{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FD2NHYWXEBF743X2M7PGRNUNAV","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":"dd8a05cb13cbb8fb94df53a3d9940bd1ec89ae22bffd690d91f43adec0438ac1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.HC","submitted_at":"2023-02-06T23:25:35Z","title_canon_sha256":"5dd814c733c2333abed8ed42aebe78af0903f04cb5baff29d150ff1eb04c86fa"},"schema_version":"1.0","source":{"id":"2302.03154","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.03154","created_at":"2026-07-05T05:39:34Z"},{"alias_kind":"arxiv_version","alias_value":"2302.03154v1","created_at":"2026-07-05T05:39:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.03154","created_at":"2026-07-05T05:39:34Z"},{"alias_kind":"pith_short_12","alias_value":"FD2NHYWXEBF7","created_at":"2026-07-05T05:39:34Z"},{"alias_kind":"pith_short_16","alias_value":"FD2NHYWXEBF743X2","created_at":"2026-07-05T05:39:34Z"},{"alias_kind":"pith_short_8","alias_value":"FD2NHYWX","created_at":"2026-07-05T05:39:34Z"}],"graph_snapshots":[{"event_id":"sha256:506466b05d805cd11813c3bef92d1477b774a6bcb9880e25681eedec837afc06","target":"graph","created_at":"2026-07-05T05:39:34Z","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/2302.03154/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained language models (LLMs) such as GPT-3 can carry fluent, multi-turn conversations out-of-the-box, making them attractive materials for chatbot design. Further, designers can improve LLM chatbot utterances by prepending textual prompts -- instructions and examples of desired interactions -- to its inputs. However, prompt-based improvements can be brittle; designers face challenges systematically understanding how a prompt strategy might impact the unfolding of subsequent conversations across users. To address this challenge, we introduce the concept of Conversation Regression Testing.","authors_text":"Bjoern Hartmann, J.D. Zamfirescu-Pereira, Qian Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.HC","submitted_at":"2023-02-06T23:25:35Z","title":"Conversation Regression Testing: A Design Technique for Prototyping Generalizable Prompt Strategies for Pre-trained Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.03154","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:a9331daf8831786b310d53aa12336cd6f25acac220ce81eff76e987a6e3ef25d","target":"record","created_at":"2026-07-05T05:39:34Z","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":"dd8a05cb13cbb8fb94df53a3d9940bd1ec89ae22bffd690d91f43adec0438ac1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.HC","submitted_at":"2023-02-06T23:25:35Z","title_canon_sha256":"5dd814c733c2333abed8ed42aebe78af0903f04cb5baff29d150ff1eb04c86fa"},"schema_version":"1.0","source":{"id":"2302.03154","kind":"arxiv","version":1}},"canonical_sha256":"28f4d3e2d7204bfe6efa67de68b68d05500bbe3483760c2974a7e21e0dc08eea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"28f4d3e2d7204bfe6efa67de68b68d05500bbe3483760c2974a7e21e0dc08eea","first_computed_at":"2026-07-05T05:39:34.329820Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:39:34.329820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9m06W5i807roluush/m0IjdRa8xdAGwGvJwa/klRuAy+08/nevhX0SDtDprxWoCsuc2JFFqVwFg6abiZHV9LBw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:39:34.330268Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.03154","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a9331daf8831786b310d53aa12336cd6f25acac220ce81eff76e987a6e3ef25d","sha256:506466b05d805cd11813c3bef92d1477b774a6bcb9880e25681eedec837afc06"],"state_sha256":"826c914a91bc53af658587344c45fde564f788fe15cc6f4900b18d1d47ba8d41"}