{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:67XYE5HEO3JBTOQW4EKJHWTFRK","short_pith_number":"pith:67XYE5HE","schema_version":"1.0","canonical_sha256":"f7ef8274e476d219ba16e11493da658a93ab0c9a8940505770c1986bd3e63b57","source":{"kind":"arxiv","id":"2309.09128","version":3},"attestation_state":"computed","paper":{"title":"ChainForge: A Visual Toolkit for Prompt Engineering and LLM Hypothesis Testing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Chelse Swoopes, Elena Glassman, Ian Arawjo, Martin Wattenberg, Priyan Vaithilingam","submitted_at":"2023-09-17T01:42:30Z","abstract_excerpt":"Evaluating outputs of large language models (LLMs) is challenging, requiring making -- and making sense of -- many responses. Yet tools that go beyond basic prompting tend to require knowledge of programming APIs, focus on narrow domains, or are closed-source. We present ChainForge, an open-source visual toolkit for prompt engineering and on-demand hypothesis testing of text generation LLMs. ChainForge provides a graphical interface for comparison of responses across models and prompt variations. Our system was designed to support three tasks: model selection, prompt template design, and hypot"},"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":"2309.09128","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2023-09-17T01:42:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f7b974513d3ba662ad25517454c417f2e27c6b4fa50519b95c25fbc53580887b","abstract_canon_sha256":"e2a4bddf7b5c9ecf72e8aae5b02fb16fe7316725ff13cdf9702f4d779cc8b8a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:15:10.997215Z","signature_b64":"r3BZD1SLgHcne/Y18pGtdtlFeIH2Kvc1JPqzCSmrabzU7keyhTAWL/rzx8uua5R9i9g3NZq2rsV88By9TfQ/AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7ef8274e476d219ba16e11493da658a93ab0c9a8940505770c1986bd3e63b57","last_reissued_at":"2026-07-05T08:15:10.996760Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:15:10.996760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ChainForge: A Visual Toolkit for Prompt Engineering and LLM Hypothesis Testing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Chelse Swoopes, Elena Glassman, Ian Arawjo, Martin Wattenberg, Priyan Vaithilingam","submitted_at":"2023-09-17T01:42:30Z","abstract_excerpt":"Evaluating outputs of large language models (LLMs) is challenging, requiring making -- and making sense of -- many responses. Yet tools that go beyond basic prompting tend to require knowledge of programming APIs, focus on narrow domains, or are closed-source. We present ChainForge, an open-source visual toolkit for prompt engineering and on-demand hypothesis testing of text generation LLMs. ChainForge provides a graphical interface for comparison of responses across models and prompt variations. Our system was designed to support three tasks: model selection, prompt template design, and hypot"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.09128","kind":"arxiv","version":3},"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/2309.09128/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":"2309.09128","created_at":"2026-07-05T08:15:10.996819+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.09128v3","created_at":"2026-07-05T08:15:10.996819+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.09128","created_at":"2026-07-05T08:15:10.996819+00:00"},{"alias_kind":"pith_short_12","alias_value":"67XYE5HEO3JB","created_at":"2026-07-05T08:15:10.996819+00:00"},{"alias_kind":"pith_short_16","alias_value":"67XYE5HEO3JBTOQW","created_at":"2026-07-05T08:15:10.996819+00:00"},{"alias_kind":"pith_short_8","alias_value":"67XYE5HE","created_at":"2026-07-05T08:15:10.996819+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/67XYE5HEO3JBTOQW4EKJHWTFRK","json":"https://pith.science/pith/67XYE5HEO3JBTOQW4EKJHWTFRK.json","graph_json":"https://pith.science/api/pith-number/67XYE5HEO3JBTOQW4EKJHWTFRK/graph.json","events_json":"https://pith.science/api/pith-number/67XYE5HEO3JBTOQW4EKJHWTFRK/events.json","paper":"https://pith.science/paper/67XYE5HE"},"agent_actions":{"view_html":"https://pith.science/pith/67XYE5HEO3JBTOQW4EKJHWTFRK","download_json":"https://pith.science/pith/67XYE5HEO3JBTOQW4EKJHWTFRK.json","view_paper":"https://pith.science/paper/67XYE5HE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.09128&json=true","fetch_graph":"https://pith.science/api/pith-number/67XYE5HEO3JBTOQW4EKJHWTFRK/graph.json","fetch_events":"https://pith.science/api/pith-number/67XYE5HEO3JBTOQW4EKJHWTFRK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/67XYE5HEO3JBTOQW4EKJHWTFRK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/67XYE5HEO3JBTOQW4EKJHWTFRK/action/storage_attestation","attest_author":"https://pith.science/pith/67XYE5HEO3JBTOQW4EKJHWTFRK/action/author_attestation","sign_citation":"https://pith.science/pith/67XYE5HEO3JBTOQW4EKJHWTFRK/action/citation_signature","submit_replication":"https://pith.science/pith/67XYE5HEO3JBTOQW4EKJHWTFRK/action/replication_record"}},"created_at":"2026-07-05T08:15:10.996819+00:00","updated_at":"2026-07-05T08:15:10.996819+00:00"}