{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:FAU6UTFN2HSVHZ5LTYHHQVD2DH","short_pith_number":"pith:FAU6UTFN","canonical_record":{"source":{"id":"2205.09812","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-05-19T19:16:45Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"0ad4bc1dc0f4f9c7c7d0dcb62bf158ca3e3f05b631159f4651ff4706d48569f1","abstract_canon_sha256":"fd7f8cbfea17596acfa935a5ca53b33666989e95763fe2814dccd7733461885c"},"schema_version":"1.0"},"canonical_sha256":"2829ea4cadd1e553e7ab9e0e78547a19f745fa07a334126b3ebdf3e18743cc6f","source":{"kind":"arxiv","id":"2205.09812","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.09812","created_at":"2026-07-05T04:25:00Z"},{"alias_kind":"arxiv_version","alias_value":"2205.09812v1","created_at":"2026-07-05T04:25:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.09812","created_at":"2026-07-05T04:25:00Z"},{"alias_kind":"pith_short_12","alias_value":"FAU6UTFN2HSV","created_at":"2026-07-05T04:25:00Z"},{"alias_kind":"pith_short_16","alias_value":"FAU6UTFN2HSVHZ5L","created_at":"2026-07-05T04:25:00Z"},{"alias_kind":"pith_short_8","alias_value":"FAU6UTFN","created_at":"2026-07-05T04:25:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:FAU6UTFN2HSVHZ5LTYHHQVD2DH","target":"record","payload":{"canonical_record":{"source":{"id":"2205.09812","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-05-19T19:16:45Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"0ad4bc1dc0f4f9c7c7d0dcb62bf158ca3e3f05b631159f4651ff4706d48569f1","abstract_canon_sha256":"fd7f8cbfea17596acfa935a5ca53b33666989e95763fe2814dccd7733461885c"},"schema_version":"1.0"},"canonical_sha256":"2829ea4cadd1e553e7ab9e0e78547a19f745fa07a334126b3ebdf3e18743cc6f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:25:00.511704Z","signature_b64":"9hpTw7DqzdnUPatIoyLwRIoGyVPpffe3yS6L34G0zmeYIIdpdvsFw5kZ14yDq1mweV51FQAATcHC8EVs4Y7FDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2829ea4cadd1e553e7ab9e0e78547a19f745fa07a334126b3ebdf3e18743cc6f","last_reissued_at":"2026-07-05T04:25:00.511211Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:25:00.511211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.09812","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":"2026-07-05T04:25:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gzQvuJFB2v7K/AnHdTJpOMibfDw1ye4hKF9l/SMcpkWY2zsBPFmYZAIC9rTPkbpNFwkTicTURvnCF9KuDAvdBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T15:58:15.181452Z"},"content_sha256":"8373aca0e1dde1e0ad4abf231d698d99a3b65a2b7c8c62c23c95a84c2fee327c","schema_version":"1.0","event_id":"sha256:8373aca0e1dde1e0ad4abf231d698d99a3b65a2b7c8c62c23c95a84c2fee327c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:FAU6UTFN2HSVHZ5LTYHHQVD2DH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Voice Activity Projection: Self-supervised Learning of Turn-taking Events","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Erik Ekstedt, Gabriel Skantze","submitted_at":"2022-05-19T19:16:45Z","abstract_excerpt":"The modeling of turn-taking in dialog can be viewed as the modeling of the dynamics of voice activity of the interlocutors. We extend prior work and define the predictive task of Voice Activity Projection, a general, self-supervised objective, as a way to train turn-taking models without the need of labeled data. We highlight a theoretical weakness with prior approaches, arguing for the need of modeling the dependency of voice activity events in the projection window. We propose four zero-shot tasks, related to the prediction of upcoming turn-shifts and backchannels, and show that the proposed"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.09812","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/2205.09812/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":"2026-07-05T04:25:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WSzzO7X98q6CN8TaPzUFfXUbTKPf27Iv3XOdv6hS7K9YGHT00ufo142JPmaVoGkmDYP/e+itUPd0l+Liux80Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T15:58:15.181824Z"},"content_sha256":"234d36734133ad7a59f525e17300ab58a952853c10971d1dcb48d9df7a50d6aa","schema_version":"1.0","event_id":"sha256:234d36734133ad7a59f525e17300ab58a952853c10971d1dcb48d9df7a50d6aa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FAU6UTFN2HSVHZ5LTYHHQVD2DH/bundle.json","state_url":"https://pith.science/pith/FAU6UTFN2HSVHZ5LTYHHQVD2DH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FAU6UTFN2HSVHZ5LTYHHQVD2DH/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":"2026-07-05T15:58:15Z","links":{"resolver":"https://pith.science/pith/FAU6UTFN2HSVHZ5LTYHHQVD2DH","bundle":"https://pith.science/pith/FAU6UTFN2HSVHZ5LTYHHQVD2DH/bundle.json","state":"https://pith.science/pith/FAU6UTFN2HSVHZ5LTYHHQVD2DH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FAU6UTFN2HSVHZ5LTYHHQVD2DH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:FAU6UTFN2HSVHZ5LTYHHQVD2DH","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":"fd7f8cbfea17596acfa935a5ca53b33666989e95763fe2814dccd7733461885c","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-05-19T19:16:45Z","title_canon_sha256":"0ad4bc1dc0f4f9c7c7d0dcb62bf158ca3e3f05b631159f4651ff4706d48569f1"},"schema_version":"1.0","source":{"id":"2205.09812","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.09812","created_at":"2026-07-05T04:25:00Z"},{"alias_kind":"arxiv_version","alias_value":"2205.09812v1","created_at":"2026-07-05T04:25:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.09812","created_at":"2026-07-05T04:25:00Z"},{"alias_kind":"pith_short_12","alias_value":"FAU6UTFN2HSV","created_at":"2026-07-05T04:25:00Z"},{"alias_kind":"pith_short_16","alias_value":"FAU6UTFN2HSVHZ5L","created_at":"2026-07-05T04:25:00Z"},{"alias_kind":"pith_short_8","alias_value":"FAU6UTFN","created_at":"2026-07-05T04:25:00Z"}],"graph_snapshots":[{"event_id":"sha256:234d36734133ad7a59f525e17300ab58a952853c10971d1dcb48d9df7a50d6aa","target":"graph","created_at":"2026-07-05T04:25:00Z","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/2205.09812/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The modeling of turn-taking in dialog can be viewed as the modeling of the dynamics of voice activity of the interlocutors. We extend prior work and define the predictive task of Voice Activity Projection, a general, self-supervised objective, as a way to train turn-taking models without the need of labeled data. We highlight a theoretical weakness with prior approaches, arguing for the need of modeling the dependency of voice activity events in the projection window. We propose four zero-shot tasks, related to the prediction of upcoming turn-shifts and backchannels, and show that the proposed","authors_text":"Erik Ekstedt, Gabriel Skantze","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-05-19T19:16:45Z","title":"Voice Activity Projection: Self-supervised Learning of Turn-taking Events"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.09812","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":"sha256:8373aca0e1dde1e0ad4abf231d698d99a3b65a2b7c8c62c23c95a84c2fee327c","target":"record","created_at":"2026-07-05T04:25:00Z","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":"fd7f8cbfea17596acfa935a5ca53b33666989e95763fe2814dccd7733461885c","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-05-19T19:16:45Z","title_canon_sha256":"0ad4bc1dc0f4f9c7c7d0dcb62bf158ca3e3f05b631159f4651ff4706d48569f1"},"schema_version":"1.0","source":{"id":"2205.09812","kind":"arxiv","version":1}},"canonical_sha256":"2829ea4cadd1e553e7ab9e0e78547a19f745fa07a334126b3ebdf3e18743cc6f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2829ea4cadd1e553e7ab9e0e78547a19f745fa07a334126b3ebdf3e18743cc6f","first_computed_at":"2026-07-05T04:25:00.511211Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:25:00.511211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9hpTw7DqzdnUPatIoyLwRIoGyVPpffe3yS6L34G0zmeYIIdpdvsFw5kZ14yDq1mweV51FQAATcHC8EVs4Y7FDg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:25:00.511704Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.09812","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8373aca0e1dde1e0ad4abf231d698d99a3b65a2b7c8c62c23c95a84c2fee327c","sha256:234d36734133ad7a59f525e17300ab58a952853c10971d1dcb48d9df7a50d6aa"],"state_sha256":"7734a428090c538a58236259bf0be491e1f2553042fda7b102435c7f133d9e26"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9xWjoBlPyxZSEGlBe9Fz1ZmM371ScN69nDutJya5P2emJsmxQoZ318dp5JI6sPVFwQp8+LsiZCtC6ySi9dOIAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T15:58:15.183918Z","bundle_sha256":"83a20102ba2536355e66301498199bcd07d98459c82a69f69d034cdb4572a441"}}