{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:DHJIO57MQMXVN5W2XWENRN3PSL","short_pith_number":"pith:DHJIO57M","canonical_record":{"source":{"id":"2008.01300","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-08-04T03:11:32Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"b91c6200cac94838302fd42e27968e7f9d28f35e89ba8e0c6d20dbad16deb334","abstract_canon_sha256":"a26045361cf741d9eac3a7b066265b3b4f3dc918b223d1ccbf5b4523972dfd5b"},"schema_version":"1.0"},"canonical_sha256":"19d28777ec832f56f6dabd88d8b76f92fd0a914506a9e5032c9cce350b35625b","source":{"kind":"arxiv","id":"2008.01300","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:DHJIO57MQMXVN5W2XWENRN3PSL","target":"record","payload":{"canonical_record":{"source":{"id":"2008.01300","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-08-04T03:11:32Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"b91c6200cac94838302fd42e27968e7f9d28f35e89ba8e0c6d20dbad16deb334","abstract_canon_sha256":"a26045361cf741d9eac3a7b066265b3b4f3dc918b223d1ccbf5b4523972dfd5b"},"schema_version":"1.0"},"canonical_sha256":"19d28777ec832f56f6dabd88d8b76f92fd0a914506a9e5032c9cce350b35625b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:36:31.533635Z","signature_b64":"2AqMwW6YsmM2VLcwoE5cd3JLHtPN/p4y1Qu/68TaEZ91pTy5hpS4lBlTnBwPYuc0Se1R1kPqRx5i9Cxob9j0Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19d28777ec832f56f6dabd88d8b76f92fd0a914506a9e5032c9cce350b35625b","last_reissued_at":"2026-07-05T01:36:31.533195Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:36:31.533195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2008.01300","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:36:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W6Bt6yBEiWGMQC8o1G93Kx4GqVQeVlU/Q9OSUy4DrDGQT40zzcrBd0HlXZ9qQkbyLKw7I89YW+ZMNC5dmeiOCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T07:26:33.921576Z"},"content_sha256":"2b65c69cf646fe972258a59bc417c2de7add651cc0f0d5ce63a02b6f0c0a76ab","schema_version":"1.0","event_id":"sha256:2b65c69cf646fe972258a59bc417c2de7add651cc0f0d5ce63a02b6f0c0a76ab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:DHJIO57MQMXVN5W2XWENRN3PSL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Weakly Supervised Construction of ASR Systems with Massive Video Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chengyu Wang, Jun Huang, Mengli Cheng, Xiaobo Wang, Xu Hu","submitted_at":"2020-08-04T03:11:32Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.01300","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/2008.01300/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":"2026-07-05T01:36:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5Jzc+IDc9SabdqQMbpIQffpxsY+MY+6XvYG3ilUE2W9PL0ZIy9h8l2k4i5eIB1hD32ijtlwmBMZYTiJOPVlAAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T07:26:33.922489Z"},"content_sha256":"473f73896a1dea023548ded470591ef98e803e3cca43e2a99a63427ae07dbb39","schema_version":"1.0","event_id":"sha256:473f73896a1dea023548ded470591ef98e803e3cca43e2a99a63427ae07dbb39"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DHJIO57MQMXVN5W2XWENRN3PSL/bundle.json","state_url":"https://pith.science/pith/DHJIO57MQMXVN5W2XWENRN3PSL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DHJIO57MQMXVN5W2XWENRN3PSL/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":"2026-08-15T07:26:33Z","links":{"resolver":"https://pith.science/pith/DHJIO57MQMXVN5W2XWENRN3PSL","bundle":"https://pith.science/pith/DHJIO57MQMXVN5W2XWENRN3PSL/bundle.json","state":"https://pith.science/pith/DHJIO57MQMXVN5W2XWENRN3PSL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DHJIO57MQMXVN5W2XWENRN3PSL/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6x0ap1Lp0ewPhdaAaF4tFETTwdn9wEykyr/KM99Mf2P8L1dznX+fv1T1grgmY0hZliz6Kkimrc75Hjn9pprSAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T07:26:33.929173Z","bundle_sha256":"35fbe1b96170809b1db090bfe9497b8165d1768747ad7a94656167d6278e490c"}}