{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:P3H2P775TD3ZC55VASBAYWCFX4","short_pith_number":"pith:P3H2P775","schema_version":"1.0","canonical_sha256":"7ecfa7fffd98f79177b504820c5845bf2b9259bc8869d452a2982bb0beb91027","source":{"kind":"arxiv","id":"2211.01246","version":2},"attestation_state":"computed","paper":{"title":"data2vec-aqc: Search for the right Teaching Assistant in the Teacher-Student training setup","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Sreyan Ghosh, S. Umesh, Vasista Sai Lodagala","submitted_at":"2022-11-02T16:29:59Z","abstract_excerpt":"In this paper, we propose a new Self-Supervised Learning (SSL) algorithm called data2vec-aqc, for speech representation learning from unlabeled speech data. Our goal is to improve SSL for speech in domains where both unlabeled and labeled data are limited. Building on the recently introduced data2vec, we introduce additional modules to the data2vec framework that leverage the benefit of data augmentations, quantized representations, and clustering. The interaction between these modules helps solve the cross-contrastive loss as an additional self-supervised objective. data2vec-aqc achieves up t"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2211.01246","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-11-02T16:29:59Z","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"title_canon_sha256":"c52c4769c27ab625a0ff6fa63913a563bd615cf7b7769b6732504ae6889695cc","abstract_canon_sha256":"823e15ded047c4c06816a6bfe96fcddcfd9a62d9e1c7ef13a212448f18fcbf26"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:09:46.036282Z","signature_b64":"XcN/fPqgsHuc3pxecTFolJG5ouMGOPZ/FkbSLMgdh7HL4h9rKKjSYEf+xnJ6WSOJGLmdoCUwKVQsunSOgTHWBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ecfa7fffd98f79177b504820c5845bf2b9259bc8869d452a2982bb0beb91027","last_reissued_at":"2026-07-05T06:09:46.035814Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:09:46.035814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"data2vec-aqc: Search for the right Teaching Assistant in the Teacher-Student training setup","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Sreyan Ghosh, S. Umesh, Vasista Sai Lodagala","submitted_at":"2022-11-02T16:29:59Z","abstract_excerpt":"In this paper, we propose a new Self-Supervised Learning (SSL) algorithm called data2vec-aqc, for speech representation learning from unlabeled speech data. Our goal is to improve SSL for speech in domains where both unlabeled and labeled data are limited. Building on the recently introduced data2vec, we introduce additional modules to the data2vec framework that leverage the benefit of data augmentations, quantized representations, and clustering. The interaction between these modules helps solve the cross-contrastive loss as an additional self-supervised objective. data2vec-aqc achieves up t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.01246","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/2211.01246/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2211.01246","created_at":"2026-07-05T06:09:46.035876+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.01246v2","created_at":"2026-07-05T06:09:46.035876+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.01246","created_at":"2026-07-05T06:09:46.035876+00:00"},{"alias_kind":"pith_short_12","alias_value":"P3H2P775TD3Z","created_at":"2026-07-05T06:09:46.035876+00:00"},{"alias_kind":"pith_short_16","alias_value":"P3H2P775TD3ZC55V","created_at":"2026-07-05T06:09:46.035876+00:00"},{"alias_kind":"pith_short_8","alias_value":"P3H2P775","created_at":"2026-07-05T06:09:46.035876+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09335","citing_title":"Factors affecting ASR performance: A study using state of the art ASR models in Indic Languages","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P3H2P775TD3ZC55VASBAYWCFX4","json":"https://pith.science/pith/P3H2P775TD3ZC55VASBAYWCFX4.json","graph_json":"https://pith.science/api/pith-number/P3H2P775TD3ZC55VASBAYWCFX4/graph.json","events_json":"https://pith.science/api/pith-number/P3H2P775TD3ZC55VASBAYWCFX4/events.json","paper":"https://pith.science/paper/P3H2P775"},"agent_actions":{"view_html":"https://pith.science/pith/P3H2P775TD3ZC55VASBAYWCFX4","download_json":"https://pith.science/pith/P3H2P775TD3ZC55VASBAYWCFX4.json","view_paper":"https://pith.science/paper/P3H2P775","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.01246&json=true","fetch_graph":"https://pith.science/api/pith-number/P3H2P775TD3ZC55VASBAYWCFX4/graph.json","fetch_events":"https://pith.science/api/pith-number/P3H2P775TD3ZC55VASBAYWCFX4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P3H2P775TD3ZC55VASBAYWCFX4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P3H2P775TD3ZC55VASBAYWCFX4/action/storage_attestation","attest_author":"https://pith.science/pith/P3H2P775TD3ZC55VASBAYWCFX4/action/author_attestation","sign_citation":"https://pith.science/pith/P3H2P775TD3ZC55VASBAYWCFX4/action/citation_signature","submit_replication":"https://pith.science/pith/P3H2P775TD3ZC55VASBAYWCFX4/action/replication_record"}},"created_at":"2026-07-05T06:09:46.035876+00:00","updated_at":"2026-07-05T06:09:46.035876+00:00"}