{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:JWBA4F4R57UVPLXHYVXM53E74H","short_pith_number":"pith:JWBA4F4R","canonical_record":{"source":{"id":"2109.06103","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-13T16:25:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c685ec86996b53ac302bbb99ee7462446ef468b21f7e5660fb9bafa8c97a95ae","abstract_canon_sha256":"1ee159616697c4dd3bfbd33dfd17df3ea261543ddee579b83f538ff6d0287c7a"},"schema_version":"1.0"},"canonical_sha256":"4d820e1791efe957aee7c56eceec9fe1c6d4e0d6347388f2e35a34a2105a624c","source":{"kind":"arxiv","id":"2109.06103","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.06103","created_at":"2026-07-05T03:13:45Z"},{"alias_kind":"arxiv_version","alias_value":"2109.06103v1","created_at":"2026-07-05T03:13:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.06103","created_at":"2026-07-05T03:13:45Z"},{"alias_kind":"pith_short_12","alias_value":"JWBA4F4R57UV","created_at":"2026-07-05T03:13:45Z"},{"alias_kind":"pith_short_16","alias_value":"JWBA4F4R57UVPLXH","created_at":"2026-07-05T03:13:45Z"},{"alias_kind":"pith_short_8","alias_value":"JWBA4F4R","created_at":"2026-07-05T03:13:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:JWBA4F4R57UVPLXHYVXM53E74H","target":"record","payload":{"canonical_record":{"source":{"id":"2109.06103","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-13T16:25:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c685ec86996b53ac302bbb99ee7462446ef468b21f7e5660fb9bafa8c97a95ae","abstract_canon_sha256":"1ee159616697c4dd3bfbd33dfd17df3ea261543ddee579b83f538ff6d0287c7a"},"schema_version":"1.0"},"canonical_sha256":"4d820e1791efe957aee7c56eceec9fe1c6d4e0d6347388f2e35a34a2105a624c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:13:45.453631Z","signature_b64":"4bjHZpD2M8/Y6HLnin8YDpD8H9FAqwWuHDjczOBzuZpXrN6HsBpK9U0uICImM8/kmddeSTY9ZYEfj9CMzMKxBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d820e1791efe957aee7c56eceec9fe1c6d4e0d6347388f2e35a34a2105a624c","last_reissued_at":"2026-07-05T03:13:45.453246Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:13:45.453246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.06103","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":"2026-07-05T03:13:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l/+yI9TR7UBMwUtDrbl9SxtQEFTb9F5S/wE51XkpNywNa7UgrxYYf7ON7XBhht4LtQI4wOgGvvz795KqaidUAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T14:31:23.033193Z"},"content_sha256":"25ff82ea469faaba2236e64d6a8e5ac90eae89e28df909b9d4e41f7e25af6c38","schema_version":"1.0","event_id":"sha256:25ff82ea469faaba2236e64d6a8e5ac90eae89e28df909b9d4e41f7e25af6c38"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:JWBA4F4R57UVPLXHYVXM53E74H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Joint prediction of truecasing and punctuation for conversational speech in low-resource scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Agnieszka Miko{\\l}ajczyk, Najim Dehak, Piotr P\\k{e}zik, Piotr \\.Zelasko, Raghavendra Pappagari","submitted_at":"2021-09-13T16:25:37Z","abstract_excerpt":"Capitalization and punctuation are important cues for comprehending written texts and conversational transcripts. Yet, many ASR systems do not produce punctuated and case-formatted speech transcripts. We propose to use a multi-task system that can exploit the relations between casing and punctuation to improve their prediction performance. Whereas text data for predicting punctuation and truecasing is seemingly abundant, we argue that written text resources are inadequate as training data for conversational models. We quantify the mismatch between written and conversational text domains by com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.06103","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/2109.06103/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":"2026-07-05T03:13:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9qYzBu09QK1uhVodt/5+CG4rU5nDJXrDnyTSnj+NqZh/GNCvs7Y9SrKlAxRFUmBRTOI5mBi0/sFb0zvCWq6XDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T14:31:23.033598Z"},"content_sha256":"e460fd2a11a5b949164f1a2c0a42b2194e443eb64745f7a0a4b719df5ff6ff74","schema_version":"1.0","event_id":"sha256:e460fd2a11a5b949164f1a2c0a42b2194e443eb64745f7a0a4b719df5ff6ff74"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JWBA4F4R57UVPLXHYVXM53E74H/bundle.json","state_url":"https://pith.science/pith/JWBA4F4R57UVPLXHYVXM53E74H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JWBA4F4R57UVPLXHYVXM53E74H/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":"2026-07-05T14:31:23Z","links":{"resolver":"https://pith.science/pith/JWBA4F4R57UVPLXHYVXM53E74H","bundle":"https://pith.science/pith/JWBA4F4R57UVPLXHYVXM53E74H/bundle.json","state":"https://pith.science/pith/JWBA4F4R57UVPLXHYVXM53E74H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JWBA4F4R57UVPLXHYVXM53E74H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:JWBA4F4R57UVPLXHYVXM53E74H","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":"1ee159616697c4dd3bfbd33dfd17df3ea261543ddee579b83f538ff6d0287c7a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-13T16:25:37Z","title_canon_sha256":"c685ec86996b53ac302bbb99ee7462446ef468b21f7e5660fb9bafa8c97a95ae"},"schema_version":"1.0","source":{"id":"2109.06103","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.06103","created_at":"2026-07-05T03:13:45Z"},{"alias_kind":"arxiv_version","alias_value":"2109.06103v1","created_at":"2026-07-05T03:13:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.06103","created_at":"2026-07-05T03:13:45Z"},{"alias_kind":"pith_short_12","alias_value":"JWBA4F4R57UV","created_at":"2026-07-05T03:13:45Z"},{"alias_kind":"pith_short_16","alias_value":"JWBA4F4R57UVPLXH","created_at":"2026-07-05T03:13:45Z"},{"alias_kind":"pith_short_8","alias_value":"JWBA4F4R","created_at":"2026-07-05T03:13:45Z"}],"graph_snapshots":[{"event_id":"sha256:e460fd2a11a5b949164f1a2c0a42b2194e443eb64745f7a0a4b719df5ff6ff74","target":"graph","created_at":"2026-07-05T03:13:45Z","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/2109.06103/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Capitalization and punctuation are important cues for comprehending written texts and conversational transcripts. Yet, many ASR systems do not produce punctuated and case-formatted speech transcripts. We propose to use a multi-task system that can exploit the relations between casing and punctuation to improve their prediction performance. Whereas text data for predicting punctuation and truecasing is seemingly abundant, we argue that written text resources are inadequate as training data for conversational models. We quantify the mismatch between written and conversational text domains by com","authors_text":"Agnieszka Miko{\\l}ajczyk, Najim Dehak, Piotr P\\k{e}zik, Piotr \\.Zelasko, Raghavendra Pappagari","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-13T16:25:37Z","title":"Joint prediction of truecasing and punctuation for conversational speech in low-resource scenarios"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.06103","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":"sha256:25ff82ea469faaba2236e64d6a8e5ac90eae89e28df909b9d4e41f7e25af6c38","target":"record","created_at":"2026-07-05T03:13:45Z","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":"1ee159616697c4dd3bfbd33dfd17df3ea261543ddee579b83f538ff6d0287c7a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-13T16:25:37Z","title_canon_sha256":"c685ec86996b53ac302bbb99ee7462446ef468b21f7e5660fb9bafa8c97a95ae"},"schema_version":"1.0","source":{"id":"2109.06103","kind":"arxiv","version":1}},"canonical_sha256":"4d820e1791efe957aee7c56eceec9fe1c6d4e0d6347388f2e35a34a2105a624c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d820e1791efe957aee7c56eceec9fe1c6d4e0d6347388f2e35a34a2105a624c","first_computed_at":"2026-07-05T03:13:45.453246Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:13:45.453246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4bjHZpD2M8/Y6HLnin8YDpD8H9FAqwWuHDjczOBzuZpXrN6HsBpK9U0uICImM8/kmddeSTY9ZYEfj9CMzMKxBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:13:45.453631Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.06103","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:25ff82ea469faaba2236e64d6a8e5ac90eae89e28df909b9d4e41f7e25af6c38","sha256:e460fd2a11a5b949164f1a2c0a42b2194e443eb64745f7a0a4b719df5ff6ff74"],"state_sha256":"3f15f83fb06a223203de7d3288df1045416f55a6dd4d5ca87fcfc44c11720646"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MR4XTpZnaH+vPdTlCM1Bz6UmrfrFHN4B56Daxc3Ove9ZLWtl+uC6skbpzJzffQsr8M3x2UsrDqlOIZdQEcWbCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T14:31:23.035892Z","bundle_sha256":"1cbafb3cb5d23305375f6b2118162f918a545a39b9107f0893ab2ee5bdd20fe1"}}