{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DPCEBRV2CKVUHOX2CRFIVVL47S","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":"2a805b12781b0764ff4c3b63ee89007316a6c539e1ffc6315a296ff1c6d096da","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-26T20:34:58Z","title_canon_sha256":"36d3683d98f56fd5986c3bc44228248d213e41b67303b401b91c11656bdf8938"},"schema_version":"1.0","source":{"id":"2502.19545","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.19545","created_at":"2026-07-05T11:40:33Z"},{"alias_kind":"arxiv_version","alias_value":"2502.19545v2","created_at":"2026-07-05T11:40:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.19545","created_at":"2026-07-05T11:40:33Z"},{"alias_kind":"pith_short_12","alias_value":"DPCEBRV2CKVU","created_at":"2026-07-05T11:40:33Z"},{"alias_kind":"pith_short_16","alias_value":"DPCEBRV2CKVUHOX2","created_at":"2026-07-05T11:40:33Z"},{"alias_kind":"pith_short_8","alias_value":"DPCEBRV2","created_at":"2026-07-05T11:40:33Z"}],"graph_snapshots":[{"event_id":"sha256:946bbd9f09da38c01f905eb6103df5ca12b74dd5cf69e4c95cbf2b3645c18d3d","target":"graph","created_at":"2026-07-05T11:40:33Z","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/2502.19545/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The deployment of Large Language Models (LLMs) in customer support is constrained by hallucination (generating false information) and the high cost of proprietary models. To address these challenges, we propose a retrieval-augmented question-answering (QA) pipeline and explore how to balance human input and automation. Using a dataset of questions about a Samsung Smart TV user manual, we demonstrate that synthetic data generated by LLMs outperforms crowdsourced data in reducing hallucination in finetuned models. We also compare self-training (fine-tuning models on their own outputs) and knowle","authors_text":"Ashley Lewis, Jing Liu, Kieran Parsons, Michael White, Toshiaki Koike-Akino, Ye Wang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-26T20:34:58Z","title":"Winning Big with Small Models: Knowledge Distillation vs. Self-Training for Reducing Hallucination in Product QA Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.19545","kind":"arxiv","version":2},"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":"sha256:48a1e508b38e1a5b3f7c53dd23c3bfe5c2ac3a896f009a637b4cbbb9a0098be7","target":"record","created_at":"2026-07-05T11:40:33Z","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":"2a805b12781b0764ff4c3b63ee89007316a6c539e1ffc6315a296ff1c6d096da","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-26T20:34:58Z","title_canon_sha256":"36d3683d98f56fd5986c3bc44228248d213e41b67303b401b91c11656bdf8938"},"schema_version":"1.0","source":{"id":"2502.19545","kind":"arxiv","version":2}},"canonical_sha256":"1bc440c6ba12ab43bafa144a8ad57cfca2d898d8ab4b9b1c259f77c4eefac471","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1bc440c6ba12ab43bafa144a8ad57cfca2d898d8ab4b9b1c259f77c4eefac471","first_computed_at":"2026-07-05T11:40:33.249720Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:40:33.249720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CQqivYyljBmE3Za0ZCHHe1uPDc5bbVSHo5hhuoXsL+NA//AHBcB0rqUbX9PD8LXTZBX8gXdth/fAXJuoOl/IDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:40:33.250207Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.19545","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:48a1e508b38e1a5b3f7c53dd23c3bfe5c2ac3a896f009a637b4cbbb9a0098be7","sha256:946bbd9f09da38c01f905eb6103df5ca12b74dd5cf69e4c95cbf2b3645c18d3d"],"state_sha256":"fb01c0e9f2dcec9d7e658799660f48b7c6be59b5687db3890eae2e03d1b6dcec"}