{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:PCK6QDOBHRCBOUH53S3G4QCWLH","short_pith_number":"pith:PCK6QDOB","canonical_record":{"source":{"id":"2004.05985","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-13T15:02:28Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"9569865101bcbb7fcc33048a2c46b07980ba34e978ce8cfd6ea9ed131b21c3d8","abstract_canon_sha256":"1a2af95a9bc1c3d50d694af1db3e70511f321db4b110bba658bae72f80552365"},"schema_version":"1.0"},"canonical_sha256":"7895e80dc13c441750fddcb66e405659e5dd2afa0e1f5f9a9aaac33b7a28c068","source":{"kind":"arxiv","id":"2004.05985","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.05985","created_at":"2026-07-05T00:54:42Z"},{"alias_kind":"arxiv_version","alias_value":"2004.05985v1","created_at":"2026-07-05T00:54:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.05985","created_at":"2026-07-05T00:54:42Z"},{"alias_kind":"pith_short_12","alias_value":"PCK6QDOBHRCB","created_at":"2026-07-05T00:54:42Z"},{"alias_kind":"pith_short_16","alias_value":"PCK6QDOBHRCBOUH5","created_at":"2026-07-05T00:54:42Z"},{"alias_kind":"pith_short_8","alias_value":"PCK6QDOB","created_at":"2026-07-05T00:54:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:PCK6QDOBHRCBOUH53S3G4QCWLH","target":"record","payload":{"canonical_record":{"source":{"id":"2004.05985","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-13T15:02:28Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"9569865101bcbb7fcc33048a2c46b07980ba34e978ce8cfd6ea9ed131b21c3d8","abstract_canon_sha256":"1a2af95a9bc1c3d50d694af1db3e70511f321db4b110bba658bae72f80552365"},"schema_version":"1.0"},"canonical_sha256":"7895e80dc13c441750fddcb66e405659e5dd2afa0e1f5f9a9aaac33b7a28c068","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:54:42.864984Z","signature_b64":"z4v8CmmSP6yofYnlKw7e7GSYg38s97WzQGSILb+bRVvp2r8Bupi6iY/SzHVPJ4Gr4b3M+NE7fWRrvCO4cFYeCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7895e80dc13c441750fddcb66e405659e5dd2afa0e1f5f9a9aaac33b7a28c068","last_reissued_at":"2026-07-05T00:54:42.864586Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:54:42.864586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.05985","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":"2026-07-05T00:54:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aecnmmiPSQnIKYSoFzK31L/VVMVTd5GrWs0p+kifIhXhchTMQqgheRe59SnzgPEgau1iyuNxRkAlCGGOHDuyBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:01:11.228740Z"},"content_sha256":"ecdf48d57f16ff9a6c0b70e16586f4060cd2925864b142a1ad5c4a09723fcc4d","schema_version":"1.0","event_id":"sha256:ecdf48d57f16ff9a6c0b70e16586f4060cd2925864b142a1ad5c4a09723fcc4d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:PCK6QDOBHRCBOUH53S3G4QCWLH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Punctuation Prediction in Spontaneous Conversations: Can We Mitigate ASR Errors with Retrofitted Word Embeddings?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Adrian Szymczak, Jan Mizgajski, {\\L}ukasz Augustyniak, Miko{\\l}aj Morzy, Najim Dehak, Piotr Szymanski, Piotr Zelasko, Yishay Carmiel","submitted_at":"2020-04-13T15:02:28Z","abstract_excerpt":"Automatic Speech Recognition (ASR) systems introduce word errors, which often confuse punctuation prediction models, turning punctuation restoration into a challenging task. These errors usually take the form of homonyms. We show how retrofitting of the word embeddings on the domain-specific data can mitigate ASR errors. Our main contribution is a method for better alignment of homonym embeddings and the validation of the presented method on the punctuation prediction task. We record the absolute improvement in punctuation prediction accuracy between 6.2% (for question marks) to 9% (for period"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.05985","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/2004.05985/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":"2026-07-05T00:54:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UrdVTZJCqyVsgjalyg6gxbG8nzP3Y/93YwII46tQ3mtaCLYZcmfabaFTWJzSLkjcZWklkXosQ0AFceWQj8hyCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:01:11.229120Z"},"content_sha256":"a85485b121e0d5803d2254e9c6dfc1aafb754efd5033c6f1c4b988a945036002","schema_version":"1.0","event_id":"sha256:a85485b121e0d5803d2254e9c6dfc1aafb754efd5033c6f1c4b988a945036002"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PCK6QDOBHRCBOUH53S3G4QCWLH/bundle.json","state_url":"https://pith.science/pith/PCK6QDOBHRCBOUH53S3G4QCWLH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PCK6QDOBHRCBOUH53S3G4QCWLH/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":"2026-07-06T17:01:11Z","links":{"resolver":"https://pith.science/pith/PCK6QDOBHRCBOUH53S3G4QCWLH","bundle":"https://pith.science/pith/PCK6QDOBHRCBOUH53S3G4QCWLH/bundle.json","state":"https://pith.science/pith/PCK6QDOBHRCBOUH53S3G4QCWLH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PCK6QDOBHRCBOUH53S3G4QCWLH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:PCK6QDOBHRCBOUH53S3G4QCWLH","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":"1a2af95a9bc1c3d50d694af1db3e70511f321db4b110bba658bae72f80552365","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-13T15:02:28Z","title_canon_sha256":"9569865101bcbb7fcc33048a2c46b07980ba34e978ce8cfd6ea9ed131b21c3d8"},"schema_version":"1.0","source":{"id":"2004.05985","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.05985","created_at":"2026-07-05T00:54:42Z"},{"alias_kind":"arxiv_version","alias_value":"2004.05985v1","created_at":"2026-07-05T00:54:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.05985","created_at":"2026-07-05T00:54:42Z"},{"alias_kind":"pith_short_12","alias_value":"PCK6QDOBHRCB","created_at":"2026-07-05T00:54:42Z"},{"alias_kind":"pith_short_16","alias_value":"PCK6QDOBHRCBOUH5","created_at":"2026-07-05T00:54:42Z"},{"alias_kind":"pith_short_8","alias_value":"PCK6QDOB","created_at":"2026-07-05T00:54:42Z"}],"graph_snapshots":[{"event_id":"sha256:a85485b121e0d5803d2254e9c6dfc1aafb754efd5033c6f1c4b988a945036002","target":"graph","created_at":"2026-07-05T00:54:42Z","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/2004.05985/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automatic Speech Recognition (ASR) systems introduce word errors, which often confuse punctuation prediction models, turning punctuation restoration into a challenging task. These errors usually take the form of homonyms. We show how retrofitting of the word embeddings on the domain-specific data can mitigate ASR errors. Our main contribution is a method for better alignment of homonym embeddings and the validation of the presented method on the punctuation prediction task. We record the absolute improvement in punctuation prediction accuracy between 6.2% (for question marks) to 9% (for period","authors_text":"Adrian Szymczak, Jan Mizgajski, {\\L}ukasz Augustyniak, Miko{\\l}aj Morzy, Najim Dehak, Piotr Szymanski, Piotr Zelasko, Yishay Carmiel","cross_cats":["cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-13T15:02:28Z","title":"Punctuation Prediction in Spontaneous Conversations: Can We Mitigate ASR Errors with Retrofitted Word Embeddings?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.05985","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:ecdf48d57f16ff9a6c0b70e16586f4060cd2925864b142a1ad5c4a09723fcc4d","target":"record","created_at":"2026-07-05T00:54:42Z","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":"1a2af95a9bc1c3d50d694af1db3e70511f321db4b110bba658bae72f80552365","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-13T15:02:28Z","title_canon_sha256":"9569865101bcbb7fcc33048a2c46b07980ba34e978ce8cfd6ea9ed131b21c3d8"},"schema_version":"1.0","source":{"id":"2004.05985","kind":"arxiv","version":1}},"canonical_sha256":"7895e80dc13c441750fddcb66e405659e5dd2afa0e1f5f9a9aaac33b7a28c068","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7895e80dc13c441750fddcb66e405659e5dd2afa0e1f5f9a9aaac33b7a28c068","first_computed_at":"2026-07-05T00:54:42.864586Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:54:42.864586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z4v8CmmSP6yofYnlKw7e7GSYg38s97WzQGSILb+bRVvp2r8Bupi6iY/SzHVPJ4Gr4b3M+NE7fWRrvCO4cFYeCw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:54:42.864984Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.05985","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ecdf48d57f16ff9a6c0b70e16586f4060cd2925864b142a1ad5c4a09723fcc4d","sha256:a85485b121e0d5803d2254e9c6dfc1aafb754efd5033c6f1c4b988a945036002"],"state_sha256":"a2646206690f145c707285eeb22f1f28ba253dd43d205df3cf50df36be2926b0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oibwbteaAxmy8MS75dedPDDJk4SaW97+Z4nTzumZdZqjteL6OGzdGHWA/LwaPjx/XbYY2XYH2GWTuyVzSQ1HBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T17:01:11.231074Z","bundle_sha256":"81837199085f166c508756ce54e38b3ebc6592b5aa7a08314b3bfd783e4bf50b"}}