{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:WZJ5W3FH32Z57LCOXR423RPAHN","short_pith_number":"pith:WZJ5W3FH","schema_version":"1.0","canonical_sha256":"b653db6ca7deb3dfac4ebc79adc5e03b42a7e2e97241b7f5552ff46583d226fc","source":{"kind":"arxiv","id":"2005.07850","version":2},"attestation_state":"computed","paper":{"title":"Large scale weakly and semi-supervised learning for low-resource video ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Abdelrahman Mohamed, Alex Xiao, Christian Fuegen, Geoffrey Zweig, Kritika Singh, Ross Girshick, Sergey Edunov, Vimal Manohar, Vitaliy Liptchinsky, Yatharth Saraf","submitted_at":"2020-05-16T03:08:45Z","abstract_excerpt":"Many semi- and weakly-supervised approaches have been investigated for overcoming the labeling cost of building high quality speech recognition systems. On the challenging task of transcribing social media videos in low-resource conditions, we conduct a large scale systematic comparison between two self-labeling methods on one hand, and weakly-supervised pretraining using contextual metadata on the other. We investigate distillation methods at the frame level and the sequence level for hybrid, encoder-only CTC-based, and encoder-decoder speech recognition systems on Dutch and Romanian language"},"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":"2005.07850","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-05-16T03:08:45Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"f13f4fb0908e156f3e303dff466ba68c4dc81d30726e4bda9c9cf7a10dfd3100","abstract_canon_sha256":"afd6ac48fc36df9b5b251b3ad21de9df4b267b713bedb2560083a5dc18e65aee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:25:26.030283Z","signature_b64":"HuWVueyzlKBhW2mhiB3q1rqEAPJzuFWApsRKUsY4ZlG/IabWNfu12exchGJGNDFbmHnfzK9AjLRsCWek6YXtAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b653db6ca7deb3dfac4ebc79adc5e03b42a7e2e97241b7f5552ff46583d226fc","last_reissued_at":"2026-07-05T01:25:26.029865Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:25:26.029865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large scale weakly and semi-supervised learning for low-resource video ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Abdelrahman Mohamed, Alex Xiao, Christian Fuegen, Geoffrey Zweig, Kritika Singh, Ross Girshick, Sergey Edunov, Vimal Manohar, Vitaliy Liptchinsky, Yatharth Saraf","submitted_at":"2020-05-16T03:08:45Z","abstract_excerpt":"Many semi- and weakly-supervised approaches have been investigated for overcoming the labeling cost of building high quality speech recognition systems. On the challenging task of transcribing social media videos in low-resource conditions, we conduct a large scale systematic comparison between two self-labeling methods on one hand, and weakly-supervised pretraining using contextual metadata on the other. We investigate distillation methods at the frame level and the sequence level for hybrid, encoder-only CTC-based, and encoder-decoder speech recognition systems on Dutch and Romanian language"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.07850","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/2005.07850/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":"2005.07850","created_at":"2026-07-05T01:25:26.029929+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.07850v2","created_at":"2026-07-05T01:25:26.029929+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.07850","created_at":"2026-07-05T01:25:26.029929+00:00"},{"alias_kind":"pith_short_12","alias_value":"WZJ5W3FH32Z5","created_at":"2026-07-05T01:25:26.029929+00:00"},{"alias_kind":"pith_short_16","alias_value":"WZJ5W3FH32Z57LCO","created_at":"2026-07-05T01:25:26.029929+00:00"},{"alias_kind":"pith_short_8","alias_value":"WZJ5W3FH","created_at":"2026-07-05T01:25:26.029929+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WZJ5W3FH32Z57LCOXR423RPAHN","json":"https://pith.science/pith/WZJ5W3FH32Z57LCOXR423RPAHN.json","graph_json":"https://pith.science/api/pith-number/WZJ5W3FH32Z57LCOXR423RPAHN/graph.json","events_json":"https://pith.science/api/pith-number/WZJ5W3FH32Z57LCOXR423RPAHN/events.json","paper":"https://pith.science/paper/WZJ5W3FH"},"agent_actions":{"view_html":"https://pith.science/pith/WZJ5W3FH32Z57LCOXR423RPAHN","download_json":"https://pith.science/pith/WZJ5W3FH32Z57LCOXR423RPAHN.json","view_paper":"https://pith.science/paper/WZJ5W3FH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.07850&json=true","fetch_graph":"https://pith.science/api/pith-number/WZJ5W3FH32Z57LCOXR423RPAHN/graph.json","fetch_events":"https://pith.science/api/pith-number/WZJ5W3FH32Z57LCOXR423RPAHN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WZJ5W3FH32Z57LCOXR423RPAHN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WZJ5W3FH32Z57LCOXR423RPAHN/action/storage_attestation","attest_author":"https://pith.science/pith/WZJ5W3FH32Z57LCOXR423RPAHN/action/author_attestation","sign_citation":"https://pith.science/pith/WZJ5W3FH32Z57LCOXR423RPAHN/action/citation_signature","submit_replication":"https://pith.science/pith/WZJ5W3FH32Z57LCOXR423RPAHN/action/replication_record"}},"created_at":"2026-07-05T01:25:26.029929+00:00","updated_at":"2026-07-05T01:25:26.029929+00:00"}