{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:7H4YKBVB7UHRPVCN32EOWD376X","short_pith_number":"pith:7H4YKBVB","canonical_record":{"source":{"id":"2110.03047","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-06T20:07:53Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"c99190042a8d66eb3d397b36a2ba2ef8ebb84f990003c11b9fa960e3b7908d08","abstract_canon_sha256":"5c64165e49b05b0dd5eee9326a807c8b4e6e931bfeadcd0239ff21c44c22607a"},"schema_version":"1.0"},"canonical_sha256":"f9f98506a1fd0f17d44dde88eb0f7ff5c1d8ecddbfa063182740052ad04aa020","source":{"kind":"arxiv","id":"2110.03047","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.03047","created_at":"2026-07-05T03:20:39Z"},{"alias_kind":"arxiv_version","alias_value":"2110.03047v1","created_at":"2026-07-05T03:20:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.03047","created_at":"2026-07-05T03:20:39Z"},{"alias_kind":"pith_short_12","alias_value":"7H4YKBVB7UHR","created_at":"2026-07-05T03:20:39Z"},{"alias_kind":"pith_short_16","alias_value":"7H4YKBVB7UHRPVCN","created_at":"2026-07-05T03:20:39Z"},{"alias_kind":"pith_short_8","alias_value":"7H4YKBVB","created_at":"2026-07-05T03:20:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:7H4YKBVB7UHRPVCN32EOWD376X","target":"record","payload":{"canonical_record":{"source":{"id":"2110.03047","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-06T20:07:53Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"c99190042a8d66eb3d397b36a2ba2ef8ebb84f990003c11b9fa960e3b7908d08","abstract_canon_sha256":"5c64165e49b05b0dd5eee9326a807c8b4e6e931bfeadcd0239ff21c44c22607a"},"schema_version":"1.0"},"canonical_sha256":"f9f98506a1fd0f17d44dde88eb0f7ff5c1d8ecddbfa063182740052ad04aa020","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:20:39.046381Z","signature_b64":"qUfRPu2EfmUjKXzwdnllXvrLBZiDp697OFZo+B9EK/WRfaIIeMr5Oy/uGBBEVZ5yEhFqHqbbkRA20uzr2TzsDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9f98506a1fd0f17d44dde88eb0f7ff5c1d8ecddbfa063182740052ad04aa020","last_reissued_at":"2026-07-05T03:20:39.045990Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:20:39.045990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.03047","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":"2026-07-05T03:20:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4wXFI8u1DcFWRhAXdWi9JxkPsdbqtBB5R3dd4Q4ScBZqYCT5OCmEdpPZpfSxSSkBHU6QaL0dQirLtSLNDsUZDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T02:01:21.488580Z"},"content_sha256":"b6034f465905e226b31fee912bf5eacee6e56d04ee7ddac0f0cdbef73d326694","schema_version":"1.0","event_id":"sha256:b6034f465905e226b31fee912bf5eacee6e56d04ee7ddac0f0cdbef73d326694"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:7H4YKBVB7UHRPVCN32EOWD376X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Integrating Categorical Features in End-to-End ASR","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Rongqing Huang","submitted_at":"2021-10-06T20:07:53Z","abstract_excerpt":"All-neural, end-to-end ASR systems gained rapid interest from the speech recognition community. Such systems convert speech input to text units using a single trainable neural network model. E2E models require large amounts of paired speech text data that is expensive to obtain. The amount of data available varies across different languages and dialects. It is critical to make use of all these data so that both low resource languages and high resource languages can be improved. When we want to deploy an ASR system for a new application domain, the amount of domain specific training data is ver"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.03047","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/2110.03047/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":"2026-07-05T03:20:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FrSGhRhl+q3UljQj2F3vk6U5rhXyljvw5L4pqz67uXh/twYr8w4cSfbRiNxAXdTr5JXO85W+GUZOpw93KOTxBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T02:01:21.488955Z"},"content_sha256":"d08bab675726f4bb00f4b8322292f23b57803dffbda475857392d4d1aa9bf19c","schema_version":"1.0","event_id":"sha256:d08bab675726f4bb00f4b8322292f23b57803dffbda475857392d4d1aa9bf19c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7H4YKBVB7UHRPVCN32EOWD376X/bundle.json","state_url":"https://pith.science/pith/7H4YKBVB7UHRPVCN32EOWD376X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7H4YKBVB7UHRPVCN32EOWD376X/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":"2026-07-09T02:01:21Z","links":{"resolver":"https://pith.science/pith/7H4YKBVB7UHRPVCN32EOWD376X","bundle":"https://pith.science/pith/7H4YKBVB7UHRPVCN32EOWD376X/bundle.json","state":"https://pith.science/pith/7H4YKBVB7UHRPVCN32EOWD376X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7H4YKBVB7UHRPVCN32EOWD376X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:7H4YKBVB7UHRPVCN32EOWD376X","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":"5c64165e49b05b0dd5eee9326a807c8b4e6e931bfeadcd0239ff21c44c22607a","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-06T20:07:53Z","title_canon_sha256":"c99190042a8d66eb3d397b36a2ba2ef8ebb84f990003c11b9fa960e3b7908d08"},"schema_version":"1.0","source":{"id":"2110.03047","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.03047","created_at":"2026-07-05T03:20:39Z"},{"alias_kind":"arxiv_version","alias_value":"2110.03047v1","created_at":"2026-07-05T03:20:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.03047","created_at":"2026-07-05T03:20:39Z"},{"alias_kind":"pith_short_12","alias_value":"7H4YKBVB7UHR","created_at":"2026-07-05T03:20:39Z"},{"alias_kind":"pith_short_16","alias_value":"7H4YKBVB7UHRPVCN","created_at":"2026-07-05T03:20:39Z"},{"alias_kind":"pith_short_8","alias_value":"7H4YKBVB","created_at":"2026-07-05T03:20:39Z"}],"graph_snapshots":[{"event_id":"sha256:d08bab675726f4bb00f4b8322292f23b57803dffbda475857392d4d1aa9bf19c","target":"graph","created_at":"2026-07-05T03:20:39Z","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/2110.03047/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"All-neural, end-to-end ASR systems gained rapid interest from the speech recognition community. Such systems convert speech input to text units using a single trainable neural network model. E2E models require large amounts of paired speech text data that is expensive to obtain. The amount of data available varies across different languages and dialects. It is critical to make use of all these data so that both low resource languages and high resource languages can be improved. When we want to deploy an ASR system for a new application domain, the amount of domain specific training data is ver","authors_text":"Rongqing Huang","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-06T20:07:53Z","title":"Integrating Categorical Features in End-to-End ASR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.03047","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:b6034f465905e226b31fee912bf5eacee6e56d04ee7ddac0f0cdbef73d326694","target":"record","created_at":"2026-07-05T03:20:39Z","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":"5c64165e49b05b0dd5eee9326a807c8b4e6e931bfeadcd0239ff21c44c22607a","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-06T20:07:53Z","title_canon_sha256":"c99190042a8d66eb3d397b36a2ba2ef8ebb84f990003c11b9fa960e3b7908d08"},"schema_version":"1.0","source":{"id":"2110.03047","kind":"arxiv","version":1}},"canonical_sha256":"f9f98506a1fd0f17d44dde88eb0f7ff5c1d8ecddbfa063182740052ad04aa020","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f9f98506a1fd0f17d44dde88eb0f7ff5c1d8ecddbfa063182740052ad04aa020","first_computed_at":"2026-07-05T03:20:39.045990Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:20:39.045990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qUfRPu2EfmUjKXzwdnllXvrLBZiDp697OFZo+B9EK/WRfaIIeMr5Oy/uGBBEVZ5yEhFqHqbbkRA20uzr2TzsDg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:20:39.046381Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.03047","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6034f465905e226b31fee912bf5eacee6e56d04ee7ddac0f0cdbef73d326694","sha256:d08bab675726f4bb00f4b8322292f23b57803dffbda475857392d4d1aa9bf19c"],"state_sha256":"5fbb1d1edc26d00b5714bd26e6a82256b6927e35824cc3183ab1031168718290"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8RIn6yjlI/QQ6K3G+h98tqG7ZyqwFdyDenK9Xe9PqjwE6sjBZ60SqgYjDIuYTYar5SI+taawXQHuqafQA66BDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T02:01:21.491027Z","bundle_sha256":"75fc21e4aec7ea67654cbfe3e5b334b00c6d44ece30509db342a12e377cf381a"}}