{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:WMU7A6J5N33EP3IDBBUB3LRDEC","short_pith_number":"pith:WMU7A6J5","canonical_record":{"source":{"id":"2111.02735","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-11-04T10:39:06Z","cross_cats_sorted":["cs.NE","cs.SD","eess.AS"],"title_canon_sha256":"70471776e1848d5e7f86fba11313cd5e569cbd9516b06e2fed36208e604b13c9","abstract_canon_sha256":"d0e8ec2d0dbea98c4c0fbca032825ca5661d4743aa166eb89dfdbc7a6b803b5b"},"schema_version":"1.0"},"canonical_sha256":"b329f0793d6ef647ed0308681dae2320ba79e13dfeb8c722d13713a40bb5a14e","source":{"kind":"arxiv","id":"2111.02735","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.02735","created_at":"2026-07-05T05:02:55Z"},{"alias_kind":"arxiv_version","alias_value":"2111.02735v3","created_at":"2026-07-05T05:02:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.02735","created_at":"2026-07-05T05:02:55Z"},{"alias_kind":"pith_short_12","alias_value":"WMU7A6J5N33E","created_at":"2026-07-05T05:02:55Z"},{"alias_kind":"pith_short_16","alias_value":"WMU7A6J5N33EP3ID","created_at":"2026-07-05T05:02:55Z"},{"alias_kind":"pith_short_8","alias_value":"WMU7A6J5","created_at":"2026-07-05T05:02:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:WMU7A6J5N33EP3IDBBUB3LRDEC","target":"record","payload":{"canonical_record":{"source":{"id":"2111.02735","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-11-04T10:39:06Z","cross_cats_sorted":["cs.NE","cs.SD","eess.AS"],"title_canon_sha256":"70471776e1848d5e7f86fba11313cd5e569cbd9516b06e2fed36208e604b13c9","abstract_canon_sha256":"d0e8ec2d0dbea98c4c0fbca032825ca5661d4743aa166eb89dfdbc7a6b803b5b"},"schema_version":"1.0"},"canonical_sha256":"b329f0793d6ef647ed0308681dae2320ba79e13dfeb8c722d13713a40bb5a14e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:02:55.634593Z","signature_b64":"ck5CoKdNIr9b+Tjusgn+0TsBvDrfKzzffrbXk6auaFX83Fbvza3JHrtiNnYYOsv+UWkazGRwRumawEpIqTQ6BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b329f0793d6ef647ed0308681dae2320ba79e13dfeb8c722d13713a40bb5a14e","last_reissued_at":"2026-07-05T05:02:55.634177Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:02:55.634177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.02735","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":"2026-07-05T05:02:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"60bhJmV46Xncy/9rt5wMmVdleLSgSeF06V7YMbrgP31iSWeQkCe8FigmK2hnAs46j106tarvPFHpFDlQCW8iAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:43:23.266686Z"},"content_sha256":"6488bcdb582207e32d8135b934c1a1258e190dbc24c8924de2d191991ec3c3f7","schema_version":"1.0","event_id":"sha256:6488bcdb582207e32d8135b934c1a1258e190dbc24c8924de2d191991ec3c3f7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:WMU7A6J5N33EP3IDBBUB3LRDEC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Fine-tuned Wav2vec 2.0/HuBERT Benchmark For Speech Emotion Recognition, Speaker Verification and Spoken Language Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Abdelmoumene Boumadane, Abdelwahab Heba, Yingzhi Wang","submitted_at":"2021-11-04T10:39:06Z","abstract_excerpt":"Speech self-supervised models such as wav2vec 2.0 and HuBERT are making revolutionary progress in Automatic Speech Recognition (ASR). However, they have not been totally proven to produce better performance on tasks other than ASR. In this work, we explored partial fine-tuning and entire fine-tuning on wav2vec 2.0 and HuBERT pre-trained models for three non-ASR speech tasks: Speech Emotion Recognition, Speaker Verification and Spoken Language Understanding. With simple proposed downstream frameworks, the best scores reached 79.58% weighted accuracy on speaker-dependent setting and 73.01% weigh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.02735","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/2111.02735/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":"2026-07-05T05:02:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yogFXmkFAqEv/qLwe+y3ufWniJ8yjU+rfegEY5pHAkOROO1jr1dxv0pw4NZs42c82AexSjX0cvWxakK1oWKkDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:43:23.267057Z"},"content_sha256":"ee213eff714d96e01e464ffc92cdbd56aac85fa480a19bf2d9b4e0063c247871","schema_version":"1.0","event_id":"sha256:ee213eff714d96e01e464ffc92cdbd56aac85fa480a19bf2d9b4e0063c247871"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WMU7A6J5N33EP3IDBBUB3LRDEC/bundle.json","state_url":"https://pith.science/pith/WMU7A6J5N33EP3IDBBUB3LRDEC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WMU7A6J5N33EP3IDBBUB3LRDEC/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":"2026-07-07T08:43:23Z","links":{"resolver":"https://pith.science/pith/WMU7A6J5N33EP3IDBBUB3LRDEC","bundle":"https://pith.science/pith/WMU7A6J5N33EP3IDBBUB3LRDEC/bundle.json","state":"https://pith.science/pith/WMU7A6J5N33EP3IDBBUB3LRDEC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WMU7A6J5N33EP3IDBBUB3LRDEC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:WMU7A6J5N33EP3IDBBUB3LRDEC","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":"d0e8ec2d0dbea98c4c0fbca032825ca5661d4743aa166eb89dfdbc7a6b803b5b","cross_cats_sorted":["cs.NE","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-11-04T10:39:06Z","title_canon_sha256":"70471776e1848d5e7f86fba11313cd5e569cbd9516b06e2fed36208e604b13c9"},"schema_version":"1.0","source":{"id":"2111.02735","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.02735","created_at":"2026-07-05T05:02:55Z"},{"alias_kind":"arxiv_version","alias_value":"2111.02735v3","created_at":"2026-07-05T05:02:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.02735","created_at":"2026-07-05T05:02:55Z"},{"alias_kind":"pith_short_12","alias_value":"WMU7A6J5N33E","created_at":"2026-07-05T05:02:55Z"},{"alias_kind":"pith_short_16","alias_value":"WMU7A6J5N33EP3ID","created_at":"2026-07-05T05:02:55Z"},{"alias_kind":"pith_short_8","alias_value":"WMU7A6J5","created_at":"2026-07-05T05:02:55Z"}],"graph_snapshots":[{"event_id":"sha256:ee213eff714d96e01e464ffc92cdbd56aac85fa480a19bf2d9b4e0063c247871","target":"graph","created_at":"2026-07-05T05:02:55Z","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/2111.02735/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech self-supervised models such as wav2vec 2.0 and HuBERT are making revolutionary progress in Automatic Speech Recognition (ASR). However, they have not been totally proven to produce better performance on tasks other than ASR. In this work, we explored partial fine-tuning and entire fine-tuning on wav2vec 2.0 and HuBERT pre-trained models for three non-ASR speech tasks: Speech Emotion Recognition, Speaker Verification and Spoken Language Understanding. With simple proposed downstream frameworks, the best scores reached 79.58% weighted accuracy on speaker-dependent setting and 73.01% weigh","authors_text":"Abdelmoumene Boumadane, Abdelwahab Heba, Yingzhi Wang","cross_cats":["cs.NE","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-11-04T10:39:06Z","title":"A Fine-tuned Wav2vec 2.0/HuBERT Benchmark For Speech Emotion Recognition, Speaker Verification and Spoken Language Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.02735","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":"sha256:6488bcdb582207e32d8135b934c1a1258e190dbc24c8924de2d191991ec3c3f7","target":"record","created_at":"2026-07-05T05:02:55Z","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":"d0e8ec2d0dbea98c4c0fbca032825ca5661d4743aa166eb89dfdbc7a6b803b5b","cross_cats_sorted":["cs.NE","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-11-04T10:39:06Z","title_canon_sha256":"70471776e1848d5e7f86fba11313cd5e569cbd9516b06e2fed36208e604b13c9"},"schema_version":"1.0","source":{"id":"2111.02735","kind":"arxiv","version":3}},"canonical_sha256":"b329f0793d6ef647ed0308681dae2320ba79e13dfeb8c722d13713a40bb5a14e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b329f0793d6ef647ed0308681dae2320ba79e13dfeb8c722d13713a40bb5a14e","first_computed_at":"2026-07-05T05:02:55.634177Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:02:55.634177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ck5CoKdNIr9b+Tjusgn+0TsBvDrfKzzffrbXk6auaFX83Fbvza3JHrtiNnYYOsv+UWkazGRwRumawEpIqTQ6BA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:02:55.634593Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.02735","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6488bcdb582207e32d8135b934c1a1258e190dbc24c8924de2d191991ec3c3f7","sha256:ee213eff714d96e01e464ffc92cdbd56aac85fa480a19bf2d9b4e0063c247871"],"state_sha256":"f69618eb2a61038eb7bffdc204fa8e1ddc63f03bae9f39ff623daab8cc03e8d3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/JyvSWTkujm9cTeaKtZoAnRm4usxDma1KRjPojTd9dhmGs2IAbGoKzaPJzvGKJGUCckmawH4Y8FVM3tWFonYAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T08:43:23.268981Z","bundle_sha256":"ab4e845c0a07934568c69ac9d09ec71c6ce1382553d283c7d4e14521430dcdaf"}}