{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WOXYTTAQMZUNXQW4AFQJ3TDAZL","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":"561eee3c43dce1bf8bde0d3374668683d2fdd0c27823e477630dfa313870c259","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-30T17:52:36Z","title_canon_sha256":"0979da4599177840ce2e5b049399fd17e310c67e3bd869fa729787caaa23b039"},"schema_version":"1.0","source":{"id":"2405.20309","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.20309","created_at":"2026-07-05T09:14:33Z"},{"alias_kind":"arxiv_version","alias_value":"2405.20309v2","created_at":"2026-07-05T09:14:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20309","created_at":"2026-07-05T09:14:33Z"},{"alias_kind":"pith_short_12","alias_value":"WOXYTTAQMZUN","created_at":"2026-07-05T09:14:33Z"},{"alias_kind":"pith_short_16","alias_value":"WOXYTTAQMZUNXQW4","created_at":"2026-07-05T09:14:33Z"},{"alias_kind":"pith_short_8","alias_value":"WOXYTTAQ","created_at":"2026-07-05T09:14:33Z"}],"graph_snapshots":[{"event_id":"sha256:67b58b19da0a58353477b857abe9510c9044c08f05603b1089b406c486c09a6e","target":"graph","created_at":"2026-07-05T09:14:33Z","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/2405.20309/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training models to act as agents that can effectively navigate and perform actions in a complex environment, such as a web browser, has typically been challenging due to lack of training data. Large language models (LLMs) have recently demonstrated some capability to navigate novel environments as agents in a zero-shot or few-shot fashion, purely guided by natural language instructions as prompts. Recent research has also demonstrated LLMs have the capability to exceed their base performance through self-improvement, i.e. fine-tuning on data generated by the model itself. In this work, we expl","authors_text":"Ajay Patel, Chris Callison-Burch, Claudiu Leoveanu-Condrei, Marius-Constantin Dinu, Markus Hofmarcher, Sepp Hochreiter","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-30T17:52:36Z","title":"Large Language Models Can Self-Improve At Web Agent Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20309","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:b4bfd1c731d7e112e421e8b79c9f9a0c92a44016bfa314b36ebfdff3369cf045","target":"record","created_at":"2026-07-05T09:14:33Z","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":"561eee3c43dce1bf8bde0d3374668683d2fdd0c27823e477630dfa313870c259","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-30T17:52:36Z","title_canon_sha256":"0979da4599177840ce2e5b049399fd17e310c67e3bd869fa729787caaa23b039"},"schema_version":"1.0","source":{"id":"2405.20309","kind":"arxiv","version":2}},"canonical_sha256":"b3af89cc106668dbc2dc01609dcc60cafc0b6cb464f1ed643c8adb885e550096","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b3af89cc106668dbc2dc01609dcc60cafc0b6cb464f1ed643c8adb885e550096","first_computed_at":"2026-07-05T09:14:33.762491Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:14:33.762491Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9wAo7stGTAZGNIpI9coOpr6OG2OBTbSDq0c4u3qqN2OWjbWBaPRUw+a9SpTq+Az1b1beiJc0ujIR24lVzvrjBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:14:33.763029Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.20309","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b4bfd1c731d7e112e421e8b79c9f9a0c92a44016bfa314b36ebfdff3369cf045","sha256:67b58b19da0a58353477b857abe9510c9044c08f05603b1089b406c486c09a6e"],"state_sha256":"7e361488aef4786c17b65c83a6faae80b779815e3442b6873238a0eb13481484"}