{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DFV5LZ4VDFVLF4EDMI44UID2O4","short_pith_number":"pith:DFV5LZ4V","schema_version":"1.0","canonical_sha256":"196bd5e795196ab2f0836239ca207a770e2b82cf2ed0ddbfdd2285ec2e989d0f","source":{"kind":"arxiv","id":"2506.01859","version":1},"attestation_state":"computed","paper":{"title":"CONFETTI: Conversational Function-Calling Evaluation Through Turn-Level Interactions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Claudia Zaghi, James Gung, Katerina Margatina, Monica Sunkara, Raphael Shu, Tamer Alkhouli, Yi Zhang","submitted_at":"2025-06-02T16:48:11Z","abstract_excerpt":"We introduce Conversational Function-Calling Evaluation Through Turn-Level Interactions (CONFETTI), a conversational benchmark1 designed to evaluate the function-calling capabilities and response quality of large language models (LLMs). Current benchmarks lack comprehensive assessment of LLMs in complex conversational scenarios. CONFETTI addresses this gap through 109 human-simulated conversations, comprising 313 user turns and covering 86 APIs. These conversations explicitly target various conversational complexities, such as follow-ups, goal correction and switching, ambiguous and implicit g"},"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":"2506.01859","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-02T16:48:11Z","cross_cats_sorted":[],"title_canon_sha256":"30f817b01cb3285453757e5dca36e9808a292dbdfd43fd9c7067b58233b5462d","abstract_canon_sha256":"b24263f0659e6e6a511d7f9fea421b9800e6b0e409695f097d382105b4114473"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:20.510815Z","signature_b64":"3Jrv8DI8WSh9sl/Drp8oUiK3OqzTXCXt2kOymuzvv4cbT3neVfVZtUBAHXiq5KWkr0w2EPAUFK0h/dYRKM5NCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"196bd5e795196ab2f0836239ca207a770e2b82cf2ed0ddbfdd2285ec2e989d0f","last_reissued_at":"2026-07-05T11:14:20.510364Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:20.510364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CONFETTI: Conversational Function-Calling Evaluation Through Turn-Level Interactions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Claudia Zaghi, James Gung, Katerina Margatina, Monica Sunkara, Raphael Shu, Tamer Alkhouli, Yi Zhang","submitted_at":"2025-06-02T16:48:11Z","abstract_excerpt":"We introduce Conversational Function-Calling Evaluation Through Turn-Level Interactions (CONFETTI), a conversational benchmark1 designed to evaluate the function-calling capabilities and response quality of large language models (LLMs). Current benchmarks lack comprehensive assessment of LLMs in complex conversational scenarios. CONFETTI addresses this gap through 109 human-simulated conversations, comprising 313 user turns and covering 86 APIs. These conversations explicitly target various conversational complexities, such as follow-ups, goal correction and switching, ambiguous and implicit g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01859","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/2506.01859/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":"2506.01859","created_at":"2026-07-05T11:14:20.510418+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01859v1","created_at":"2026-07-05T11:14:20.510418+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01859","created_at":"2026-07-05T11:14:20.510418+00:00"},{"alias_kind":"pith_short_12","alias_value":"DFV5LZ4VDFVL","created_at":"2026-07-05T11:14:20.510418+00:00"},{"alias_kind":"pith_short_16","alias_value":"DFV5LZ4VDFVLF4ED","created_at":"2026-07-05T11:14:20.510418+00:00"},{"alias_kind":"pith_short_8","alias_value":"DFV5LZ4V","created_at":"2026-07-05T11:14:20.510418+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/DFV5LZ4VDFVLF4EDMI44UID2O4","json":"https://pith.science/pith/DFV5LZ4VDFVLF4EDMI44UID2O4.json","graph_json":"https://pith.science/api/pith-number/DFV5LZ4VDFVLF4EDMI44UID2O4/graph.json","events_json":"https://pith.science/api/pith-number/DFV5LZ4VDFVLF4EDMI44UID2O4/events.json","paper":"https://pith.science/paper/DFV5LZ4V"},"agent_actions":{"view_html":"https://pith.science/pith/DFV5LZ4VDFVLF4EDMI44UID2O4","download_json":"https://pith.science/pith/DFV5LZ4VDFVLF4EDMI44UID2O4.json","view_paper":"https://pith.science/paper/DFV5LZ4V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01859&json=true","fetch_graph":"https://pith.science/api/pith-number/DFV5LZ4VDFVLF4EDMI44UID2O4/graph.json","fetch_events":"https://pith.science/api/pith-number/DFV5LZ4VDFVLF4EDMI44UID2O4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DFV5LZ4VDFVLF4EDMI44UID2O4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DFV5LZ4VDFVLF4EDMI44UID2O4/action/storage_attestation","attest_author":"https://pith.science/pith/DFV5LZ4VDFVLF4EDMI44UID2O4/action/author_attestation","sign_citation":"https://pith.science/pith/DFV5LZ4VDFVLF4EDMI44UID2O4/action/citation_signature","submit_replication":"https://pith.science/pith/DFV5LZ4VDFVLF4EDMI44UID2O4/action/replication_record"}},"created_at":"2026-07-05T11:14:20.510418+00:00","updated_at":"2026-07-05T11:14:20.510418+00:00"}