{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:F4NTWXVSIFA5R32GSI3OULVWQN","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":"8c43a557a96f0bf5fe59bddcff33f915b04ea61ae0650f28db9c234713a99339","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-05-18T16:32:58Z","title_canon_sha256":"fa4bc11213f6a17666483dbb65f7dbcd739ab4bf1d751b0220576d0eeed74cdf"},"schema_version":"1.0","source":{"id":"2305.11095","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.11095","created_at":"2026-07-05T06:41:49Z"},{"alias_kind":"arxiv_version","alias_value":"2305.11095v3","created_at":"2026-07-05T06:41:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11095","created_at":"2026-07-05T06:41:49Z"},{"alias_kind":"pith_short_12","alias_value":"F4NTWXVSIFA5","created_at":"2026-07-05T06:41:49Z"},{"alias_kind":"pith_short_16","alias_value":"F4NTWXVSIFA5R32G","created_at":"2026-07-05T06:41:49Z"},{"alias_kind":"pith_short_8","alias_value":"F4NTWXVS","created_at":"2026-07-05T06:41:49Z"}],"graph_snapshots":[{"event_id":"sha256:aa9531b98fd173460384bd66523f86e182bc468122fc974ccc3ca836f8f9f5ba","target":"graph","created_at":"2026-07-05T06:41:49Z","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/2305.11095/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We investigate the emergent abilities of the recently proposed web-scale speech model Whisper, by adapting it to unseen tasks with prompt engineering. We selected three tasks: audio-visual speech recognition (AVSR), code-switched speech recognition (CS-ASR), and speech translation (ST) on unseen language pairs. We design task-specific prompts, by either leveraging another large-scale model, or simply manipulating the special tokens in the default prompts. Experiments show that compared to the default prompts, our proposed prompts improve performance by 10% to 45% on the three zero-shot tasks, ","authors_text":"Brian Yan, David Harwath, Puyuan Peng, Shinji Watanabe","cross_cats":["cs.AI","cs.CL","cs.LG","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-05-18T16:32:58Z","title":"Prompting the Hidden Talent of Web-Scale Speech Models for Zero-Shot Task Generalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11095","kind":"arxiv","version":3},"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:f6f13dd0f54210f1b507a3da2e788f85be3c037fbf18ffcb56637783f26855f4","target":"record","created_at":"2026-07-05T06:41:49Z","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":"8c43a557a96f0bf5fe59bddcff33f915b04ea61ae0650f28db9c234713a99339","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-05-18T16:32:58Z","title_canon_sha256":"fa4bc11213f6a17666483dbb65f7dbcd739ab4bf1d751b0220576d0eeed74cdf"},"schema_version":"1.0","source":{"id":"2305.11095","kind":"arxiv","version":3}},"canonical_sha256":"2f1b3b5eb24141d8ef469236ea2eb68341e63b4eeda211d34e5a680df5353121","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f1b3b5eb24141d8ef469236ea2eb68341e63b4eeda211d34e5a680df5353121","first_computed_at":"2026-07-05T06:41:49.410806Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:41:49.410806Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OdM/l3A2s8gFmo+UTNOaN/o8s/qEPrbPWYQWL/kcMSi8VQFNy3qHZd3bv85jLJGhryFsDwBgfR0+K237Jy3sDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:41:49.411292Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.11095","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6f13dd0f54210f1b507a3da2e788f85be3c037fbf18ffcb56637783f26855f4","sha256:aa9531b98fd173460384bd66523f86e182bc468122fc974ccc3ca836f8f9f5ba"],"state_sha256":"8295cc2e8fce6442d89d477957b4cd5b230cefdcb986d0ddf5f235b02537710d"}