{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RGTYIUX6SDCCBDTWR5FODQZSZA","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":"8f05937173ba352343fda78f10837f8973ea25538f83c78afe4f066191d1dc90","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-14T18:59:33Z","title_canon_sha256":"6a50b71107dde463063ff994ff6b0dde735305a201bc1b15024ba18029569de2"},"schema_version":"1.0","source":{"id":"2402.09404","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.09404","created_at":"2026-07-05T11:24:51Z"},{"alias_kind":"arxiv_version","alias_value":"2402.09404v2","created_at":"2026-07-05T11:24:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09404","created_at":"2026-07-05T11:24:51Z"},{"alias_kind":"pith_short_12","alias_value":"RGTYIUX6SDCC","created_at":"2026-07-05T11:24:51Z"},{"alias_kind":"pith_short_16","alias_value":"RGTYIUX6SDCCBDTW","created_at":"2026-07-05T11:24:51Z"},{"alias_kind":"pith_short_8","alias_value":"RGTYIUX6","created_at":"2026-07-05T11:24:51Z"}],"graph_snapshots":[{"event_id":"sha256:17c367dfa0050e062ebbaeaa25dd3249184a8862193fef01c5c80823ca6df51f","target":"graph","created_at":"2026-07-05T11:24:51Z","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/2402.09404/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces AQA-Bench, a novel benchmark to assess the sequential reasoning capabilities of large language models (LLMs) in algorithmic contexts, such as depth-first search (DFS). The key feature of our evaluation benchmark lies in its interactive evaluation protocol - for example, in DFS, the availability of each node's connected edge is contingent upon the model's traversal to that node, thereby necessitating the LLM's ability to effectively remember visited nodes and strategize subsequent moves considering the possible environmental feedback in the future steps. We comprehensively","authors_text":"Bingchen Zhao, Cihang Xie, Siwei Yang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-14T18:59:33Z","title":"AQA-Bench: An Interactive Benchmark for Evaluating LLMs' Sequential Reasoning Ability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09404","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":"sha256:2ed325f11c0f93cfee138bccb1c0b22248db96ee98a808f5d76833a42d921a9a","target":"record","created_at":"2026-07-05T11:24:51Z","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":"8f05937173ba352343fda78f10837f8973ea25538f83c78afe4f066191d1dc90","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-14T18:59:33Z","title_canon_sha256":"6a50b71107dde463063ff994ff6b0dde735305a201bc1b15024ba18029569de2"},"schema_version":"1.0","source":{"id":"2402.09404","kind":"arxiv","version":2}},"canonical_sha256":"89a78452fe90c4208e768f4ae1c332c802a98a778fbb0cea29c5216a708093b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89a78452fe90c4208e768f4ae1c332c802a98a778fbb0cea29c5216a708093b7","first_computed_at":"2026-07-05T11:24:51.193088Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:24:51.193088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K9ACeB1L+CrAa2Vo1nDyKcsU2URg8Sscq0Z4UFr4SOtue+o24HGASKa/Cl/jfjjUc0wspULxIaJCuC2avKx3Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:24:51.193603Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.09404","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2ed325f11c0f93cfee138bccb1c0b22248db96ee98a808f5d76833a42d921a9a","sha256:17c367dfa0050e062ebbaeaa25dd3249184a8862193fef01c5c80823ca6df51f"],"state_sha256":"355ecd85f9dfa290a3672534075a7275eb283cb859528272c18dd07aa7601988"}