{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:5S2FYI6LQ5H4ZZHWXZYFSPKLYJ","short_pith_number":"pith:5S2FYI6L","canonical_record":{"source":{"id":"2108.01812","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-04T02:11:37Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"a64b898b0a285db516cd56186397becfe08375614c67b23518a6850a85f7a62b","abstract_canon_sha256":"9330b8753853eda5414c078e0aa9a2d4922671bd50c6ce23e5bb8a6296464987"},"schema_version":"1.0"},"canonical_sha256":"ecb45c23cb874fcce4f6be70593d4bc27c66db3d7555d8fc886d1d894608fef5","source":{"kind":"arxiv","id":"2108.01812","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.01812","created_at":"2026-07-05T03:03:10Z"},{"alias_kind":"arxiv_version","alias_value":"2108.01812v1","created_at":"2026-07-05T03:03:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.01812","created_at":"2026-07-05T03:03:10Z"},{"alias_kind":"pith_short_12","alias_value":"5S2FYI6LQ5H4","created_at":"2026-07-05T03:03:10Z"},{"alias_kind":"pith_short_16","alias_value":"5S2FYI6LQ5H4ZZHW","created_at":"2026-07-05T03:03:10Z"},{"alias_kind":"pith_short_8","alias_value":"5S2FYI6L","created_at":"2026-07-05T03:03:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:5S2FYI6LQ5H4ZZHWXZYFSPKLYJ","target":"record","payload":{"canonical_record":{"source":{"id":"2108.01812","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-04T02:11:37Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"a64b898b0a285db516cd56186397becfe08375614c67b23518a6850a85f7a62b","abstract_canon_sha256":"9330b8753853eda5414c078e0aa9a2d4922671bd50c6ce23e5bb8a6296464987"},"schema_version":"1.0"},"canonical_sha256":"ecb45c23cb874fcce4f6be70593d4bc27c66db3d7555d8fc886d1d894608fef5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:03:10.945248Z","signature_b64":"X5GS7rUu9C6/EQYPQ6fO8qOkhvb0/14nER4bQi2BB4lEZYb0p0fP8fKfgeb/u3dRJlrFWy9NFhYIYB4oJW4LDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ecb45c23cb874fcce4f6be70593d4bc27c66db3d7555d8fc886d1d894608fef5","last_reissued_at":"2026-07-05T03:03:10.944765Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:03:10.944765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2108.01812","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":"2026-07-05T03:03:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0psKlAoV1BZbHrmlgI9XXSAoWaKFAW9yL92tuNp5jAP6C1yaT6nluKFoGlHi1CV8EMjfreMUK7eKmMdQTp5vCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T16:24:43.459435Z"},"content_sha256":"70d5e214b94ed0e6e3ed5900e8c4940284b1f3a817eed0f1f4b212977ee0d230","schema_version":"1.0","event_id":"sha256:70d5e214b94ed0e6e3ed5900e8c4940284b1f3a817eed0f1f4b212977ee0d230"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:5S2FYI6LQ5H4ZZHWXZYFSPKLYJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Distinction between ASR Errors and Speech Disfluencies with Feature Space Interpolation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Alena Kazakova, Dongchan Shin, Jihwa Lee, Sangyoun Paik, Seongmin Park, Subong Choi","submitted_at":"2021-08-04T02:11:37Z","abstract_excerpt":"Fine-tuning pretrained language models (LMs) is a popular approach to automatic speech recognition (ASR) error detection during post-processing. While error detection systems often take advantage of statistical language archetypes captured by LMs, at times the pretrained knowledge can hinder error detection performance. For instance, presence of speech disfluencies might confuse the post-processing system into tagging disfluent but accurate transcriptions as ASR errors. Such confusion occurs because both error detection and disfluency detection tasks attempt to identify tokens at statistically"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.01812","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/2108.01812/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":"2026-07-05T03:03:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jLj+fICac6mq5QDIwonNTDE3qkhgCUABs6QwKob6hst0tVLDCESS5zDhTOdEQvbIOrxf9b7AJknKOpEE5HPxDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T16:24:43.459813Z"},"content_sha256":"62c2f870812c4f370cd1363197de5f0eb6272426591330b0a404ed9c6dc535f1","schema_version":"1.0","event_id":"sha256:62c2f870812c4f370cd1363197de5f0eb6272426591330b0a404ed9c6dc535f1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5S2FYI6LQ5H4ZZHWXZYFSPKLYJ/bundle.json","state_url":"https://pith.science/pith/5S2FYI6LQ5H4ZZHWXZYFSPKLYJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5S2FYI6LQ5H4ZZHWXZYFSPKLYJ/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":"2026-08-22T16:24:43Z","links":{"resolver":"https://pith.science/pith/5S2FYI6LQ5H4ZZHWXZYFSPKLYJ","bundle":"https://pith.science/pith/5S2FYI6LQ5H4ZZHWXZYFSPKLYJ/bundle.json","state":"https://pith.science/pith/5S2FYI6LQ5H4ZZHWXZYFSPKLYJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5S2FYI6LQ5H4ZZHWXZYFSPKLYJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:5S2FYI6LQ5H4ZZHWXZYFSPKLYJ","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":"9330b8753853eda5414c078e0aa9a2d4922671bd50c6ce23e5bb8a6296464987","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-04T02:11:37Z","title_canon_sha256":"a64b898b0a285db516cd56186397becfe08375614c67b23518a6850a85f7a62b"},"schema_version":"1.0","source":{"id":"2108.01812","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.01812","created_at":"2026-07-05T03:03:10Z"},{"alias_kind":"arxiv_version","alias_value":"2108.01812v1","created_at":"2026-07-05T03:03:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.01812","created_at":"2026-07-05T03:03:10Z"},{"alias_kind":"pith_short_12","alias_value":"5S2FYI6LQ5H4","created_at":"2026-07-05T03:03:10Z"},{"alias_kind":"pith_short_16","alias_value":"5S2FYI6LQ5H4ZZHW","created_at":"2026-07-05T03:03:10Z"},{"alias_kind":"pith_short_8","alias_value":"5S2FYI6L","created_at":"2026-07-05T03:03:10Z"}],"graph_snapshots":[{"event_id":"sha256:62c2f870812c4f370cd1363197de5f0eb6272426591330b0a404ed9c6dc535f1","target":"graph","created_at":"2026-07-05T03:03:10Z","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/2108.01812/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-tuning pretrained language models (LMs) is a popular approach to automatic speech recognition (ASR) error detection during post-processing. While error detection systems often take advantage of statistical language archetypes captured by LMs, at times the pretrained knowledge can hinder error detection performance. For instance, presence of speech disfluencies might confuse the post-processing system into tagging disfluent but accurate transcriptions as ASR errors. Such confusion occurs because both error detection and disfluency detection tasks attempt to identify tokens at statistically","authors_text":"Alena Kazakova, Dongchan Shin, Jihwa Lee, Sangyoun Paik, Seongmin Park, Subong Choi","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-04T02:11:37Z","title":"Improving Distinction between ASR Errors and Speech Disfluencies with Feature Space Interpolation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.01812","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":"sha256:70d5e214b94ed0e6e3ed5900e8c4940284b1f3a817eed0f1f4b212977ee0d230","target":"record","created_at":"2026-07-05T03:03:10Z","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":"9330b8753853eda5414c078e0aa9a2d4922671bd50c6ce23e5bb8a6296464987","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-04T02:11:37Z","title_canon_sha256":"a64b898b0a285db516cd56186397becfe08375614c67b23518a6850a85f7a62b"},"schema_version":"1.0","source":{"id":"2108.01812","kind":"arxiv","version":1}},"canonical_sha256":"ecb45c23cb874fcce4f6be70593d4bc27c66db3d7555d8fc886d1d894608fef5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ecb45c23cb874fcce4f6be70593d4bc27c66db3d7555d8fc886d1d894608fef5","first_computed_at":"2026-07-05T03:03:10.944765Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:03:10.944765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X5GS7rUu9C6/EQYPQ6fO8qOkhvb0/14nER4bQi2BB4lEZYb0p0fP8fKfgeb/u3dRJlrFWy9NFhYIYB4oJW4LDw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:03:10.945248Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.01812","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:70d5e214b94ed0e6e3ed5900e8c4940284b1f3a817eed0f1f4b212977ee0d230","sha256:62c2f870812c4f370cd1363197de5f0eb6272426591330b0a404ed9c6dc535f1"],"state_sha256":"f0474d5e1e38e6068bad2cc8551457796d01748c12e9d1f9ee323ad0e7acd3fb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SY/rV5ADxne+5vr8Hg+XJ3ZK5P0WGUNszETHl37+DLXsGbZfbPDFCvsBtDhkOym0fJqikwdTapDAluyyJFZcBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T16:24:43.462369Z","bundle_sha256":"06d332330dbf06bae8e5a2335c4547b431c1e11f327aff3143df3426f957542a"}}