{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KB6MU7LDQS263PBRJ2ZINNULHP","short_pith_number":"pith:KB6MU7LD","canonical_record":{"source":{"id":"2407.17852","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-25T08:08:55Z","cross_cats_sorted":[],"title_canon_sha256":"fcea9f05a9c3e497779c52a642ee6ab3b07df0b85ce6ec2eee2a6e1341559e77","abstract_canon_sha256":"fd8e482ab74f70871a408f5d31d955780c6cdd3f808dd08f22955484af53759f"},"schema_version":"1.0"},"canonical_sha256":"507cca7d6384b5edbc314eb286b68b3bfefe006961516bf7caa197339f882f23","source":{"kind":"arxiv","id":"2407.17852","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.17852","created_at":"2026-07-05T08:48:22Z"},{"alias_kind":"arxiv_version","alias_value":"2407.17852v1","created_at":"2026-07-05T08:48:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.17852","created_at":"2026-07-05T08:48:22Z"},{"alias_kind":"pith_short_12","alias_value":"KB6MU7LDQS26","created_at":"2026-07-05T08:48:22Z"},{"alias_kind":"pith_short_16","alias_value":"KB6MU7LDQS263PBR","created_at":"2026-07-05T08:48:22Z"},{"alias_kind":"pith_short_8","alias_value":"KB6MU7LD","created_at":"2026-07-05T08:48:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KB6MU7LDQS263PBRJ2ZINNULHP","target":"record","payload":{"canonical_record":{"source":{"id":"2407.17852","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-25T08:08:55Z","cross_cats_sorted":[],"title_canon_sha256":"fcea9f05a9c3e497779c52a642ee6ab3b07df0b85ce6ec2eee2a6e1341559e77","abstract_canon_sha256":"fd8e482ab74f70871a408f5d31d955780c6cdd3f808dd08f22955484af53759f"},"schema_version":"1.0"},"canonical_sha256":"507cca7d6384b5edbc314eb286b68b3bfefe006961516bf7caa197339f882f23","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:22.562327Z","signature_b64":"oEB/Cnjb92tBYViOexC3kI4Vo36qLfB0l06RgfxWrn2KFFnWdxuojsVU/bfKf1oMzDbOm3/qiWwSaFSQfXo1CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"507cca7d6384b5edbc314eb286b68b3bfefe006961516bf7caa197339f882f23","last_reissued_at":"2026-07-05T08:48:22.561905Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:22.561905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.17852","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:48:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uEnxCBjKeG5qkfQffzPk5Pdg5QMN9ROmMFLJB1ouMclGm8ueaz2nKP1EUL6ssfvwuW00dTEfynLOaz9qDa6aDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:34:25.071715Z"},"content_sha256":"4b24eb01c38a8b225fdd1943e59c0b89cd393105da2b10ba2f7980d4843ded20","schema_version":"1.0","event_id":"sha256:4b24eb01c38a8b225fdd1943e59c0b89cd393105da2b10ba2f7980d4843ded20"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KB6MU7LDQS263PBRJ2ZINNULHP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scaling A Simple Approach to Zero-Shot Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jinming Zhao, Michael Auli, Vineel Pratap","submitted_at":"2024-07-25T08:08:55Z","abstract_excerpt":"Despite rapid progress in increasing the language coverage of automatic speech recognition, the field is still far from covering all languages with a known writing script. Recent work showed promising results with a zero-shot approach requiring only a small amount of text data, however, accuracy heavily depends on the quality of the used phonemizer which is often weak for unseen languages. In this paper, we present MMS Zero-shot a conceptually simpler approach based on romanization and an acoustic model trained on data in 1,078 different languages or three orders of magnitude more than prior a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.17852","kind":"arxiv","version":1},"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/2407.17852/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":"2026-07-05T08:48:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oqyok/JxAbOHHOcswspdMmTylqcuIFO/sEoq17FdSQFjb7HEiD2Tm2JFIO8pMGgCMzdBPYbzMsgAshbhlkSnAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:34:25.072219Z"},"content_sha256":"83504354a0ae89b8c5ac1085aa30d65d1ed72cc9e148983a03dbb07a65bd6206","schema_version":"1.0","event_id":"sha256:83504354a0ae89b8c5ac1085aa30d65d1ed72cc9e148983a03dbb07a65bd6206"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KB6MU7LDQS263PBRJ2ZINNULHP/bundle.json","state_url":"https://pith.science/pith/KB6MU7LDQS263PBRJ2ZINNULHP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KB6MU7LDQS263PBRJ2ZINNULHP/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":"2026-08-08T17:34:25Z","links":{"resolver":"https://pith.science/pith/KB6MU7LDQS263PBRJ2ZINNULHP","bundle":"https://pith.science/pith/KB6MU7LDQS263PBRJ2ZINNULHP/bundle.json","state":"https://pith.science/pith/KB6MU7LDQS263PBRJ2ZINNULHP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KB6MU7LDQS263PBRJ2ZINNULHP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KB6MU7LDQS263PBRJ2ZINNULHP","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":"fd8e482ab74f70871a408f5d31d955780c6cdd3f808dd08f22955484af53759f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-25T08:08:55Z","title_canon_sha256":"fcea9f05a9c3e497779c52a642ee6ab3b07df0b85ce6ec2eee2a6e1341559e77"},"schema_version":"1.0","source":{"id":"2407.17852","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.17852","created_at":"2026-07-05T08:48:22Z"},{"alias_kind":"arxiv_version","alias_value":"2407.17852v1","created_at":"2026-07-05T08:48:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.17852","created_at":"2026-07-05T08:48:22Z"},{"alias_kind":"pith_short_12","alias_value":"KB6MU7LDQS26","created_at":"2026-07-05T08:48:22Z"},{"alias_kind":"pith_short_16","alias_value":"KB6MU7LDQS263PBR","created_at":"2026-07-05T08:48:22Z"},{"alias_kind":"pith_short_8","alias_value":"KB6MU7LD","created_at":"2026-07-05T08:48:22Z"}],"graph_snapshots":[{"event_id":"sha256:83504354a0ae89b8c5ac1085aa30d65d1ed72cc9e148983a03dbb07a65bd6206","target":"graph","created_at":"2026-07-05T08:48:22Z","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/2407.17852/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite rapid progress in increasing the language coverage of automatic speech recognition, the field is still far from covering all languages with a known writing script. Recent work showed promising results with a zero-shot approach requiring only a small amount of text data, however, accuracy heavily depends on the quality of the used phonemizer which is often weak for unseen languages. In this paper, we present MMS Zero-shot a conceptually simpler approach based on romanization and an acoustic model trained on data in 1,078 different languages or three orders of magnitude more than prior a","authors_text":"Jinming Zhao, Michael Auli, Vineel Pratap","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-25T08:08:55Z","title":"Scaling A Simple Approach to Zero-Shot Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.17852","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":"sha256:4b24eb01c38a8b225fdd1943e59c0b89cd393105da2b10ba2f7980d4843ded20","target":"record","created_at":"2026-07-05T08:48:22Z","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":"fd8e482ab74f70871a408f5d31d955780c6cdd3f808dd08f22955484af53759f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-25T08:08:55Z","title_canon_sha256":"fcea9f05a9c3e497779c52a642ee6ab3b07df0b85ce6ec2eee2a6e1341559e77"},"schema_version":"1.0","source":{"id":"2407.17852","kind":"arxiv","version":1}},"canonical_sha256":"507cca7d6384b5edbc314eb286b68b3bfefe006961516bf7caa197339f882f23","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"507cca7d6384b5edbc314eb286b68b3bfefe006961516bf7caa197339f882f23","first_computed_at":"2026-07-05T08:48:22.561905Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:48:22.561905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oEB/Cnjb92tBYViOexC3kI4Vo36qLfB0l06RgfxWrn2KFFnWdxuojsVU/bfKf1oMzDbOm3/qiWwSaFSQfXo1CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:48:22.562327Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.17852","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b24eb01c38a8b225fdd1943e59c0b89cd393105da2b10ba2f7980d4843ded20","sha256:83504354a0ae89b8c5ac1085aa30d65d1ed72cc9e148983a03dbb07a65bd6206"],"state_sha256":"06ecb075d98aee58b48d84c6437aaab1d4f9439a88e5b02144f9c5a05b577aef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"84/2SPLE/yNVFfuoIR2mUdqM86q7+0maP7LhWPemEYoWbRl77bgQDY9vopLgxinqOE3hyhZnrJkHTXdoqzd0DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T17:34:25.076619Z","bundle_sha256":"c483ef00f4f848337c6ddcf11175b0f804ecc81f3296ec977b24c88d91d5af9b"}}