{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:LJHQFSTO2SSYVTCUBIG6ZAETG5","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":"6edf09070432587c2841763d2e45effd4e6558fef121b34e2ea31379f63b35fb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-15T18:50:14Z","title_canon_sha256":"fdf6a0755f9f503946c7792d6ffb5d0e4ea853a80d8f1158d8b237021ff08422"},"schema_version":"1.0","source":{"id":"2112.08342","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.08342","created_at":"2026-07-05T03:41:21Z"},{"alias_kind":"arxiv_version","alias_value":"2112.08342v1","created_at":"2026-07-05T03:41:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.08342","created_at":"2026-07-05T03:41:21Z"},{"alias_kind":"pith_short_12","alias_value":"LJHQFSTO2SSY","created_at":"2026-07-05T03:41:21Z"},{"alias_kind":"pith_short_16","alias_value":"LJHQFSTO2SSYVTCU","created_at":"2026-07-05T03:41:21Z"},{"alias_kind":"pith_short_8","alias_value":"LJHQFSTO","created_at":"2026-07-05T03:41:21Z"}],"graph_snapshots":[{"event_id":"sha256:ba8465ddd8c6413913d286f75a8541916d47df971dfbdc8dcb66d0507e79949e","target":"graph","created_at":"2026-07-05T03:41:21Z","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/2112.08342/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Derek Chen, Luis A. Lastras, Qingyang Wu, Sachindra Joshi, Song Feng, Zhou Yu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-15T18:50:14Z","title":"DG2: Data Augmentation Through Document Grounded Dialogue Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.08342","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":"sha256:3485642c084e7f9b1c651e78f62218f0e83afa7aea4cb5d29f805be5c4e97afd","target":"record","created_at":"2026-07-05T03:41:21Z","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":"6edf09070432587c2841763d2e45effd4e6558fef121b34e2ea31379f63b35fb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-15T18:50:14Z","title_canon_sha256":"fdf6a0755f9f503946c7792d6ffb5d0e4ea853a80d8f1158d8b237021ff08422"},"schema_version":"1.0","source":{"id":"2112.08342","kind":"arxiv","version":1}},"canonical_sha256":"5a4f02ca6ed4a58acc540a0dec809337516f7fe4e9348adcbe5c88ff0dbbe18b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a4f02ca6ed4a58acc540a0dec809337516f7fe4e9348adcbe5c88ff0dbbe18b","first_computed_at":"2026-07-05T03:41:21.090099Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:41:21.090099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A9NJ5eAWUuxWkccfKXn8G2P9HZ9m1Z55JWsgRcOkQJIauQ4SpzlAYaDpkScZzBlGaHkPPSW7Xi2eBRrRGLOpDw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:41:21.090529Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.08342","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3485642c084e7f9b1c651e78f62218f0e83afa7aea4cb5d29f805be5c4e97afd","sha256:ba8465ddd8c6413913d286f75a8541916d47df971dfbdc8dcb66d0507e79949e"],"state_sha256":"ef68cc0a9ee162dd86bcc5bde9520f47e90c279a445ab29184b67ba2dcd57a51"}