{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KPBG7WMOFZCDE2ICAK7IYMONNH","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":"d7cf02a0cc8ecaeabc9b54690e16407dda7005d67d74cdb1e1102ead9436c878","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-07-06T17:58:28Z","title_canon_sha256":"e0bd8f97dfdbbfe131acb1efa31474fcde77f719c88e7e7ef2ef818d2d5fdcda"},"schema_version":"1.0","source":{"id":"2307.03183","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.03183","created_at":"2026-07-05T06:58:11Z"},{"alias_kind":"arxiv_version","alias_value":"2307.03183v1","created_at":"2026-07-05T06:58:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.03183","created_at":"2026-07-05T06:58:11Z"},{"alias_kind":"pith_short_12","alias_value":"KPBG7WMOFZCD","created_at":"2026-07-05T06:58:11Z"},{"alias_kind":"pith_short_16","alias_value":"KPBG7WMOFZCDE2IC","created_at":"2026-07-05T06:58:11Z"},{"alias_kind":"pith_short_8","alias_value":"KPBG7WMO","created_at":"2026-07-05T06:58:11Z"}],"graph_snapshots":[{"event_id":"sha256:3b1a8d74e7c35e90531ea7e1aeb4fdc0c74ed46ea6a6a3a87aff0a5d525b4a5c","target":"graph","created_at":"2026-07-05T06:58:11Z","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/2307.03183/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we focus on Whisper, a recent automatic speech recognition model trained with a massive 680k hour labeled speech corpus recorded in diverse conditions. We first show an interesting finding that while Whisper is very robust against real-world background sounds (e.g., music), its audio representation is actually not noise-invariant, but is instead highly correlated to non-speech sounds, indicating that Whisper recognizes speech conditioned on the noise type. With this finding, we build a unified audio tagging and speech recognition model Whisper-AT by freezing the backbone of Whis","authors_text":"James Glass, Leonid Karlinsky, Sameer Khurana, Yuan Gong","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-07-06T17:58:28Z","title":"Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong General Audio Event Taggers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.03183","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:cd075e11175a26afeac75381191635ea4dca7f4e270cb16ca241eb429f87d4d4","target":"record","created_at":"2026-07-05T06:58:11Z","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":"d7cf02a0cc8ecaeabc9b54690e16407dda7005d67d74cdb1e1102ead9436c878","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-07-06T17:58:28Z","title_canon_sha256":"e0bd8f97dfdbbfe131acb1efa31474fcde77f719c88e7e7ef2ef818d2d5fdcda"},"schema_version":"1.0","source":{"id":"2307.03183","kind":"arxiv","version":1}},"canonical_sha256":"53c26fd98e2e4432690202be8c31cd69fa733fcb18cf0d1b08fe5eed14d4f2a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53c26fd98e2e4432690202be8c31cd69fa733fcb18cf0d1b08fe5eed14d4f2a1","first_computed_at":"2026-07-05T06:58:11.619761Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:58:11.619761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p5YcsG6DuWQPtU5BYm+wp8A7XVwybXUy5EQsDi7bjFrKrrnqcdJyG5x4rWmPhm2LiXcFjqnkinGBHc0kubyTAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:58:11.620299Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.03183","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cd075e11175a26afeac75381191635ea4dca7f4e270cb16ca241eb429f87d4d4","sha256:3b1a8d74e7c35e90531ea7e1aeb4fdc0c74ed46ea6a6a3a87aff0a5d525b4a5c"],"state_sha256":"954729041babe4b803229d02854a71f7eb3ec6d63f9f788a74ff63f7cfb51e76"}