{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:BENQYUOYDU4PY4OLOPODURZY5X","short_pith_number":"pith:BENQYUOY","canonical_record":{"source":{"id":"2307.05796","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-11T20:42:06Z","cross_cats_sorted":[],"title_canon_sha256":"2db36e3193d4bd508f0708007316e377cd2aa7a7daeac5787f74a3f0667d5f89","abstract_canon_sha256":"41fd3234dc0edb9c06c3e606e52fe5db9d3237d39477b337718bf5812d6281f7"},"schema_version":"1.0"},"canonical_sha256":"091b0c51d81d38fc71cb73dc3a4738ede91c829b544983f5340713afac84786c","source":{"kind":"arxiv","id":"2307.05796","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.05796","created_at":"2026-07-05T06:30:12Z"},{"alias_kind":"arxiv_version","alias_value":"2307.05796v1","created_at":"2026-07-05T06:30:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.05796","created_at":"2026-07-05T06:30:12Z"},{"alias_kind":"pith_short_12","alias_value":"BENQYUOYDU4P","created_at":"2026-07-05T06:30:12Z"},{"alias_kind":"pith_short_16","alias_value":"BENQYUOYDU4PY4OL","created_at":"2026-07-05T06:30:12Z"},{"alias_kind":"pith_short_8","alias_value":"BENQYUOY","created_at":"2026-07-05T06:30:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:BENQYUOYDU4PY4OLOPODURZY5X","target":"record","payload":{"canonical_record":{"source":{"id":"2307.05796","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-11T20:42:06Z","cross_cats_sorted":[],"title_canon_sha256":"2db36e3193d4bd508f0708007316e377cd2aa7a7daeac5787f74a3f0667d5f89","abstract_canon_sha256":"41fd3234dc0edb9c06c3e606e52fe5db9d3237d39477b337718bf5812d6281f7"},"schema_version":"1.0"},"canonical_sha256":"091b0c51d81d38fc71cb73dc3a4738ede91c829b544983f5340713afac84786c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:30:12.662286Z","signature_b64":"bxRGYWRj1dcbHXkkQFzGt+VKwRNg+5JZgh36jgiiinnGD5NFHUUuJtYvt2x6pAlb4DDmJbcWNEwpzA3wW8rNDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"091b0c51d81d38fc71cb73dc3a4738ede91c829b544983f5340713afac84786c","last_reissued_at":"2026-07-05T06:30:12.661828Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:30:12.661828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.05796","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":"2026-07-05T06:30:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DMocJV6FTefW0B47UCFvPN2p8O0w0CZK+v6c/0O2hsGLkHgOkSPzsO2Esvygce7VmqYiPPglp1jkwSV5BGX7Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T07:07:34.275570Z"},"content_sha256":"a9a576a7ca6eecca95585a9e33193a9d649b2350e8ab013abe8493671614c614","schema_version":"1.0","event_id":"sha256:a9a576a7ca6eecca95585a9e33193a9d649b2350e8ab013abe8493671614c614"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:BENQYUOYDU4PY4OLOPODURZY5X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improved POS tagging for spontaneous, clinical speech using data augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David J. Irwin, Naomi Nevler, Neville Ryant, Seth Kulick, Sunghye Cho","submitted_at":"2023-07-11T20:42:06Z","abstract_excerpt":"This paper addresses the problem of improving POS tagging of transcripts of speech from clinical populations. In contrast to prior work on parsing and POS tagging of transcribed speech, we do not make use of an in domain treebank for training. Instead, we train on an out of domain treebank of newswire using data augmentation techniques to make these structures resemble natural, spontaneous speech. We trained a parser with and without the augmented data and tested its performance using manually validated POS tags in clinical speech produced by patients with various types of neurodegenerative co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.05796","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/2307.05796/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":"2026-07-05T06:30:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qGWtUQ+mjjJ1vmA2Ei33MA8sEHy6KcEMbhh08jqkbnvAUKrXHM1fQPzoAsIQb/T2uSlBUjPlkqIRfv3vWKFmDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T07:07:34.276121Z"},"content_sha256":"a55b4950cbe882ba03af5cd04851f688cd67df9aa506094237c83aa57e3d94b8","schema_version":"1.0","event_id":"sha256:a55b4950cbe882ba03af5cd04851f688cd67df9aa506094237c83aa57e3d94b8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BENQYUOYDU4PY4OLOPODURZY5X/bundle.json","state_url":"https://pith.science/pith/BENQYUOYDU4PY4OLOPODURZY5X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BENQYUOYDU4PY4OLOPODURZY5X/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":"2026-08-15T07:07:34Z","links":{"resolver":"https://pith.science/pith/BENQYUOYDU4PY4OLOPODURZY5X","bundle":"https://pith.science/pith/BENQYUOYDU4PY4OLOPODURZY5X/bundle.json","state":"https://pith.science/pith/BENQYUOYDU4PY4OLOPODURZY5X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BENQYUOYDU4PY4OLOPODURZY5X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BENQYUOYDU4PY4OLOPODURZY5X","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":"41fd3234dc0edb9c06c3e606e52fe5db9d3237d39477b337718bf5812d6281f7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-11T20:42:06Z","title_canon_sha256":"2db36e3193d4bd508f0708007316e377cd2aa7a7daeac5787f74a3f0667d5f89"},"schema_version":"1.0","source":{"id":"2307.05796","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.05796","created_at":"2026-07-05T06:30:12Z"},{"alias_kind":"arxiv_version","alias_value":"2307.05796v1","created_at":"2026-07-05T06:30:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.05796","created_at":"2026-07-05T06:30:12Z"},{"alias_kind":"pith_short_12","alias_value":"BENQYUOYDU4P","created_at":"2026-07-05T06:30:12Z"},{"alias_kind":"pith_short_16","alias_value":"BENQYUOYDU4PY4OL","created_at":"2026-07-05T06:30:12Z"},{"alias_kind":"pith_short_8","alias_value":"BENQYUOY","created_at":"2026-07-05T06:30:12Z"}],"graph_snapshots":[{"event_id":"sha256:a55b4950cbe882ba03af5cd04851f688cd67df9aa506094237c83aa57e3d94b8","target":"graph","created_at":"2026-07-05T06:30:12Z","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/2307.05796/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper addresses the problem of improving POS tagging of transcripts of speech from clinical populations. In contrast to prior work on parsing and POS tagging of transcribed speech, we do not make use of an in domain treebank for training. Instead, we train on an out of domain treebank of newswire using data augmentation techniques to make these structures resemble natural, spontaneous speech. We trained a parser with and without the augmented data and tested its performance using manually validated POS tags in clinical speech produced by patients with various types of neurodegenerative co","authors_text":"David J. Irwin, Naomi Nevler, Neville Ryant, Seth Kulick, Sunghye Cho","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-11T20:42:06Z","title":"Improved POS tagging for spontaneous, clinical speech using data augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.05796","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:a9a576a7ca6eecca95585a9e33193a9d649b2350e8ab013abe8493671614c614","target":"record","created_at":"2026-07-05T06:30:12Z","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":"41fd3234dc0edb9c06c3e606e52fe5db9d3237d39477b337718bf5812d6281f7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-11T20:42:06Z","title_canon_sha256":"2db36e3193d4bd508f0708007316e377cd2aa7a7daeac5787f74a3f0667d5f89"},"schema_version":"1.0","source":{"id":"2307.05796","kind":"arxiv","version":1}},"canonical_sha256":"091b0c51d81d38fc71cb73dc3a4738ede91c829b544983f5340713afac84786c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"091b0c51d81d38fc71cb73dc3a4738ede91c829b544983f5340713afac84786c","first_computed_at":"2026-07-05T06:30:12.661828Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:30:12.661828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bxRGYWRj1dcbHXkkQFzGt+VKwRNg+5JZgh36jgiiinnGD5NFHUUuJtYvt2x6pAlb4DDmJbcWNEwpzA3wW8rNDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:30:12.662286Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.05796","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a9a576a7ca6eecca95585a9e33193a9d649b2350e8ab013abe8493671614c614","sha256:a55b4950cbe882ba03af5cd04851f688cd67df9aa506094237c83aa57e3d94b8"],"state_sha256":"10cba2491d2608e7e3f6582d3b1d5722a17621452ad20c8bcb8d8bea349ed243"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tr/fClWoJHM6vtuz5a6MFiY07GLEg3/hvXq4kkul2aH2zKtUJ45xC8B59rFSJK8XKuO2i5e5pkTc2H2gXHG0AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T07:07:34.280711Z","bundle_sha256":"44e884f31203597408b8f53740bb1e89363fb3ad029e2993ac20f3b65be921fe"}}