{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6JH2K3KUV5BA4J343RCL6EKMTN","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":"34b1d3d9b621688ec3c358e91c3c316f3f4eb35bb8e7a903f6e7ed796c1da760","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-15T17:53:47Z","title_canon_sha256":"3864d7174f5291b18cca72e450cd6fa9548c450a234180af0b8424a82d03d0a3"},"schema_version":"1.0","source":{"id":"2505.10543","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.10543","created_at":"2026-07-05T11:51:26Z"},{"alias_kind":"arxiv_version","alias_value":"2505.10543v2","created_at":"2026-07-05T11:51:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.10543","created_at":"2026-07-05T11:51:26Z"},{"alias_kind":"pith_short_12","alias_value":"6JH2K3KUV5BA","created_at":"2026-07-05T11:51:26Z"},{"alias_kind":"pith_short_16","alias_value":"6JH2K3KUV5BA4J34","created_at":"2026-07-05T11:51:26Z"},{"alias_kind":"pith_short_8","alias_value":"6JH2K3KU","created_at":"2026-07-05T11:51:26Z"}],"graph_snapshots":[{"event_id":"sha256:302f06f245f4a2fbd590cbcc48cdfde4a1ce20408595cf49360460d60e7d2b64","target":"graph","created_at":"2026-07-05T11:51:26Z","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/2505.10543/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models excel on static benchmarks, but their ability as self-learning agents in dynamic environments remains unclear. We evaluate three prompting strategies: self-reflection, heuristic mutation, and planning across dynamic tasks with open-source models. We find that larger models generally outperform smaller ones, but that strategic prompting can close this performance gap. Second, an overly long prompt can negatively impact smaller models on basic reactive tasks, while larger models show more robust behaviour. Third, advanced prompting techniques primarily benefit smaller model","authors_text":"Anna V. Kononova, Annie Wong, Aske Plaat, Niki van Stein, Thomas B\\\"ack","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-15T17:53:47Z","title":"Reasoning Capabilities of Large Language Models on Dynamic Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.10543","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":"sha256:2ead80b939fba74aaf527229c661d0a72810078adc4771f49f22b9ec896dae46","target":"record","created_at":"2026-07-05T11:51:26Z","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":"34b1d3d9b621688ec3c358e91c3c316f3f4eb35bb8e7a903f6e7ed796c1da760","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-15T17:53:47Z","title_canon_sha256":"3864d7174f5291b18cca72e450cd6fa9548c450a234180af0b8424a82d03d0a3"},"schema_version":"1.0","source":{"id":"2505.10543","kind":"arxiv","version":2}},"canonical_sha256":"f24fa56d54af420e277cdc44bf114c9b7a18dbb065abda6e9893a310bd18eb76","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f24fa56d54af420e277cdc44bf114c9b7a18dbb065abda6e9893a310bd18eb76","first_computed_at":"2026-07-05T11:51:26.991809Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:51:26.991809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j6xviOj/sBe/chf6mx4KrBOoshpVG4m+1YMkuUHn6AT4mPWDJLjZ0KijCz78+TmS0tfe9xqbNnzy1A+7VM0KBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:51:26.992376Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.10543","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2ead80b939fba74aaf527229c661d0a72810078adc4771f49f22b9ec896dae46","sha256:302f06f245f4a2fbd590cbcc48cdfde4a1ce20408595cf49360460d60e7d2b64"],"state_sha256":"938ff15bfb65d8db00492e680f115decf52c7042d65d2bdab4bcaa8aa3585843"}