{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:JDPMMZXP3CV2ABSDAELZCNM735","short_pith_number":"pith:JDPMMZXP","canonical_record":{"source":{"id":"2110.12138","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-10-23T04:45:22Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"21e36bc452e165aa97423831420b73a904143bf2e7e7d95afa76c5358b4cd878","abstract_canon_sha256":"eba7c9aaff2d2f68caee1ea28213db3683129f16ceabafff0ffca9c7697f6bbc"},"schema_version":"1.0"},"canonical_sha256":"48dec666efd8aba00643011791359fdf74dc3bb3bc59a8ccae8fbd3b08579ffb","source":{"kind":"arxiv","id":"2110.12138","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.12138","created_at":"2026-07-05T03:25:00Z"},{"alias_kind":"arxiv_version","alias_value":"2110.12138v1","created_at":"2026-07-05T03:25:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.12138","created_at":"2026-07-05T03:25:00Z"},{"alias_kind":"pith_short_12","alias_value":"JDPMMZXP3CV2","created_at":"2026-07-05T03:25:00Z"},{"alias_kind":"pith_short_16","alias_value":"JDPMMZXP3CV2ABSD","created_at":"2026-07-05T03:25:00Z"},{"alias_kind":"pith_short_8","alias_value":"JDPMMZXP","created_at":"2026-07-05T03:25:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:JDPMMZXP3CV2ABSDAELZCNM735","target":"record","payload":{"canonical_record":{"source":{"id":"2110.12138","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-10-23T04:45:22Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"21e36bc452e165aa97423831420b73a904143bf2e7e7d95afa76c5358b4cd878","abstract_canon_sha256":"eba7c9aaff2d2f68caee1ea28213db3683129f16ceabafff0ffca9c7697f6bbc"},"schema_version":"1.0"},"canonical_sha256":"48dec666efd8aba00643011791359fdf74dc3bb3bc59a8ccae8fbd3b08579ffb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:25:00.770007Z","signature_b64":"WC6ymsXeaYu5Gy/OsOROgHgghfFqTUjzLIW8l7GC8I6RhiNUj4RgWSJmAccjbWum6ODGD1QAX/CSJr0gj2UbCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48dec666efd8aba00643011791359fdf74dc3bb3bc59a8ccae8fbd3b08579ffb","last_reissued_at":"2026-07-05T03:25:00.769586Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:25:00.769586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.12138","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":"2026-07-05T03:25:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3X5i3EmCc1VqtfABL7CkT0VnutbXSUsx0NGEeqDzazvh62f+KDWgwSf6p8RsSqsa/5tSIv4445SjeFu6VSE/Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:29:19.445011Z"},"content_sha256":"10df1b1c7a3c63dd7615f6720fa2f60d01276a030b2f93fe619f5f3073c2e158","schema_version":"1.0","event_id":"sha256:10df1b1c7a3c63dd7615f6720fa2f60d01276a030b2f93fe619f5f3073c2e158"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:JDPMMZXP3CV2ABSDAELZCNM735","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimizing Alignment of Speech and Language Latent Spaces for End-to-End Speech Recognition and Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Michael Zeng, Shujie Liu, Shuo Ren, Wei Wang, Yanmin Qian, Yao Qian, Yu Shi","submitted_at":"2021-10-23T04:45:22Z","abstract_excerpt":"The advances in attention-based encoder-decoder (AED) networks have brought great progress to end-to-end (E2E) automatic speech recognition (ASR). One way to further improve the performance of AED-based E2E ASR is to introduce an extra text encoder for leveraging extensive text data and thus capture more context-aware linguistic information. However, this approach brings a mismatch problem between the speech encoder and the text encoder due to the different units used for modeling. In this paper, we propose an embedding aligner and modality switch training to better align the speech and text l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.12138","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/2110.12138/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":"2026-07-05T03:25:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FDbQbO52Fwh/6darCetM3n+gvYqVA1tqT+7fcTM5qbURyVelw66WxCeM0qmW4lunKRMTeLBQc/0OdgDHMoWxAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:29:19.445530Z"},"content_sha256":"10e38905f9776e640ff4695499b4745b3779150b68ef91b1135dd2346522fa2e","schema_version":"1.0","event_id":"sha256:10e38905f9776e640ff4695499b4745b3779150b68ef91b1135dd2346522fa2e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JDPMMZXP3CV2ABSDAELZCNM735/bundle.json","state_url":"https://pith.science/pith/JDPMMZXP3CV2ABSDAELZCNM735/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JDPMMZXP3CV2ABSDAELZCNM735/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":"2026-08-04T21:29:19Z","links":{"resolver":"https://pith.science/pith/JDPMMZXP3CV2ABSDAELZCNM735","bundle":"https://pith.science/pith/JDPMMZXP3CV2ABSDAELZCNM735/bundle.json","state":"https://pith.science/pith/JDPMMZXP3CV2ABSDAELZCNM735/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JDPMMZXP3CV2ABSDAELZCNM735/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:JDPMMZXP3CV2ABSDAELZCNM735","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":"eba7c9aaff2d2f68caee1ea28213db3683129f16ceabafff0ffca9c7697f6bbc","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-10-23T04:45:22Z","title_canon_sha256":"21e36bc452e165aa97423831420b73a904143bf2e7e7d95afa76c5358b4cd878"},"schema_version":"1.0","source":{"id":"2110.12138","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.12138","created_at":"2026-07-05T03:25:00Z"},{"alias_kind":"arxiv_version","alias_value":"2110.12138v1","created_at":"2026-07-05T03:25:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.12138","created_at":"2026-07-05T03:25:00Z"},{"alias_kind":"pith_short_12","alias_value":"JDPMMZXP3CV2","created_at":"2026-07-05T03:25:00Z"},{"alias_kind":"pith_short_16","alias_value":"JDPMMZXP3CV2ABSD","created_at":"2026-07-05T03:25:00Z"},{"alias_kind":"pith_short_8","alias_value":"JDPMMZXP","created_at":"2026-07-05T03:25:00Z"}],"graph_snapshots":[{"event_id":"sha256:10e38905f9776e640ff4695499b4745b3779150b68ef91b1135dd2346522fa2e","target":"graph","created_at":"2026-07-05T03:25:00Z","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/2110.12138/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The advances in attention-based encoder-decoder (AED) networks have brought great progress to end-to-end (E2E) automatic speech recognition (ASR). One way to further improve the performance of AED-based E2E ASR is to introduce an extra text encoder for leveraging extensive text data and thus capture more context-aware linguistic information. However, this approach brings a mismatch problem between the speech encoder and the text encoder due to the different units used for modeling. In this paper, we propose an embedding aligner and modality switch training to better align the speech and text l","authors_text":"Michael Zeng, Shujie Liu, Shuo Ren, Wei Wang, Yanmin Qian, Yao Qian, Yu Shi","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-10-23T04:45:22Z","title":"Optimizing Alignment of Speech and Language Latent Spaces for End-to-End Speech Recognition and Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.12138","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":"sha256:10df1b1c7a3c63dd7615f6720fa2f60d01276a030b2f93fe619f5f3073c2e158","target":"record","created_at":"2026-07-05T03:25:00Z","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":"eba7c9aaff2d2f68caee1ea28213db3683129f16ceabafff0ffca9c7697f6bbc","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-10-23T04:45:22Z","title_canon_sha256":"21e36bc452e165aa97423831420b73a904143bf2e7e7d95afa76c5358b4cd878"},"schema_version":"1.0","source":{"id":"2110.12138","kind":"arxiv","version":1}},"canonical_sha256":"48dec666efd8aba00643011791359fdf74dc3bb3bc59a8ccae8fbd3b08579ffb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"48dec666efd8aba00643011791359fdf74dc3bb3bc59a8ccae8fbd3b08579ffb","first_computed_at":"2026-07-05T03:25:00.769586Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:25:00.769586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WC6ymsXeaYu5Gy/OsOROgHgghfFqTUjzLIW8l7GC8I6RhiNUj4RgWSJmAccjbWum6ODGD1QAX/CSJr0gj2UbCw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:25:00.770007Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.12138","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:10df1b1c7a3c63dd7615f6720fa2f60d01276a030b2f93fe619f5f3073c2e158","sha256:10e38905f9776e640ff4695499b4745b3779150b68ef91b1135dd2346522fa2e"],"state_sha256":"70cfda24148aba6e7183707d1dcd7a05dfb21c485fb5013e7ba2d90d96b1dd93"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hJJ98C1BCiwJaXezMrsT6pg61N2YbVEGBj/6WDrG7dKraruE4llM/5/3uk9PukKSf+gSiqUi2OH6ZD+eW7AYBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T21:29:19.450791Z","bundle_sha256":"58dc0ae6d8958b30b30bceac37fd7b58ce3fab1860180aee3b1d0d0ac9095f9b"}}