{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KAFUXR4A2I2D4VVN2GDMZHQJNW","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":"4107e26d678b39c880178c4abfb9816d052787481783ae1c8bba226d49c8574c","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-12T04:35:02Z","title_canon_sha256":"2d35fed922642af0a3900df2a1d4174ccba488d94239df71f38df40e9cc37036"},"schema_version":"1.0","source":{"id":"2506.10341","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.10341","created_at":"2026-06-09T01:05:07Z"},{"alias_kind":"arxiv_version","alias_value":"2506.10341v2","created_at":"2026-06-09T01:05:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.10341","created_at":"2026-06-09T01:05:07Z"},{"alias_kind":"pith_short_12","alias_value":"KAFUXR4A2I2D","created_at":"2026-06-09T01:05:07Z"},{"alias_kind":"pith_short_16","alias_value":"KAFUXR4A2I2D4VVN","created_at":"2026-06-09T01:05:07Z"},{"alias_kind":"pith_short_8","alias_value":"KAFUXR4A","created_at":"2026-06-09T01:05:07Z"}],"graph_snapshots":[{"event_id":"sha256:70972c550ca7b496784c4bb32efb5cf871ccdc3e287264f0c22743c2f57bf612","target":"graph","created_at":"2026-06-09T01:05:07Z","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/2506.10341/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Interactively learning from observation and language feedback is an increasingly studied area driven by the emergence of large language model (LLM) agents. Despite impressive empirical demonstrations, so far a principled framing of these decision problems remains lacking. We formalize the Learning from Language Feedback (LLF) problem, assert sufficient assumptions to enable learning despite latent rewards, and introduce $\\textit{transfer eluder dimension}$ as a measure to characterize the hardness of LLF. We formalize the intuition that information in the language feedback governs the learning","authors_text":"Adith Swaminathan, Aditya Modi, Allen Nie, Ching-An Cheng, Ruijie Zheng, Wanqiao Xu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-12T04:35:02Z","title":"Formalizing Learning from Language Feedback with Provable Guarantees"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.10341","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":"sha256:5a0105932b55a3d40642157175c2a478d940f8ce9c0b133ff411f8898fdcf21e","target":"record","created_at":"2026-06-09T01:05:07Z","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":"4107e26d678b39c880178c4abfb9816d052787481783ae1c8bba226d49c8574c","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-12T04:35:02Z","title_canon_sha256":"2d35fed922642af0a3900df2a1d4174ccba488d94239df71f38df40e9cc37036"},"schema_version":"1.0","source":{"id":"2506.10341","kind":"arxiv","version":2}},"canonical_sha256":"500b4bc780d2343e56add186cc9e096d95084e8abbce7c182ac7501f1ecedbfd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"500b4bc780d2343e56add186cc9e096d95084e8abbce7c182ac7501f1ecedbfd","first_computed_at":"2026-06-09T01:05:07.148466Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:05:07.148466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BrNcIsenUUC1pfL4dVlwJt6DIslCM2cQGV9a9zmFCQD76/rQPh3zycMNWD3grgethMph3m/vb64Eu2y+mYSvBA==","signature_status":"signed_v1","signed_at":"2026-06-09T01:05:07.149285Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.10341","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a0105932b55a3d40642157175c2a478d940f8ce9c0b133ff411f8898fdcf21e","sha256:70972c550ca7b496784c4bb32efb5cf871ccdc3e287264f0c22743c2f57bf612"],"state_sha256":"44b292f734eaa09d4c1c0ef415efc855a8afe84199ff3622dd8f522f87daa18b"}