{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:FE5ESRTB6446Z2WUFW4QCS3DID","short_pith_number":"pith:FE5ESRTB","canonical_record":{"source":{"id":"2507.00055","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-26T04:13:47Z","cross_cats_sorted":["cs.HC","cs.MM","eess.AS","eess.IV","eess.SP"],"title_canon_sha256":"2c7cb5a7a69ef8f811c8b3955731c790edef0524d11dbeaec874225f51306fc2","abstract_canon_sha256":"7c97d4f194528f38db1105f3a0afe0628765c6afe1db2b9920c7788e0d764cc6"},"schema_version":"1.0"},"canonical_sha256":"293a494661f739ecead42db9014b6340db2de4fc8630e05204c5d82d51515f89","source":{"kind":"arxiv","id":"2507.00055","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.00055","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"arxiv_version","alias_value":"2507.00055v1","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00055","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"pith_short_12","alias_value":"FE5ESRTB6446","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"pith_short_16","alias_value":"FE5ESRTB6446Z2WU","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"pith_short_8","alias_value":"FE5ESRTB","created_at":"2026-07-05T11:29:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:FE5ESRTB6446Z2WUFW4QCS3DID","target":"record","payload":{"canonical_record":{"source":{"id":"2507.00055","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-26T04:13:47Z","cross_cats_sorted":["cs.HC","cs.MM","eess.AS","eess.IV","eess.SP"],"title_canon_sha256":"2c7cb5a7a69ef8f811c8b3955731c790edef0524d11dbeaec874225f51306fc2","abstract_canon_sha256":"7c97d4f194528f38db1105f3a0afe0628765c6afe1db2b9920c7788e0d764cc6"},"schema_version":"1.0"},"canonical_sha256":"293a494661f739ecead42db9014b6340db2de4fc8630e05204c5d82d51515f89","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:35.906711Z","signature_b64":"jEgJiDwVQ72382O4NPFM/Qn3MFQp8OwK5H1SVobdiBm6U6EXWytNSxlyXgVo/W8la3YrqWbXflFQWGehX8FfBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"293a494661f739ecead42db9014b6340db2de4fc8630e05204c5d82d51515f89","last_reissued_at":"2026-07-05T11:29:35.906143Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:35.906143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.00055","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":"2026-07-05T11:29:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5UrcgRNRCSA9exoWHE3YimzWqInrV3S8iEaGB//5SygzUvUfwIFuxTf3oVK5MhXD3StRge5mtaPbyEfq2yGiBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T11:52:49.623889Z"},"content_sha256":"83d43b2da4aa7cf087f64d8a82999186504d19d57cf52ed2d17cf7aa95b22754","schema_version":"1.0","event_id":"sha256:83d43b2da4aa7cf087f64d8a82999186504d19d57cf52ed2d17cf7aa95b22754"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:FE5ESRTB6446Z2WUFW4QCS3DID","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging Unlabeled Audio-Visual Data in Speech Emotion Recognition using Knowledge Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC","cs.MM","eess.AS","eess.IV","eess.SP"],"primary_cat":"cs.LG","authors_text":"Pedro Morgado, Varsha Pendyala, William Sethares","submitted_at":"2025-06-26T04:13:47Z","abstract_excerpt":"Voice interfaces integral to the human-computer interaction systems can benefit from speech emotion recognition (SER) to customize responses based on user emotions. Since humans convey emotions through multi-modal audio-visual cues, developing SER systems using both the modalities is beneficial. However, collecting a vast amount of labeled data for their development is expensive. This paper proposes a knowledge distillation framework called LightweightSER (LiSER) that leverages unlabeled audio-visual data for SER, using large teacher models built on advanced speech and face representation mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00055","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/2507.00055/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":"2026-07-05T11:29:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2WtYCjAidS474YS9J5ld6EUDfQpLSaw6mU0w1KkYInehGt5PzXcQNljtouL3l2L1gpOAkFm2npcfWMNISXD/Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T11:52:49.624542Z"},"content_sha256":"49f2218ab95b5dcac11dbc846c8491c6900ade72b3cbc14ee8061f8153cf6fb0","schema_version":"1.0","event_id":"sha256:49f2218ab95b5dcac11dbc846c8491c6900ade72b3cbc14ee8061f8153cf6fb0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FE5ESRTB6446Z2WUFW4QCS3DID/bundle.json","state_url":"https://pith.science/pith/FE5ESRTB6446Z2WUFW4QCS3DID/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FE5ESRTB6446Z2WUFW4QCS3DID/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":"2026-08-04T11:52:49Z","links":{"resolver":"https://pith.science/pith/FE5ESRTB6446Z2WUFW4QCS3DID","bundle":"https://pith.science/pith/FE5ESRTB6446Z2WUFW4QCS3DID/bundle.json","state":"https://pith.science/pith/FE5ESRTB6446Z2WUFW4QCS3DID/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FE5ESRTB6446Z2WUFW4QCS3DID/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FE5ESRTB6446Z2WUFW4QCS3DID","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":"7c97d4f194528f38db1105f3a0afe0628765c6afe1db2b9920c7788e0d764cc6","cross_cats_sorted":["cs.HC","cs.MM","eess.AS","eess.IV","eess.SP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-26T04:13:47Z","title_canon_sha256":"2c7cb5a7a69ef8f811c8b3955731c790edef0524d11dbeaec874225f51306fc2"},"schema_version":"1.0","source":{"id":"2507.00055","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.00055","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"arxiv_version","alias_value":"2507.00055v1","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00055","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"pith_short_12","alias_value":"FE5ESRTB6446","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"pith_short_16","alias_value":"FE5ESRTB6446Z2WU","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"pith_short_8","alias_value":"FE5ESRTB","created_at":"2026-07-05T11:29:35Z"}],"graph_snapshots":[{"event_id":"sha256:49f2218ab95b5dcac11dbc846c8491c6900ade72b3cbc14ee8061f8153cf6fb0","target":"graph","created_at":"2026-07-05T11:29:35Z","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/2507.00055/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Voice interfaces integral to the human-computer interaction systems can benefit from speech emotion recognition (SER) to customize responses based on user emotions. Since humans convey emotions through multi-modal audio-visual cues, developing SER systems using both the modalities is beneficial. However, collecting a vast amount of labeled data for their development is expensive. This paper proposes a knowledge distillation framework called LightweightSER (LiSER) that leverages unlabeled audio-visual data for SER, using large teacher models built on advanced speech and face representation mode","authors_text":"Pedro Morgado, Varsha Pendyala, William Sethares","cross_cats":["cs.HC","cs.MM","eess.AS","eess.IV","eess.SP"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-26T04:13:47Z","title":"Leveraging Unlabeled Audio-Visual Data in Speech Emotion Recognition using Knowledge Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00055","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":"sha256:83d43b2da4aa7cf087f64d8a82999186504d19d57cf52ed2d17cf7aa95b22754","target":"record","created_at":"2026-07-05T11:29:35Z","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":"7c97d4f194528f38db1105f3a0afe0628765c6afe1db2b9920c7788e0d764cc6","cross_cats_sorted":["cs.HC","cs.MM","eess.AS","eess.IV","eess.SP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-26T04:13:47Z","title_canon_sha256":"2c7cb5a7a69ef8f811c8b3955731c790edef0524d11dbeaec874225f51306fc2"},"schema_version":"1.0","source":{"id":"2507.00055","kind":"arxiv","version":1}},"canonical_sha256":"293a494661f739ecead42db9014b6340db2de4fc8630e05204c5d82d51515f89","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"293a494661f739ecead42db9014b6340db2de4fc8630e05204c5d82d51515f89","first_computed_at":"2026-07-05T11:29:35.906143Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:29:35.906143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jEgJiDwVQ72382O4NPFM/Qn3MFQp8OwK5H1SVobdiBm6U6EXWytNSxlyXgVo/W8la3YrqWbXflFQWGehX8FfBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:29:35.906711Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.00055","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:83d43b2da4aa7cf087f64d8a82999186504d19d57cf52ed2d17cf7aa95b22754","sha256:49f2218ab95b5dcac11dbc846c8491c6900ade72b3cbc14ee8061f8153cf6fb0"],"state_sha256":"680911fb97926bb9631f1d1e35bf7d3ac68d08f9bf5d456ec43c14afab0cd0b3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v+r4btHz9ZZ990YXSUhNvszbv80pIzYmmIEGlD6WECgYPyzfyxnRWJIEKPHH/WSqRP0yYjqKXSGTtwYELMH4AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T11:52:49.633143Z","bundle_sha256":"ad78a10db795daff422e550622bb4746f615d1cf95cd86acdabafbaadc0b40e5"}}