{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:VT7WITEI4ZCLU2KNZOJT32IXEW","short_pith_number":"pith:VT7WITEI","canonical_record":{"source":{"id":"2302.10186","kind":"arxiv","version":7},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2023-02-16T21:45:35Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"33b2c4cfde1b5d6917e1cdf47c7d8e358d75c81c0b47669bddb0973575717fd0","abstract_canon_sha256":"b5a1820248a69ef388297b0173a8ee2515f9cf6cee6917682c54cb652cbe3e46"},"schema_version":"1.0"},"canonical_sha256":"acff644c88e644ba694dcb933de917258d565c15868218b12e5de62467bd8c6f","source":{"kind":"arxiv","id":"2302.10186","version":7},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.10186","created_at":"2026-07-05T07:11:13Z"},{"alias_kind":"arxiv_version","alias_value":"2302.10186v7","created_at":"2026-07-05T07:11:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.10186","created_at":"2026-07-05T07:11:13Z"},{"alias_kind":"pith_short_12","alias_value":"VT7WITEI4ZCL","created_at":"2026-07-05T07:11:13Z"},{"alias_kind":"pith_short_16","alias_value":"VT7WITEI4ZCLU2KN","created_at":"2026-07-05T07:11:13Z"},{"alias_kind":"pith_short_8","alias_value":"VT7WITEI","created_at":"2026-07-05T07:11:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:VT7WITEI4ZCLU2KNZOJT32IXEW","target":"record","payload":{"canonical_record":{"source":{"id":"2302.10186","kind":"arxiv","version":7},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2023-02-16T21:45:35Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"33b2c4cfde1b5d6917e1cdf47c7d8e358d75c81c0b47669bddb0973575717fd0","abstract_canon_sha256":"b5a1820248a69ef388297b0173a8ee2515f9cf6cee6917682c54cb652cbe3e46"},"schema_version":"1.0"},"canonical_sha256":"acff644c88e644ba694dcb933de917258d565c15868218b12e5de62467bd8c6f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:11:13.989924Z","signature_b64":"Gwqz2MIfmJ+Ys08jyJzRorcJ7GwN4/zFtO2+AtT1tCd4CRUjPYJuv9YCFWB/ZHAza/7yuPwVwGSeferETVVqCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acff644c88e644ba694dcb933de917258d565c15868218b12e5de62467bd8c6f","last_reissued_at":"2026-07-05T07:11:13.989425Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:11:13.989425Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.10186","source_version":7,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:11:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dF8xbRwLkZH4LU/Abc4BNqmXW9tIjl5xFGUOuNxOo6xbVTrF7PLsLPygNaTnK+5IP5hlLg36AZp8N6ArKasNBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T18:09:23.883571Z"},"content_sha256":"0c5e3aa36e4f4627fa885023cd7d2838731ff9b6e27ab1d2a24a72d731627eab","schema_version":"1.0","event_id":"sha256:0c5e3aa36e4f4627fa885023cd7d2838731ff9b6e27ab1d2a24a72d731627eab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:VT7WITEI4ZCLU2KNZOJT32IXEW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"E2E Spoken Entity Extraction for Virtual Agents","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Karan Singla, Srinivas Bangalore, Yeon-Jun Kim","submitted_at":"2023-02-16T21:45:35Z","abstract_excerpt":"In human-computer conversations, extracting entities such as names, street addresses and email addresses from speech is a challenging task. In this paper, we study the impact of fine-tuning pre-trained speech encoders on extracting spoken entities in human-readable form directly from speech without the need for text transcription. We illustrate that such a direct approach optimizes the encoder to transcribe only the entity relevant portions of speech ignoring the superfluous portions such as carrier phrases, or spell name entities. In the context of dialog from an enterprise virtual agent, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.10186","kind":"arxiv","version":7},"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/2302.10186/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":"2026-07-05T07:11:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dtGdLdRmMjuq2ZVfV/u5GaeSTjTh2NbOO6Nq4524jbWD22nOhuyqIVeMmhVXP/qR6+M40FU4rrDOuLOm+5rIDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T18:09:23.884393Z"},"content_sha256":"87526e5a7bb515961f53ddbc390bd329f875e9a86f8c6ac37953c6b955fa49bc","schema_version":"1.0","event_id":"sha256:87526e5a7bb515961f53ddbc390bd329f875e9a86f8c6ac37953c6b955fa49bc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VT7WITEI4ZCLU2KNZOJT32IXEW/bundle.json","state_url":"https://pith.science/pith/VT7WITEI4ZCLU2KNZOJT32IXEW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VT7WITEI4ZCLU2KNZOJT32IXEW/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":"2026-08-19T18:09:23Z","links":{"resolver":"https://pith.science/pith/VT7WITEI4ZCLU2KNZOJT32IXEW","bundle":"https://pith.science/pith/VT7WITEI4ZCLU2KNZOJT32IXEW/bundle.json","state":"https://pith.science/pith/VT7WITEI4ZCLU2KNZOJT32IXEW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VT7WITEI4ZCLU2KNZOJT32IXEW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VT7WITEI4ZCLU2KNZOJT32IXEW","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":"b5a1820248a69ef388297b0173a8ee2515f9cf6cee6917682c54cb652cbe3e46","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2023-02-16T21:45:35Z","title_canon_sha256":"33b2c4cfde1b5d6917e1cdf47c7d8e358d75c81c0b47669bddb0973575717fd0"},"schema_version":"1.0","source":{"id":"2302.10186","kind":"arxiv","version":7}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.10186","created_at":"2026-07-05T07:11:13Z"},{"alias_kind":"arxiv_version","alias_value":"2302.10186v7","created_at":"2026-07-05T07:11:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.10186","created_at":"2026-07-05T07:11:13Z"},{"alias_kind":"pith_short_12","alias_value":"VT7WITEI4ZCL","created_at":"2026-07-05T07:11:13Z"},{"alias_kind":"pith_short_16","alias_value":"VT7WITEI4ZCLU2KN","created_at":"2026-07-05T07:11:13Z"},{"alias_kind":"pith_short_8","alias_value":"VT7WITEI","created_at":"2026-07-05T07:11:13Z"}],"graph_snapshots":[{"event_id":"sha256:87526e5a7bb515961f53ddbc390bd329f875e9a86f8c6ac37953c6b955fa49bc","target":"graph","created_at":"2026-07-05T07:11:13Z","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/2302.10186/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In human-computer conversations, extracting entities such as names, street addresses and email addresses from speech is a challenging task. In this paper, we study the impact of fine-tuning pre-trained speech encoders on extracting spoken entities in human-readable form directly from speech without the need for text transcription. We illustrate that such a direct approach optimizes the encoder to transcribe only the entity relevant portions of speech ignoring the superfluous portions such as carrier phrases, or spell name entities. In the context of dialog from an enterprise virtual agent, we ","authors_text":"Karan Singla, Srinivas Bangalore, Yeon-Jun Kim","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2023-02-16T21:45:35Z","title":"E2E Spoken Entity Extraction for Virtual Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.10186","kind":"arxiv","version":7},"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":"sha256:0c5e3aa36e4f4627fa885023cd7d2838731ff9b6e27ab1d2a24a72d731627eab","target":"record","created_at":"2026-07-05T07:11:13Z","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":"b5a1820248a69ef388297b0173a8ee2515f9cf6cee6917682c54cb652cbe3e46","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2023-02-16T21:45:35Z","title_canon_sha256":"33b2c4cfde1b5d6917e1cdf47c7d8e358d75c81c0b47669bddb0973575717fd0"},"schema_version":"1.0","source":{"id":"2302.10186","kind":"arxiv","version":7}},"canonical_sha256":"acff644c88e644ba694dcb933de917258d565c15868218b12e5de62467bd8c6f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"acff644c88e644ba694dcb933de917258d565c15868218b12e5de62467bd8c6f","first_computed_at":"2026-07-05T07:11:13.989425Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:11:13.989425Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Gwqz2MIfmJ+Ys08jyJzRorcJ7GwN4/zFtO2+AtT1tCd4CRUjPYJuv9YCFWB/ZHAza/7yuPwVwGSeferETVVqCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:11:13.989924Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.10186","source_kind":"arxiv","source_version":7}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0c5e3aa36e4f4627fa885023cd7d2838731ff9b6e27ab1d2a24a72d731627eab","sha256:87526e5a7bb515961f53ddbc390bd329f875e9a86f8c6ac37953c6b955fa49bc"],"state_sha256":"b5d40a047eb273a5f604d236d77692be1c7991d912746296999bbd09eecc6f4e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4cIT8BuLiyvnapxNShV51Y5sE8I1fXzMTk03ncsVsmlCS9nNYOIRoW03af8x4MWt9n3RpUeLXvQaXhvt8by4DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T18:09:23.891115Z","bundle_sha256":"1cc9c58c9334adde6321795a992d1277e4844099d7ade8742475d7bcba8e3540"}}