{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:WWGNPPK4Q6ATRU4LBITUHCEICM","short_pith_number":"pith:WWGNPPK4","canonical_record":{"source":{"id":"2306.06410","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-10T11:04:10Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"924730e97ddb39832f5b72db18d9543bb13c8b0347f62c42ca1d331d8e7e0969","abstract_canon_sha256":"f04941543b88d2dbd339cbb6ea5f74896f346c3886e45dd852dbb3465fc9e739"},"schema_version":"1.0"},"canonical_sha256":"b58cd7bd5c878138d38b0a2743888813267c7c3ae9058277e9a8512e249d1e9a","source":{"kind":"arxiv","id":"2306.06410","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.06410","created_at":"2026-07-05T06:19:24Z"},{"alias_kind":"arxiv_version","alias_value":"2306.06410v1","created_at":"2026-07-05T06:19:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.06410","created_at":"2026-07-05T06:19:24Z"},{"alias_kind":"pith_short_12","alias_value":"WWGNPPK4Q6AT","created_at":"2026-07-05T06:19:24Z"},{"alias_kind":"pith_short_16","alias_value":"WWGNPPK4Q6ATRU4L","created_at":"2026-07-05T06:19:24Z"},{"alias_kind":"pith_short_8","alias_value":"WWGNPPK4","created_at":"2026-07-05T06:19:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:WWGNPPK4Q6ATRU4LBITUHCEICM","target":"record","payload":{"canonical_record":{"source":{"id":"2306.06410","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-10T11:04:10Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"924730e97ddb39832f5b72db18d9543bb13c8b0347f62c42ca1d331d8e7e0969","abstract_canon_sha256":"f04941543b88d2dbd339cbb6ea5f74896f346c3886e45dd852dbb3465fc9e739"},"schema_version":"1.0"},"canonical_sha256":"b58cd7bd5c878138d38b0a2743888813267c7c3ae9058277e9a8512e249d1e9a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:24.538837Z","signature_b64":"qlYxx3bGRexwxb0eWQi+xhZu3TzU+/UXM7SynN06J0bLH5S+sZBlyoGk3XOgpfLBedUI5XSXYwrE4guXZ8SKCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b58cd7bd5c878138d38b0a2743888813267c7c3ae9058277e9a8512e249d1e9a","last_reissued_at":"2026-07-05T06:19:24.538418Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:24.538418Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.06410","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":"2026-07-05T06:19:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vak1pI8DHPY5IwbiIouZiERrqRy4iNmNdmbcO7W/feoXyvFVTaWmHQnutCr/DIOylXVfC2QdBQ4ScfG9t+UwAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T19:28:26.411053Z"},"content_sha256":"135338b0cda1b8da1bb0cc23d3f23adddb4ff0b0698816653cd8dda87eb3a118","schema_version":"1.0","event_id":"sha256:135338b0cda1b8da1bb0cc23d3f23adddb4ff0b0698816653cd8dda87eb3a118"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:WWGNPPK4Q6ATRU4LBITUHCEICM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"OpenSR: Open-Modality Speech Recognition via Maintaining Multi-Modality Alignment","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Linjun Li, Tao Jin, Wang Lin, Xinyu Duan, Xize Cheng, Zhou Zhao","submitted_at":"2023-06-10T11:04:10Z","abstract_excerpt":"Speech Recognition builds a bridge between the multimedia streaming (audio-only, visual-only or audio-visual) and the corresponding text transcription. However, when training the specific model of new domain, it often gets stuck in the lack of new-domain utterances, especially the labeled visual utterances. To break through this restriction, we attempt to achieve zero-shot modality transfer by maintaining the multi-modality alignment in phoneme space learned with unlabeled multimedia utterances in the high resource domain during the pre-training \\cite{shi2022learning}, and propose a training s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.06410","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/2306.06410/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":"2026-07-05T06:19:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EiHitTYvrbD/GDCXji7e9E1qHm/KkpEjEWokInIAreTu29KvIoN3gyYXhugfDMzxw+XQkbdT/aE/I6fR5FA3AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T19:28:26.411551Z"},"content_sha256":"42e3825c22abcaf834ab50d6245510a69fabdbebb43de4087d69fef0c7c970f8","schema_version":"1.0","event_id":"sha256:42e3825c22abcaf834ab50d6245510a69fabdbebb43de4087d69fef0c7c970f8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WWGNPPK4Q6ATRU4LBITUHCEICM/bundle.json","state_url":"https://pith.science/pith/WWGNPPK4Q6ATRU4LBITUHCEICM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WWGNPPK4Q6ATRU4LBITUHCEICM/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":"2026-08-09T19:28:26Z","links":{"resolver":"https://pith.science/pith/WWGNPPK4Q6ATRU4LBITUHCEICM","bundle":"https://pith.science/pith/WWGNPPK4Q6ATRU4LBITUHCEICM/bundle.json","state":"https://pith.science/pith/WWGNPPK4Q6ATRU4LBITUHCEICM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WWGNPPK4Q6ATRU4LBITUHCEICM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WWGNPPK4Q6ATRU4LBITUHCEICM","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":"f04941543b88d2dbd339cbb6ea5f74896f346c3886e45dd852dbb3465fc9e739","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-10T11:04:10Z","title_canon_sha256":"924730e97ddb39832f5b72db18d9543bb13c8b0347f62c42ca1d331d8e7e0969"},"schema_version":"1.0","source":{"id":"2306.06410","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.06410","created_at":"2026-07-05T06:19:24Z"},{"alias_kind":"arxiv_version","alias_value":"2306.06410v1","created_at":"2026-07-05T06:19:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.06410","created_at":"2026-07-05T06:19:24Z"},{"alias_kind":"pith_short_12","alias_value":"WWGNPPK4Q6AT","created_at":"2026-07-05T06:19:24Z"},{"alias_kind":"pith_short_16","alias_value":"WWGNPPK4Q6ATRU4L","created_at":"2026-07-05T06:19:24Z"},{"alias_kind":"pith_short_8","alias_value":"WWGNPPK4","created_at":"2026-07-05T06:19:24Z"}],"graph_snapshots":[{"event_id":"sha256:42e3825c22abcaf834ab50d6245510a69fabdbebb43de4087d69fef0c7c970f8","target":"graph","created_at":"2026-07-05T06:19:24Z","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/2306.06410/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech Recognition builds a bridge between the multimedia streaming (audio-only, visual-only or audio-visual) and the corresponding text transcription. However, when training the specific model of new domain, it often gets stuck in the lack of new-domain utterances, especially the labeled visual utterances. To break through this restriction, we attempt to achieve zero-shot modality transfer by maintaining the multi-modality alignment in phoneme space learned with unlabeled multimedia utterances in the high resource domain during the pre-training \\cite{shi2022learning}, and propose a training s","authors_text":"Linjun Li, Tao Jin, Wang Lin, Xinyu Duan, Xize Cheng, Zhou Zhao","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-10T11:04:10Z","title":"OpenSR: Open-Modality Speech Recognition via Maintaining Multi-Modality Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.06410","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":"sha256:135338b0cda1b8da1bb0cc23d3f23adddb4ff0b0698816653cd8dda87eb3a118","target":"record","created_at":"2026-07-05T06:19:24Z","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":"f04941543b88d2dbd339cbb6ea5f74896f346c3886e45dd852dbb3465fc9e739","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-10T11:04:10Z","title_canon_sha256":"924730e97ddb39832f5b72db18d9543bb13c8b0347f62c42ca1d331d8e7e0969"},"schema_version":"1.0","source":{"id":"2306.06410","kind":"arxiv","version":1}},"canonical_sha256":"b58cd7bd5c878138d38b0a2743888813267c7c3ae9058277e9a8512e249d1e9a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b58cd7bd5c878138d38b0a2743888813267c7c3ae9058277e9a8512e249d1e9a","first_computed_at":"2026-07-05T06:19:24.538418Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:19:24.538418Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qlYxx3bGRexwxb0eWQi+xhZu3TzU+/UXM7SynN06J0bLH5S+sZBlyoGk3XOgpfLBedUI5XSXYwrE4guXZ8SKCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:19:24.538837Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.06410","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:135338b0cda1b8da1bb0cc23d3f23adddb4ff0b0698816653cd8dda87eb3a118","sha256:42e3825c22abcaf834ab50d6245510a69fabdbebb43de4087d69fef0c7c970f8"],"state_sha256":"46eb9c3c45de4f3ed40b4cda0207e8959f1b489f67942cac1e81240cccf42d4f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cSfy5qGm/19XLd3vvGu1tSDH5dKNoTpTynhVKkjGPyPNDD9wFBD631fevHNujf5jcE9kf/b5UCxkCc+7SI98AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T19:28:26.415901Z","bundle_sha256":"95ef4599dc82411b448a5bf9d9820aa230d5dd1e4bbfd0000fe5d9c2ac18a650"}}