01:20:20.192004+00:00"}