{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6VLRKYZOS2PQKWZLESMOYDW7KL","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":"693f52f8a48017e28f08a061f26a7c9ffcc2cddf7ff4bb43e1e78ed268ad685f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-12-11T21:49:04Z","title_canon_sha256":"21b4b961c161f9766800f7ade168301177499c9226eb506352d631f5b264ba39"},"schema_version":"1.0","source":{"id":"2312.06853","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.06853","created_at":"2026-07-05T07:23:32Z"},{"alias_kind":"arxiv_version","alias_value":"2312.06853v2","created_at":"2026-07-05T07:23:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.06853","created_at":"2026-07-05T07:23:32Z"},{"alias_kind":"pith_short_12","alias_value":"6VLRKYZOS2PQ","created_at":"2026-07-05T07:23:32Z"},{"alias_kind":"pith_short_16","alias_value":"6VLRKYZOS2PQKWZL","created_at":"2026-07-05T07:23:32Z"},{"alias_kind":"pith_short_8","alias_value":"6VLRKYZO","created_at":"2026-07-05T07:23:32Z"}],"graph_snapshots":[{"event_id":"sha256:5a7b6ca44bdd1e673467e7db20a8e48c2d0f40f0beb922113f64ef663c8272da","target":"graph","created_at":"2026-07-05T07:23:32Z","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/2312.06853/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a new benchmark, LLF-Bench (Learning from Language Feedback Benchmark; pronounced as \"elf-bench\"), to evaluate the ability of AI agents to interactively learn from natural language feedback and instructions. Learning from language feedback (LLF) is essential for people, largely because the rich information this feedback provides can help a learner avoid much of trial and error and thereby speed up the learning process. Large Language Models (LLMs) have recently enabled AI agents to comprehend natural language -- and hence AI agents can potentially benefit from language feedback du","authors_text":"Adith Swaminathan, Allen Nie, Andrey Kolobov, Ching-An Cheng, Dipendra Misra","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-12-11T21:49:04Z","title":"LLF-Bench: Benchmark for Interactive Learning from Language Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.06853","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":"sha256:9ff7d1ca8941c2a4fe9800b8619165d8fb09fbac72e4c2d401e1da48fbd23c6c","target":"record","created_at":"2026-07-05T07:23:32Z","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":"693f52f8a48017e28f08a061f26a7c9ffcc2cddf7ff4bb43e1e78ed268ad685f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-12-11T21:49:04Z","title_canon_sha256":"21b4b961c161f9766800f7ade168301177499c9226eb506352d631f5b264ba39"},"schema_version":"1.0","source":{"id":"2312.06853","kind":"arxiv","version":2}},"canonical_sha256":"f55715632e969f055b2b2498ec0edf52f14ddf6f0a568b3bfd8a96135140f4a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f55715632e969f055b2b2498ec0edf52f14ddf6f0a568b3bfd8a96135140f4a3","first_computed_at":"2026-07-05T07:23:32.126561Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:23:32.126561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x3KqLT5+Xv21c6tKjCfuzomswV5CWqfiLlqRV4OxmK+1jrJ1cz0xFSwM8QztlQv4wmchCkuUJUYtteG0/QfOBg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:23:32.127034Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.06853","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9ff7d1ca8941c2a4fe9800b8619165d8fb09fbac72e4c2d401e1da48fbd23c6c","sha256:5a7b6ca44bdd1e673467e7db20a8e48c2d0f40f0beb922113f64ef663c8272da"],"state_sha256":"04927c19f72f8261ff1b8118b54e5e3f3d91a102f356f9b8f87f6c102d666812"}