{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:LJHQFSTO2SSYVTCUBIG6ZAETG5","short_pith_number":"pith:LJHQFSTO","schema_version":"1.0","canonical_sha256":"5a4f02ca6ed4a58acc540a0dec809337516f7fe4e9348adcbe5c88ff0dbbe18b","source":{"kind":"arxiv","id":"2112.08342","version":1},"attestation_state":"computed","paper":{"title":"DG2: Data Augmentation Through Document Grounded Dialogue Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Derek Chen, Luis A. Lastras, Qingyang Wu, Sachindra Joshi, Song Feng, Zhou Yu","submitted_at":"2021-12-15T18:50:14Z","abstract_excerpt":"Collecting data for training dialog systems can be extremely expensive due to the involvement of human participants and need for extensive annotation. Especially in document-grounded dialog systems, human experts need to carefully read the unstructured documents to answer the users' questions. As a result, existing document-grounded dialog datasets are relatively small-scale and obstruct the effective training of dialogue systems. In this paper, we propose an automatic data augmentation technique grounded on documents through a generative dialogue model. The dialogue model consists of a user b"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2112.08342","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-15T18:50:14Z","cross_cats_sorted":[],"title_canon_sha256":"fdf6a0755f9f503946c7792d6ffb5d0e4ea853a80d8f1158d8b237021ff08422","abstract_canon_sha256":"6edf09070432587c2841763d2e45effd4e6558fef121b34e2ea31379f63b35fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:41:21.090529Z","signature_b64":"A9NJ5eAWUuxWkccfKXn8G2P9HZ9m1Z55JWsgRcOkQJIauQ4SpzlAYaDpkScZzBlGaHkPPSW7Xi2eBRrRGLOpDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a4f02ca6ed4a58acc540a0dec809337516f7fe4e9348adcbe5c88ff0dbbe18b","last_reissued_at":"2026-07-05T03:41:21.090099Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:41:21.090099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DG2: Data Augmentation Through Document Grounded Dialogue Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Derek Chen, Luis A. Lastras, Qingyang Wu, Sachindra Joshi, Song Feng, Zhou Yu","submitted_at":"2021-12-15T18:50:14Z","abstract_excerpt":"Collecting data for training dialog systems can be extremely expensive due to the involvement of human participants and need for extensive annotation. Especially in document-grounded dialog systems, human experts need to carefully read the unstructured documents to answer the users' questions. As a result, existing document-grounded dialog datasets are relatively small-scale and obstruct the effective training of dialogue systems. In this paper, we propose an automatic data augmentation technique grounded on documents through a generative dialogue model. The dialogue model consists of a user b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.08342","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/2112.08342/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2112.08342","created_at":"2026-07-05T03:41:21.090150+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.08342v1","created_at":"2026-07-05T03:41:21.090150+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.08342","created_at":"2026-07-05T03:41:21.090150+00:00"},{"alias_kind":"pith_short_12","alias_value":"LJHQFSTO2SSY","created_at":"2026-07-05T03:41:21.090150+00:00"},{"alias_kind":"pith_short_16","alias_value":"LJHQFSTO2SSYVTCU","created_at":"2026-07-05T03:41:21.090150+00:00"},{"alias_kind":"pith_short_8","alias_value":"LJHQFSTO","created_at":"2026-07-05T03:41:21.090150+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LJHQFSTO2SSYVTCUBIG6ZAETG5","json":"https://pith.science/pith/LJHQFSTO2SSYVTCUBIG6ZAETG5.json","graph_json":"https://pith.science/api/pith-number/LJHQFSTO2SSYVTCUBIG6ZAETG5/graph.json","events_json":"https://pith.science/api/pith-number/LJHQFSTO2SSYVTCUBIG6ZAETG5/events.json","paper":"https://pith.science/paper/LJHQFSTO"},"agent_actions":{"view_html":"https://pith.science/pith/LJHQFSTO2SSYVTCUBIG6ZAETG5","download_json":"https://pith.science/pith/LJHQFSTO2SSYVTCUBIG6ZAETG5.json","view_paper":"https://pith.science/paper/LJHQFSTO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.08342&json=true","fetch_graph":"https://pith.science/api/pith-number/LJHQFSTO2SSYVTCUBIG6ZAETG5/graph.json","fetch_events":"https://pith.science/api/pith-number/LJHQFSTO2SSYVTCUBIG6ZAETG5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LJHQFSTO2SSYVTCUBIG6ZAETG5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LJHQFSTO2SSYVTCUBIG6ZAETG5/action/storage_attestation","attest_author":"https://pith.science/pith/LJHQFSTO2SSYVTCUBIG6ZAETG5/action/author_attestation","sign_citation":"https://pith.science/pith/LJHQFSTO2SSYVTCUBIG6ZAETG5/action/citation_signature","submit_replication":"https://pith.science/pith/LJHQFSTO2SSYVTCUBIG6ZAETG5/action/replication_record"}},"created_at":"2026-07-05T03:41:21.090150+00:00","updated_at":"2026-07-05T03:41:21.090150+00:00"}