{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:B6NTKMESZK3HQCLUUPWGK6OWS6","short_pith_number":"pith:B6NTKMES","schema_version":"1.0","canonical_sha256":"0f9b353092cab6780974a3ec6579d697a89708cbfa3d6496a5b9157e6260239a","source":{"kind":"arxiv","id":"2506.22853","version":2},"attestation_state":"computed","paper":{"title":"DICE-BENCH: Evaluating the Tool-Use Capabilities of Large Language Models in Multi-Round, Multi-Party Dialogues","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bongwon Suh, Donghyeon Lee, Dongseok Heo, Kyochul Jang, Kyusik Kim, Taewhoo Lee, Woojeong Kim","submitted_at":"2025-06-28T11:28:04Z","abstract_excerpt":"Existing function-calling benchmarks focus on single-turn interactions. However, they overlook the complexity of real-world scenarios. To quantify how existing benchmarks address practical applications, we introduce DICE-SCORE, a metric that evaluates the dispersion of tool-related information such as function name and parameter values throughout the dialogue. Analyzing existing benchmarks through DICE-SCORE reveals notably low scores, highlighting the need for more realistic scenarios. To address this gap, we present DICE-BENCH, a framework that constructs practical function-calling datasets "},"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":"2506.22853","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-28T11:28:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d721f9f3b9136787c287e204b1e157d6146ca7d96d690039dfbedc933f1cbab9","abstract_canon_sha256":"a301ce441364810d1a60e3104cc2ed2626db445fe222badb978e7735eda9348f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:45.663479Z","signature_b64":"+yuJFYM65pYo4oTDD+/rwRgDxbDTpBrikKNOZShHvrpcnhD4Otr2X9+0d9vR0w8ZILROV3dipx8G4KhlKXsxDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f9b353092cab6780974a3ec6579d697a89708cbfa3d6496a5b9157e6260239a","last_reissued_at":"2026-07-05T11:30:45.662961Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:45.662961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DICE-BENCH: Evaluating the Tool-Use Capabilities of Large Language Models in Multi-Round, Multi-Party Dialogues","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bongwon Suh, Donghyeon Lee, Dongseok Heo, Kyochul Jang, Kyusik Kim, Taewhoo Lee, Woojeong Kim","submitted_at":"2025-06-28T11:28:04Z","abstract_excerpt":"Existing function-calling benchmarks focus on single-turn interactions. However, they overlook the complexity of real-world scenarios. To quantify how existing benchmarks address practical applications, we introduce DICE-SCORE, a metric that evaluates the dispersion of tool-related information such as function name and parameter values throughout the dialogue. Analyzing existing benchmarks through DICE-SCORE reveals notably low scores, highlighting the need for more realistic scenarios. To address this gap, we present DICE-BENCH, a framework that constructs practical function-calling datasets "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.22853","kind":"arxiv","version":2},"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/2506.22853/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":"2506.22853","created_at":"2026-07-05T11:30:45.663022+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.22853v2","created_at":"2026-07-05T11:30:45.663022+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.22853","created_at":"2026-07-05T11:30:45.663022+00:00"},{"alias_kind":"pith_short_12","alias_value":"B6NTKMESZK3H","created_at":"2026-07-05T11:30:45.663022+00:00"},{"alias_kind":"pith_short_16","alias_value":"B6NTKMESZK3HQCLU","created_at":"2026-07-05T11:30:45.663022+00:00"},{"alias_kind":"pith_short_8","alias_value":"B6NTKMES","created_at":"2026-07-05T11:30:45.663022+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/B6NTKMESZK3HQCLUUPWGK6OWS6","json":"https://pith.science/pith/B6NTKMESZK3HQCLUUPWGK6OWS6.json","graph_json":"https://pith.science/api/pith-number/B6NTKMESZK3HQCLUUPWGK6OWS6/graph.json","events_json":"https://pith.science/api/pith-number/B6NTKMESZK3HQCLUUPWGK6OWS6/events.json","paper":"https://pith.science/paper/B6NTKMES"},"agent_actions":{"view_html":"https://pith.science/pith/B6NTKMESZK3HQCLUUPWGK6OWS6","download_json":"https://pith.science/pith/B6NTKMESZK3HQCLUUPWGK6OWS6.json","view_paper":"https://pith.science/paper/B6NTKMES","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.22853&json=true","fetch_graph":"https://pith.science/api/pith-number/B6NTKMESZK3HQCLUUPWGK6OWS6/graph.json","fetch_events":"https://pith.science/api/pith-number/B6NTKMESZK3HQCLUUPWGK6OWS6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B6NTKMESZK3HQCLUUPWGK6OWS6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B6NTKMESZK3HQCLUUPWGK6OWS6/action/storage_attestation","attest_author":"https://pith.science/pith/B6NTKMESZK3HQCLUUPWGK6OWS6/action/author_attestation","sign_citation":"https://pith.science/pith/B6NTKMESZK3HQCLUUPWGK6OWS6/action/citation_signature","submit_replication":"https://pith.science/pith/B6NTKMESZK3HQCLUUPWGK6OWS6/action/replication_record"}},"created_at":"2026-07-05T11:30:45.663022+00:00","updated_at":"2026-07-05T11:30:45.663022+00:00"}