{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:AJIVCMBYOSXYTLG6J6TXGXMGNF","short_pith_number":"pith:AJIVCMBY","canonical_record":{"source":{"id":"2010.12951","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-10-24T18:44:00Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"4149458807bbb38747914d395834454c5063ab720da5d5eaaeb66002b72f03af","abstract_canon_sha256":"4ca9e3ce85cf2fffa2840b58c448bac5ea6f533a134e7dad21829eab8ed0569f"},"schema_version":"1.0"},"canonical_sha256":"025151303874af89acde4fa7735d86694c0123f88c445aa5e1adf4a8c9c5283a","source":{"kind":"arxiv","id":"2010.12951","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.12951","created_at":"2026-07-05T02:47:40Z"},{"alias_kind":"arxiv_version","alias_value":"2010.12951v3","created_at":"2026-07-05T02:47:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.12951","created_at":"2026-07-05T02:47:40Z"},{"alias_kind":"pith_short_12","alias_value":"AJIVCMBYOSXY","created_at":"2026-07-05T02:47:40Z"},{"alias_kind":"pith_short_16","alias_value":"AJIVCMBYOSXYTLG6","created_at":"2026-07-05T02:47:40Z"},{"alias_kind":"pith_short_8","alias_value":"AJIVCMBY","created_at":"2026-07-05T02:47:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:AJIVCMBYOSXYTLG6J6TXGXMGNF","target":"record","payload":{"canonical_record":{"source":{"id":"2010.12951","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-10-24T18:44:00Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"4149458807bbb38747914d395834454c5063ab720da5d5eaaeb66002b72f03af","abstract_canon_sha256":"4ca9e3ce85cf2fffa2840b58c448bac5ea6f533a134e7dad21829eab8ed0569f"},"schema_version":"1.0"},"canonical_sha256":"025151303874af89acde4fa7735d86694c0123f88c445aa5e1adf4a8c9c5283a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:47:40.184097Z","signature_b64":"yrQ0jPzulNWJ6MKkp9DW9FoGeRYww6aJKfot3CleYZCw6i5R57CokErnyP31mkc715fK/WHZblLlvmDa1woJCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"025151303874af89acde4fa7735d86694c0123f88c445aa5e1adf4a8c9c5283a","last_reissued_at":"2026-07-05T02:47:40.183535Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:47:40.183535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.12951","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:47:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2ljTUS5hdbSzk3hf7taKBjZ9I3NfsQDLzRMK5giyk3tGUfzqB8pUih+FAHFyho8NqSR9vTeVFou7tn8lwrMxCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T13:47:13.942467Z"},"content_sha256":"ed18ec9a50c9483d421770ef97137035aeae527c3aff2979ccacb2dc678f5725","schema_version":"1.0","event_id":"sha256:ed18ec9a50c9483d421770ef97137035aeae527c3aff2979ccacb2dc678f5725"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:AJIVCMBYOSXYTLG6J6TXGXMGNF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Y-Vector: Multiscale Waveform Encoder for Speaker Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Fei Jiang, Ge Zhu, Zhiyao Duan","submitted_at":"2020-10-24T18:44:00Z","abstract_excerpt":"State-of-the-art text-independent speaker verification systems typically use cepstral features or filter bank energies as speech features. Recent studies attempted to extract speaker embeddings directly from raw waveforms and have shown competitive results. In this paper, we propose a novel multi-scale waveform encoder that uses three convolution branches with different time scales to compute speech features from the waveform. These features are then processed by squeeze-and-excitation blocks, a multi-level feature aggregator, and a time delayed neural network (TDNN) to compute speaker embeddi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.12951","kind":"arxiv","version":3},"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/2010.12951/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":"2026-07-05T02:47:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MWhS0UeIhYXuQ4faiA11wpC8Ik4wBeNz1d401GBayyQ96uKg7hviXHn/yuHWo4YFdvCkOodOUfDxgNEAlAyLCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T13:47:13.942897Z"},"content_sha256":"4e85a32ecea9945d7d29d7c5bd15df4b48f1bedc5c368302863bf28b8ce14978","schema_version":"1.0","event_id":"sha256:4e85a32ecea9945d7d29d7c5bd15df4b48f1bedc5c368302863bf28b8ce14978"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AJIVCMBYOSXYTLG6J6TXGXMGNF/bundle.json","state_url":"https://pith.science/pith/AJIVCMBYOSXYTLG6J6TXGXMGNF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AJIVCMBYOSXYTLG6J6TXGXMGNF/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":"2026-07-17T13:47:13Z","links":{"resolver":"https://pith.science/pith/AJIVCMBYOSXYTLG6J6TXGXMGNF","bundle":"https://pith.science/pith/AJIVCMBYOSXYTLG6J6TXGXMGNF/bundle.json","state":"https://pith.science/pith/AJIVCMBYOSXYTLG6J6TXGXMGNF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AJIVCMBYOSXYTLG6J6TXGXMGNF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:AJIVCMBYOSXYTLG6J6TXGXMGNF","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":"4ca9e3ce85cf2fffa2840b58c448bac5ea6f533a134e7dad21829eab8ed0569f","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-10-24T18:44:00Z","title_canon_sha256":"4149458807bbb38747914d395834454c5063ab720da5d5eaaeb66002b72f03af"},"schema_version":"1.0","source":{"id":"2010.12951","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.12951","created_at":"2026-07-05T02:47:40Z"},{"alias_kind":"arxiv_version","alias_value":"2010.12951v3","created_at":"2026-07-05T02:47:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.12951","created_at":"2026-07-05T02:47:40Z"},{"alias_kind":"pith_short_12","alias_value":"AJIVCMBYOSXY","created_at":"2026-07-05T02:47:40Z"},{"alias_kind":"pith_short_16","alias_value":"AJIVCMBYOSXYTLG6","created_at":"2026-07-05T02:47:40Z"},{"alias_kind":"pith_short_8","alias_value":"AJIVCMBY","created_at":"2026-07-05T02:47:40Z"}],"graph_snapshots":[{"event_id":"sha256:4e85a32ecea9945d7d29d7c5bd15df4b48f1bedc5c368302863bf28b8ce14978","target":"graph","created_at":"2026-07-05T02:47:40Z","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/2010.12951/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"State-of-the-art text-independent speaker verification systems typically use cepstral features or filter bank energies as speech features. Recent studies attempted to extract speaker embeddings directly from raw waveforms and have shown competitive results. In this paper, we propose a novel multi-scale waveform encoder that uses three convolution branches with different time scales to compute speech features from the waveform. These features are then processed by squeeze-and-excitation blocks, a multi-level feature aggregator, and a time delayed neural network (TDNN) to compute speaker embeddi","authors_text":"Fei Jiang, Ge Zhu, Zhiyao Duan","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-10-24T18:44:00Z","title":"Y-Vector: Multiscale Waveform Encoder for Speaker Embedding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.12951","kind":"arxiv","version":3},"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:ed18ec9a50c9483d421770ef97137035aeae527c3aff2979ccacb2dc678f5725","target":"record","created_at":"2026-07-05T02:47:40Z","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":"4ca9e3ce85cf2fffa2840b58c448bac5ea6f533a134e7dad21829eab8ed0569f","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-10-24T18:44:00Z","title_canon_sha256":"4149458807bbb38747914d395834454c5063ab720da5d5eaaeb66002b72f03af"},"schema_version":"1.0","source":{"id":"2010.12951","kind":"arxiv","version":3}},"canonical_sha256":"025151303874af89acde4fa7735d86694c0123f88c445aa5e1adf4a8c9c5283a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"025151303874af89acde4fa7735d86694c0123f88c445aa5e1adf4a8c9c5283a","first_computed_at":"2026-07-05T02:47:40.183535Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:47:40.183535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yrQ0jPzulNWJ6MKkp9DW9FoGeRYww6aJKfot3CleYZCw6i5R57CokErnyP31mkc715fK/WHZblLlvmDa1woJCg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:47:40.184097Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.12951","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed18ec9a50c9483d421770ef97137035aeae527c3aff2979ccacb2dc678f5725","sha256:4e85a32ecea9945d7d29d7c5bd15df4b48f1bedc5c368302863bf28b8ce14978"],"state_sha256":"e9d896ec0c237585ec46db82b873014978f4c90a4d015acb438f7ecddaa8584b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hk2PYJua6eJkbL1gweOwQwx0MT0QrPjFawLTQDZw/IbYvqEWyZIz2/vnvxi4fl8+eJJczRZxU7WvExRuVztsBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T13:47:13.946114Z","bundle_sha256":"718fd7b5bbcc53fcf2d777ce289ab47f3781a8b22073c85fb12bac406b8be2c5"}}