{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:AWVX77V3NMJFKOC75QECJV4OTC","short_pith_number":"pith:AWVX77V3","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"},"canonical_sha256":"05ab7ffebb6b1255385fec0824d78e98b3c14da8551bc203d023c2c5d8cc3cb6","source":{"kind":"arxiv","id":"2607.07294","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.07294","created_at":"2026-07-09T01:20:20Z"},{"alias_kind":"arxiv_version","alias_value":"2607.07294v1","created_at":"2026-07-09T01:20:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.07294","created_at":"2026-07-09T01:20:20Z"},{"alias_kind":"pith_short_12","alias_value":"AWVX77V3NMJF","created_at":"2026-07-09T01:20:20Z"},{"alias_kind":"pith_short_16","alias_value":"AWVX77V3NMJFKOC7","created_at":"2026-07-09T01:20:20Z"},{"alias_kind":"pith_short_8","alias_value":"AWVX77V3","created_at":"2026-07-09T01:20:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:AWVX77V3NMJFKOC75QECJV4OTC","target":"record","payload":{"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"},"canonical_sha256":"05ab7ffebb6b1255385fec0824d78e98b3c14da8551bc203d023c2c5d8cc3cb6","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"},"source_kind":"arxiv","source_id":"2607.07294","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":"2026-07-09T01:20:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J/zBm69dDU6JUGxCpGR75KbcxYJ5bryqhdZhGKywkhq+nAo7ECaHkDPBNKOSQT2VLxzyyJOEPaN5N3pXgQ8lCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:04:16.772051Z"},"content_sha256":"9a6ca582eef05efd6796f462f99c826b6c353937c8f1277505d6c3a3739472e8","schema_version":"1.0","event_id":"sha256:9a6ca582eef05efd6796f462f99c826b6c353937c8f1277505d6c3a3739472e8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:AWVX77V3NMJFKOC75QECJV4OTC","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-09T01:20:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UZMwwQIXQL8yDg/lVGPwlrGxVsG1j5yoLsBaIZSHWfYbathj+jm0zdVhVbXOYP+XkIv03RUbuzluon4Q9gJCBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:04:16.772594Z"},"content_sha256":"3e8ced8cede2feeef8dcf94f39f6a76081d2b0b1219faed2b5e91c8b0673c844","schema_version":"1.0","event_id":"sha256:3e8ced8cede2feeef8dcf94f39f6a76081d2b0b1219faed2b5e91c8b0673c844"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AWVX77V3NMJFKOC75QECJV4OTC/bundle.json","state_url":"https://pith.science/pith/AWVX77V3NMJFKOC75QECJV4OTC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AWVX77V3NMJFKOC75QECJV4OTC/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":"2026-08-04T23:04:16Z","links":{"resolver":"https://pith.science/pith/AWVX77V3NMJFKOC75QECJV4OTC","bundle":"https://pith.science/pith/AWVX77V3NMJFKOC75QECJV4OTC/bundle.json","state":"https://pith.science/pith/AWVX77V3NMJFKOC75QECJV4OTC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AWVX77V3NMJFKOC75QECJV4OTC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AWVX77V3NMJFKOC75QECJV4OTC","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":"7c1e22e2fc28caaf59ec43340e57e5a12ac81d42254b42955850e23d50d4438b","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-08T11:34:00Z","title_canon_sha256":"cb26a2abfa926fe5447ecf0dee9fbfc4f6e7cd1db27a6c732a37353d28e4b009"},"schema_version":"1.0","source":{"id":"2607.07294","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.07294","created_at":"2026-07-09T01:20:20Z"},{"alias_kind":"arxiv_version","alias_value":"2607.07294v1","created_at":"2026-07-09T01:20:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.07294","created_at":"2026-07-09T01:20:20Z"},{"alias_kind":"pith_short_12","alias_value":"AWVX77V3NMJF","created_at":"2026-07-09T01:20:20Z"},{"alias_kind":"pith_short_16","alias_value":"AWVX77V3NMJFKOC7","created_at":"2026-07-09T01:20:20Z"},{"alias_kind":"pith_short_8","alias_value":"AWVX77V3","created_at":"2026-07-09T01:20:20Z"}],"graph_snapshots":[{"event_id":"sha256:3e8ced8cede2feeef8dcf94f39f6a76081d2b0b1219faed2b5e91c8b0673c844","target":"graph","created_at":"2026-07-09T01:20:20Z","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/2607.07294/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Antonio Cano, Guillermo P\\'erez, Luis Merino, Randy Gomez","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-08T11:34:00Z","title":"Multimodal Voice Activity Projection for Turn-Taking in Social Robots with Voice-Activity-Related Pretrained Encoders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.07294","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":"sha256:9a6ca582eef05efd6796f462f99c826b6c353937c8f1277505d6c3a3739472e8","target":"record","created_at":"2026-07-09T01:20:20Z","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":"7c1e22e2fc28caaf59ec43340e57e5a12ac81d42254b42955850e23d50d4438b","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-08T11:34:00Z","title_canon_sha256":"cb26a2abfa926fe5447ecf0dee9fbfc4f6e7cd1db27a6c732a37353d28e4b009"},"schema_version":"1.0","source":{"id":"2607.07294","kind":"arxiv","version":1}},"canonical_sha256":"05ab7ffebb6b1255385fec0824d78e98b3c14da8551bc203d023c2c5d8cc3cb6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"05ab7ffebb6b1255385fec0824d78e98b3c14da8551bc203d023c2c5d8cc3cb6","first_computed_at":"2026-07-09T01:20:20.191907Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-09T01:20:20.191907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FModrq/iS8OeKtO+JYcPQ3EXQgny1YMkxNyORPVZqQEoswMmKuXlYEpB6F2HvvSKdQVsvy9depbgUSoxMYpyDw==","signature_status":"signed_v1","signed_at":"2026-07-09T01:20:20.192504Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.07294","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a6ca582eef05efd6796f462f99c826b6c353937c8f1277505d6c3a3739472e8","sha256:3e8ced8cede2feeef8dcf94f39f6a76081d2b0b1219faed2b5e91c8b0673c844"],"state_sha256":"7a574be7675c98cffef0dcf970bccdd04df9afff461145803d751c4baee6fccb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CuvTnT3RbjG1OM/IVS0eOJPzNeOsdyZoRTs985HRLJfWeNRwGpfjxIjqMeGBTja0VjrpZS//rvunTzXXDtinCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T23:04:16.779723Z","bundle_sha256":"add6d164349692f37502ad9b377638873b4c592a0aab729bf229afc29affa65b"}}