{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:NFRYWL5DETIB7JJ7ALHN27XU3K","short_pith_number":"pith:NFRYWL5D","canonical_record":{"source":{"id":"2104.02571","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-04-06T15:10:14Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"e99b4d02ed5732c66035e869d8d2c1974403459e0788c7479fadf7254e401be8","abstract_canon_sha256":"64e84718b95122d1a8cd78c01a3280255b83898938482b94e728a8d7a0400591"},"schema_version":"1.0"},"canonical_sha256":"69638b2fa324d01fa53f02cedd7ef4dab10d8ce0776aaf9ada766595984443b7","source":{"kind":"arxiv","id":"2104.02571","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.02571","created_at":"2026-07-05T02:55:55Z"},{"alias_kind":"arxiv_version","alias_value":"2104.02571v2","created_at":"2026-07-05T02:55:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.02571","created_at":"2026-07-05T02:55:55Z"},{"alias_kind":"pith_short_12","alias_value":"NFRYWL5DETIB","created_at":"2026-07-05T02:55:55Z"},{"alias_kind":"pith_short_16","alias_value":"NFRYWL5DETIB7JJ7","created_at":"2026-07-05T02:55:55Z"},{"alias_kind":"pith_short_8","alias_value":"NFRYWL5D","created_at":"2026-07-05T02:55:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:NFRYWL5DETIB7JJ7ALHN27XU3K","target":"record","payload":{"canonical_record":{"source":{"id":"2104.02571","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-04-06T15:10:14Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"e99b4d02ed5732c66035e869d8d2c1974403459e0788c7479fadf7254e401be8","abstract_canon_sha256":"64e84718b95122d1a8cd78c01a3280255b83898938482b94e728a8d7a0400591"},"schema_version":"1.0"},"canonical_sha256":"69638b2fa324d01fa53f02cedd7ef4dab10d8ce0776aaf9ada766595984443b7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:55:55.177566Z","signature_b64":"touS9JTBaxHILbr/isK06hHomgSWp7hbGSI0kjfe8g6mgH9am5L3TXS9ehciweeZScQJnwdYXCw1RAArxC56DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69638b2fa324d01fa53f02cedd7ef4dab10d8ce0776aaf9ada766595984443b7","last_reissued_at":"2026-07-05T02:55:55.177081Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:55:55.177081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.02571","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:55:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J8JI6fP1T/gx/56zIh6lFA8RtAnDVQosQrxa1uIVXZFrXRCO1RQQ8m4y0KNZPTGmFSsjmijElmyPK+LFd8SwCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T13:51:28.303412Z"},"content_sha256":"34c8f77fc6fbe9f298941cafcb00cadf32dbe1c7ad58ae4f323e120fcfd8fb15","schema_version":"1.0","event_id":"sha256:34c8f77fc6fbe9f298941cafcb00cadf32dbe1c7ad58ae4f323e120fcfd8fb15"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:NFRYWL5DETIB7JJ7ALHN27XU3K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Speaker embeddings by modeling channel-wise correlations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.AS","authors_text":"Johan Rohdin, Lukas Burget, Themos Stafylakis","submitted_at":"2021-04-06T15:10:14Z","abstract_excerpt":"Speaker embeddings extracted with deep 2D convolutional neural networks are typically modeled as projections of first and second order statistics of channel-frequency pairs onto a linear layer, using either average or attentive pooling along the time axis. In this paper we examine an alternative pooling method, where pairwise correlations between channels for given frequencies are used as statistics. The method is inspired by style-transfer methods in computer vision, where the style of an image, modeled by the matrix of channel-wise correlations, is transferred to another image, in order to p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.02571","kind":"arxiv","version":2},"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/2104.02571/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":"2026-07-05T02:55:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JcmtEOwyNnNXotvq72U5Pokc5G+YqCb/RzICofhiYu35vS3gyoVBAZpiZiP4gdpt48WBb9x0QeqsqfVKcMACBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T13:51:28.303997Z"},"content_sha256":"90423a88d90204f82fba4adf27589de79a378b7b610c6a5cbe1f1ebdeaf9b467","schema_version":"1.0","event_id":"sha256:90423a88d90204f82fba4adf27589de79a378b7b610c6a5cbe1f1ebdeaf9b467"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NFRYWL5DETIB7JJ7ALHN27XU3K/bundle.json","state_url":"https://pith.science/pith/NFRYWL5DETIB7JJ7ALHN27XU3K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NFRYWL5DETIB7JJ7ALHN27XU3K/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":"2026-08-22T13:51:28Z","links":{"resolver":"https://pith.science/pith/NFRYWL5DETIB7JJ7ALHN27XU3K","bundle":"https://pith.science/pith/NFRYWL5DETIB7JJ7ALHN27XU3K/bundle.json","state":"https://pith.science/pith/NFRYWL5DETIB7JJ7ALHN27XU3K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NFRYWL5DETIB7JJ7ALHN27XU3K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:NFRYWL5DETIB7JJ7ALHN27XU3K","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":"64e84718b95122d1a8cd78c01a3280255b83898938482b94e728a8d7a0400591","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-04-06T15:10:14Z","title_canon_sha256":"e99b4d02ed5732c66035e869d8d2c1974403459e0788c7479fadf7254e401be8"},"schema_version":"1.0","source":{"id":"2104.02571","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.02571","created_at":"2026-07-05T02:55:55Z"},{"alias_kind":"arxiv_version","alias_value":"2104.02571v2","created_at":"2026-07-05T02:55:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.02571","created_at":"2026-07-05T02:55:55Z"},{"alias_kind":"pith_short_12","alias_value":"NFRYWL5DETIB","created_at":"2026-07-05T02:55:55Z"},{"alias_kind":"pith_short_16","alias_value":"NFRYWL5DETIB7JJ7","created_at":"2026-07-05T02:55:55Z"},{"alias_kind":"pith_short_8","alias_value":"NFRYWL5D","created_at":"2026-07-05T02:55:55Z"}],"graph_snapshots":[{"event_id":"sha256:90423a88d90204f82fba4adf27589de79a378b7b610c6a5cbe1f1ebdeaf9b467","target":"graph","created_at":"2026-07-05T02:55:55Z","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/2104.02571/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speaker embeddings extracted with deep 2D convolutional neural networks are typically modeled as projections of first and second order statistics of channel-frequency pairs onto a linear layer, using either average or attentive pooling along the time axis. In this paper we examine an alternative pooling method, where pairwise correlations between channels for given frequencies are used as statistics. The method is inspired by style-transfer methods in computer vision, where the style of an image, modeled by the matrix of channel-wise correlations, is transferred to another image, in order to p","authors_text":"Johan Rohdin, Lukas Burget, Themos Stafylakis","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-04-06T15:10:14Z","title":"Speaker embeddings by modeling channel-wise correlations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.02571","kind":"arxiv","version":2},"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":"sha256:34c8f77fc6fbe9f298941cafcb00cadf32dbe1c7ad58ae4f323e120fcfd8fb15","target":"record","created_at":"2026-07-05T02:55:55Z","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":"64e84718b95122d1a8cd78c01a3280255b83898938482b94e728a8d7a0400591","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-04-06T15:10:14Z","title_canon_sha256":"e99b4d02ed5732c66035e869d8d2c1974403459e0788c7479fadf7254e401be8"},"schema_version":"1.0","source":{"id":"2104.02571","kind":"arxiv","version":2}},"canonical_sha256":"69638b2fa324d01fa53f02cedd7ef4dab10d8ce0776aaf9ada766595984443b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"69638b2fa324d01fa53f02cedd7ef4dab10d8ce0776aaf9ada766595984443b7","first_computed_at":"2026-07-05T02:55:55.177081Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:55:55.177081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"touS9JTBaxHILbr/isK06hHomgSWp7hbGSI0kjfe8g6mgH9am5L3TXS9ehciweeZScQJnwdYXCw1RAArxC56DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:55:55.177566Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.02571","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:34c8f77fc6fbe9f298941cafcb00cadf32dbe1c7ad58ae4f323e120fcfd8fb15","sha256:90423a88d90204f82fba4adf27589de79a378b7b610c6a5cbe1f1ebdeaf9b467"],"state_sha256":"0b8fe3377d0252c6a794b8ce5a6fca7a24aad837eb4f3dc9ff16cb8bcb526370"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z4WQB1Mf6Vt4pq9Q8Dyv1KJfRnITUykTX3eLlmbhCYqWVtoFoGSvZwjBs1gQTPPQZ9u83JKjMTRQ2aVxypGcAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T13:51:28.308719Z","bundle_sha256":"acd7ef2d484189297821f31fff70f498dbeb4e925dc02d99b11ce32c8ce32b42"}}