{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7LA3PIOHUCILP7YFZJAENBEFAQ","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":"9354e87c57c0e2285a74c7e44fb620806771483f427793fd8c38e438ec47dad7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-25T04:07:44Z","title_canon_sha256":"081fcf6672785e2e5ed84e637c9c9895cd1d22baa797490e0adef63821212f8a"},"schema_version":"1.0","source":{"id":"2605.26172","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.26172","created_at":"2026-05-27T00:04:27Z"},{"alias_kind":"arxiv_version","alias_value":"2605.26172v1","created_at":"2026-05-27T00:04:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26172","created_at":"2026-05-27T00:04:27Z"},{"alias_kind":"pith_short_12","alias_value":"7LA3PIOHUCIL","created_at":"2026-05-27T00:04:27Z"},{"alias_kind":"pith_short_16","alias_value":"7LA3PIOHUCILP7YF","created_at":"2026-05-27T00:04:27Z"},{"alias_kind":"pith_short_8","alias_value":"7LA3PIOH","created_at":"2026-05-27T00:04:27Z"}],"graph_snapshots":[{"event_id":"sha256:b94b976b2e21639358397e4845915e7dc7dd149f4b63ddcbd0ad428d0be96b36","target":"graph","created_at":"2026-05-27T00:04:27Z","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/2605.26172/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"When language models use test-time sampling, they generate multiple reasoning trajectories and select an answer by majority vote. We show that these trajectories are not independent: for a given question, they concentrate into a small number of clusters, or reasoning basins, each defined by a normalized final answer and the solutions that reach it. A majority vote therefore selects the most stable basin rather than the most accurate one, which creates wrong-majority failures where the correct answer is present but outvoted. We introduce ARBITER, a model-agnostic approach that models interactio","authors_text":"Farhana Choudhury, Lars Kulik, Meng Cai","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-25T04:07:44Z","title":"ARBITER: Reasoning Trajectory Basins and Majority Vote Failures in Test-Time Sampling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26172","kind":"arxiv","version":1},"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":"sha256:02ec7ebfd6072d210f17818feeaa56ff7fadc3980c8ebfdbce445f78e7bf350d","target":"record","created_at":"2026-05-27T00:04:27Z","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":"9354e87c57c0e2285a74c7e44fb620806771483f427793fd8c38e438ec47dad7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-25T04:07:44Z","title_canon_sha256":"081fcf6672785e2e5ed84e637c9c9895cd1d22baa797490e0adef63821212f8a"},"schema_version":"1.0","source":{"id":"2605.26172","kind":"arxiv","version":1}},"canonical_sha256":"fac1b7a1c7a090b7ff05ca404684850420b2228efc60b4c8ae911cef38ce23b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fac1b7a1c7a090b7ff05ca404684850420b2228efc60b4c8ae911cef38ce23b3","first_computed_at":"2026-05-27T00:04:27.263218Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T00:04:27.263218Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MrBHxD+eI17vUxcOxW3SWkYyTZE0hxX321poY/iXhCbosvGdLopx9CjAm9jqS1as0Y1wmLgaq3uJyM3qYbVTAA==","signature_status":"signed_v1","signed_at":"2026-05-27T00:04:27.264027Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.26172","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:02ec7ebfd6072d210f17818feeaa56ff7fadc3980c8ebfdbce445f78e7bf350d","sha256:b94b976b2e21639358397e4845915e7dc7dd149f4b63ddcbd0ad428d0be96b36"],"state_sha256":"2b414ed9c93b82faede3dc5e407c08bdc9fc32a9e46ebb44e6f91d8edad178ad"}