{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:DHJIO57MQMXVN5W2XWENRN3PSL","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":"a26045361cf741d9eac3a7b066265b3b4f3dc918b223d1ccbf5b4523972dfd5b","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-08-04T03:11:32Z","title_canon_sha256":"b91c6200cac94838302fd42e27968e7f9d28f35e89ba8e0c6d20dbad16deb334"},"schema_version":"1.0","source":{"id":"2008.01300","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.01300","created_at":"2026-07-05T01:36:31Z"},{"alias_kind":"arxiv_version","alias_value":"2008.01300v2","created_at":"2026-07-05T01:36:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.01300","created_at":"2026-07-05T01:36:31Z"},{"alias_kind":"pith_short_12","alias_value":"DHJIO57MQMXV","created_at":"2026-07-05T01:36:31Z"},{"alias_kind":"pith_short_16","alias_value":"DHJIO57MQMXVN5W2","created_at":"2026-07-05T01:36:31Z"},{"alias_kind":"pith_short_8","alias_value":"DHJIO57M","created_at":"2026-07-05T01:36:31Z"}],"graph_snapshots":[{"event_id":"sha256:473f73896a1dea023548ded470591ef98e803e3cca43e2a99a63427ae07dbb39","target":"graph","created_at":"2026-07-05T01:36:31Z","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/2008.01300/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Building Automatic Speech Recognition (ASR) systems from scratch is significantly challenging, mostly due to the time-consuming and financially-expensive process of annotating a large amount of audio data with transcripts. Although several unsupervised pre-training models have been proposed, applying such models directly might still be sub-optimal if more labeled, training data could be obtained without a large cost. In this paper, we present a weakly supervised framework for constructing ASR systems with massive video data. As videos often contain human-speech audios aligned with subtitles, w","authors_text":"Chengyu Wang, Jun Huang, Mengli Cheng, Xiaobo Wang, Xu Hu","cross_cats":["cs.CL","cs.LG","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-08-04T03:11:32Z","title":"Weakly Supervised Construction of ASR Systems with Massive Video Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.01300","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":"sha256:2b65c69cf646fe972258a59bc417c2de7add651cc0f0d5ce63a02b6f0c0a76ab","target":"record","created_at":"2026-07-05T01:36:31Z","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":"a26045361cf741d9eac3a7b066265b3b4f3dc918b223d1ccbf5b4523972dfd5b","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-08-04T03:11:32Z","title_canon_sha256":"b91c6200cac94838302fd42e27968e7f9d28f35e89ba8e0c6d20dbad16deb334"},"schema_version":"1.0","source":{"id":"2008.01300","kind":"arxiv","version":2}},"canonical_sha256":"19d28777ec832f56f6dabd88d8b76f92fd0a914506a9e5032c9cce350b35625b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"19d28777ec832f56f6dabd88d8b76f92fd0a914506a9e5032c9cce350b35625b","first_computed_at":"2026-07-05T01:36:31.533195Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:36:31.533195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2AqMwW6YsmM2VLcwoE5cd3JLHtPN/p4y1Qu/68TaEZ91pTy5hpS4lBlTnBwPYuc0Se1R1kPqRx5i9Cxob9j0Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:36:31.533635Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.01300","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b65c69cf646fe972258a59bc417c2de7add651cc0f0d5ce63a02b6f0c0a76ab","sha256:473f73896a1dea023548ded470591ef98e803e3cca43e2a99a63427ae07dbb39"],"state_sha256":"179df0e2e4007dcaead976fb6f7cc6b1da223164b073d8a688df50735a517246"}