{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:WRHJ3SEG2JFUYRNEVRYGFTRFWS","short_pith_number":"pith:WRHJ3SEG","schema_version":"1.0","canonical_sha256":"b44e9dc886d24b4c45a4ac7062ce25b4a9aa07b7664c61c1089a6589fc515d46","source":{"kind":"arxiv","id":"2102.04643","version":1},"attestation_state":"computed","paper":{"title":"Efficient Retrieval Augmented Generation from Unstructured Knowledge for Task-Oriented Dialog","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Christian Dugast, David Thulke, Hermann Ney, Nico Daheim","submitted_at":"2021-02-09T04:50:35Z","abstract_excerpt":"This paper summarizes our work on the first track of the ninth Dialog System Technology Challenge (DSTC 9), \"Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access\". The goal of the task is to generate responses to user turns in a task-oriented dialog that require knowledge from unstructured documents. The task is divided into three subtasks: detection, selection and generation. In order to be compute efficient, we formulate the selection problem in terms of hierarchical classification steps. We achieve our best results with this model. Alternatively, we e"},"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":"2102.04643","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-09T04:50:35Z","cross_cats_sorted":[],"title_canon_sha256":"86fe3cb20c750fb9e0038916c53286e006b21101a745a02d52298e40af65987e","abstract_canon_sha256":"04776dee19ac3636d7a4b839bc5fb3bbe019d0c915b7d8e91da31af81093ed6c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:14:03.210740Z","signature_b64":"CS+3zvlCOOfJO0HrrtZ234Ue/xnMcQWxqsPCocQKSI0EOexXJqsUwWS+SX68f6Wbkx8ea9K6lTDlGjH0M5qMBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b44e9dc886d24b4c45a4ac7062ce25b4a9aa07b7664c61c1089a6589fc515d46","last_reissued_at":"2026-07-05T02:14:03.210292Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:14:03.210292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Retrieval Augmented Generation from Unstructured Knowledge for Task-Oriented Dialog","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Christian Dugast, David Thulke, Hermann Ney, Nico Daheim","submitted_at":"2021-02-09T04:50:35Z","abstract_excerpt":"This paper summarizes our work on the first track of the ninth Dialog System Technology Challenge (DSTC 9), \"Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access\". The goal of the task is to generate responses to user turns in a task-oriented dialog that require knowledge from unstructured documents. The task is divided into three subtasks: detection, selection and generation. In order to be compute efficient, we formulate the selection problem in terms of hierarchical classification steps. We achieve our best results with this model. Alternatively, we e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.04643","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/2102.04643/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":"2102.04643","created_at":"2026-07-05T02:14:03.210362+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.04643v1","created_at":"2026-07-05T02:14:03.210362+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.04643","created_at":"2026-07-05T02:14:03.210362+00:00"},{"alias_kind":"pith_short_12","alias_value":"WRHJ3SEG2JFU","created_at":"2026-07-05T02:14:03.210362+00:00"},{"alias_kind":"pith_short_16","alias_value":"WRHJ3SEG2JFUYRNE","created_at":"2026-07-05T02:14:03.210362+00:00"},{"alias_kind":"pith_short_8","alias_value":"WRHJ3SEG","created_at":"2026-07-05T02:14:03.210362+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.18845","citing_title":"Text Data Augmentation for Large Language Models: A Comprehensive Survey of Methods, Challenges, and Opportunities","ref_index":58,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WRHJ3SEG2JFUYRNEVRYGFTRFWS","json":"https://pith.science/pith/WRHJ3SEG2JFUYRNEVRYGFTRFWS.json","graph_json":"https://pith.science/api/pith-number/WRHJ3SEG2JFUYRNEVRYGFTRFWS/graph.json","events_json":"https://pith.science/api/pith-number/WRHJ3SEG2JFUYRNEVRYGFTRFWS/events.json","paper":"https://pith.science/paper/WRHJ3SEG"},"agent_actions":{"view_html":"https://pith.science/pith/WRHJ3SEG2JFUYRNEVRYGFTRFWS","download_json":"https://pith.science/pith/WRHJ3SEG2JFUYRNEVRYGFTRFWS.json","view_paper":"https://pith.science/paper/WRHJ3SEG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.04643&json=true","fetch_graph":"https://pith.science/api/pith-number/WRHJ3SEG2JFUYRNEVRYGFTRFWS/graph.json","fetch_events":"https://pith.science/api/pith-number/WRHJ3SEG2JFUYRNEVRYGFTRFWS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WRHJ3SEG2JFUYRNEVRYGFTRFWS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WRHJ3SEG2JFUYRNEVRYGFTRFWS/action/storage_attestation","attest_author":"https://pith.science/pith/WRHJ3SEG2JFUYRNEVRYGFTRFWS/action/author_attestation","sign_citation":"https://pith.science/pith/WRHJ3SEG2JFUYRNEVRYGFTRFWS/action/citation_signature","submit_replication":"https://pith.science/pith/WRHJ3SEG2JFUYRNEVRYGFTRFWS/action/replication_record"}},"created_at":"2026-07-05T02:14:03.210362+00:00","updated_at":"2026-07-05T02:14:03.210362+00:00"}