{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:U2MNZ5MY2R4EB2XMAMSTXYHG3Z","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":"ae7a9f4aeea78b01a8253b0137a272b43d873d62392e6a373d9bee0ad5412475","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-02-04T18:39:58Z","title_canon_sha256":"88c0da02e2580274a616d441b823362083bf184ef6fe1b8f61ed0e2aa0831092"},"schema_version":"1.0","source":{"id":"2602.04853","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.04853","created_at":"2026-07-07T02:18:34Z"},{"alias_kind":"arxiv_version","alias_value":"2602.04853v2","created_at":"2026-07-07T02:18:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.04853","created_at":"2026-07-07T02:18:34Z"},{"alias_kind":"pith_short_12","alias_value":"U2MNZ5MY2R4E","created_at":"2026-07-07T02:18:34Z"},{"alias_kind":"pith_short_16","alias_value":"U2MNZ5MY2R4EB2XM","created_at":"2026-07-07T02:18:34Z"},{"alias_kind":"pith_short_8","alias_value":"U2MNZ5MY","created_at":"2026-07-07T02:18:34Z"}],"graph_snapshots":[{"event_id":"sha256:efcd4c379df63a590e95f0f197689c88a67664db166ebaa24573273d1b39106c","target":"graph","created_at":"2026-07-07T02:18:34Z","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/2602.04853/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models often struggle to recognize their knowledge limits in closed-book question answering, leading to confident hallucinations. While decomposed prompting is typically used to improve accuracy, we investigate its impact on reliability. We evaluate three task-equivalent prompting regimes: Direct, Assistive, and Incremental, across different model scales and multi-hop QA benchmarks. We find that although accuracy gains from decomposition diminish in frontier models, disagreements between prompting regimes remain highly indicative of potential errors. Because factual knowledge is","authors_text":"Dan Roth, Dhruv Madhwal, Lyuxin David Zhang, Tomer Wolfson, Vivek Gupta","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-02-04T18:39:58Z","title":"Decomposed Prompting Does Not Fix Knowledge Gaps, But Helps Models Say \"I Don't Know\""},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.04853","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:e7399fda70e1a4245e4936d34fef3d57c9066409d0c3dc323ba1b6e73d3de4a6","target":"record","created_at":"2026-07-07T02:18:34Z","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":"ae7a9f4aeea78b01a8253b0137a272b43d873d62392e6a373d9bee0ad5412475","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-02-04T18:39:58Z","title_canon_sha256":"88c0da02e2580274a616d441b823362083bf184ef6fe1b8f61ed0e2aa0831092"},"schema_version":"1.0","source":{"id":"2602.04853","kind":"arxiv","version":2}},"canonical_sha256":"a698dcf598d47840eaec03253be0e6de6768dde596694939eb61c5e5f179b67e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a698dcf598d47840eaec03253be0e6de6768dde596694939eb61c5e5f179b67e","first_computed_at":"2026-07-07T02:18:34.183544Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:18:34.183544Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KjGVCEqwkVWLF6oPlrf7geZqiaq+axowNgtu/YHUGB8nJTvCdLtjKykJlxe3asA03o4n4ubIbIwk6QHNfBGtCw==","signature_status":"signed_v1","signed_at":"2026-07-07T02:18:34.184642Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.04853","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e7399fda70e1a4245e4936d34fef3d57c9066409d0c3dc323ba1b6e73d3de4a6","sha256:efcd4c379df63a590e95f0f197689c88a67664db166ebaa24573273d1b39106c"],"state_sha256":"659d7a1c0cb9eb316af8e5142b1cd05042a3b4175d581b1a89388cb3a8a55bee"}