{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YOSF547IIPN4WTGWEVOA2WM777","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":"693cc7bd822fa027a0216bbc27f8e2cad30cf2b70cdc18288dad73810d5a94a7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-29T03:29:24Z","title_canon_sha256":"1876ea3cdadd367a70f20ae235f009299e38c7976602a79d4fe8ef50ece8d788"},"schema_version":"1.0","source":{"id":"2501.17399","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.17399","created_at":"2026-07-05T10:25:16Z"},{"alias_kind":"arxiv_version","alias_value":"2501.17399v2","created_at":"2026-07-05T10:25:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.17399","created_at":"2026-07-05T10:25:16Z"},{"alias_kind":"pith_short_12","alias_value":"YOSF547IIPN4","created_at":"2026-07-05T10:25:16Z"},{"alias_kind":"pith_short_16","alias_value":"YOSF547IIPN4WTGW","created_at":"2026-07-05T10:25:16Z"},{"alias_kind":"pith_short_8","alias_value":"YOSF547I","created_at":"2026-07-05T10:25:16Z"}],"graph_snapshots":[{"event_id":"sha256:1284d0d26e5dec31d132ae52502143856197030305a512374b7fdcad764b0b87","target":"graph","created_at":"2026-07-05T10:25:16Z","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/2501.17399/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present MultiChallenge, a pioneering benchmark evaluating large language models (LLMs) on conducting multi-turn conversations with human users, a crucial yet underexamined capability for their applications. MultiChallenge identifies four categories of challenges in multi-turn conversations that are not only common and realistic among current human-LLM interactions, but are also challenging to all current frontier LLMs. All 4 challenges require accurate instruction-following, context allocation, and in-context reasoning at the same time. We also develop LLM as judge with instance-level rubri","authors_text":"Chen Xing, Dean Lee, Ed-Yeremai Cardona, Jeremy Kritz, Johannes Mols, Kaustubh Deshpande, Lifeng Jin, Summer Yue, Ved Sirdeshmukh, Willow Primack","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-29T03:29:24Z","title":"MultiChallenge: A Realistic Multi-Turn Conversation Evaluation Benchmark Challenging to Frontier LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.17399","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":"sha256:16e3aec608204e865906ec4f46eb6549ba5120da08c44e844e35e04bcfb90ea6","target":"record","created_at":"2026-07-05T10:25:16Z","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":"693cc7bd822fa027a0216bbc27f8e2cad30cf2b70cdc18288dad73810d5a94a7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-29T03:29:24Z","title_canon_sha256":"1876ea3cdadd367a70f20ae235f009299e38c7976602a79d4fe8ef50ece8d788"},"schema_version":"1.0","source":{"id":"2501.17399","kind":"arxiv","version":2}},"canonical_sha256":"c3a45ef3e843dbcb4cd6255c0d599fffe5111c4867ff091b745e516b4ddc9c15","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c3a45ef3e843dbcb4cd6255c0d599fffe5111c4867ff091b745e516b4ddc9c15","first_computed_at":"2026-07-05T10:25:16.631098Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:25:16.631098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XcchUoCWqf8WCcN3EO8R4g06Mq4rTWwvtfzEtqlNDIwgWfsltnFTKi227o03weOIDv0apbtwlaZ1GNyrpsyiBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:25:16.631767Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.17399","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16e3aec608204e865906ec4f46eb6549ba5120da08c44e844e35e04bcfb90ea6","sha256:1284d0d26e5dec31d132ae52502143856197030305a512374b7fdcad764b0b87"],"state_sha256":"5796e44828ad0ab5a9ad42dc6d2b206b5cc19ecf399f6d18f451a0ad70485a38"}