{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GN6CNVM2F6A6LOYAZ6VZ5KNTQ2","short_pith_number":"pith:GN6CNVM2","canonical_record":{"source":{"id":"2410.05434","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-07T18:55:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6d011a5df2f7c5bb821288a2df20b2f58cb7e29d132226e638dd319898a770f2","abstract_canon_sha256":"ed54c75195ee4ff4c21cc38134058c7befb8d9e51d61d254b3c8736425425960"},"schema_version":"1.0"},"canonical_sha256":"337c26d59a2f81e5bb00cfab9ea9b386ae0ae36000604086aa5c36d447f795cd","source":{"kind":"arxiv","id":"2410.05434","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.05434","created_at":"2026-07-05T09:17:19Z"},{"alias_kind":"arxiv_version","alias_value":"2410.05434v1","created_at":"2026-07-05T09:17:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.05434","created_at":"2026-07-05T09:17:19Z"},{"alias_kind":"pith_short_12","alias_value":"GN6CNVM2F6A6","created_at":"2026-07-05T09:17:19Z"},{"alias_kind":"pith_short_16","alias_value":"GN6CNVM2F6A6LOYA","created_at":"2026-07-05T09:17:19Z"},{"alias_kind":"pith_short_8","alias_value":"GN6CNVM2","created_at":"2026-07-05T09:17:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GN6CNVM2F6A6LOYAZ6VZ5KNTQ2","target":"record","payload":{"canonical_record":{"source":{"id":"2410.05434","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-07T18:55:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6d011a5df2f7c5bb821288a2df20b2f58cb7e29d132226e638dd319898a770f2","abstract_canon_sha256":"ed54c75195ee4ff4c21cc38134058c7befb8d9e51d61d254b3c8736425425960"},"schema_version":"1.0"},"canonical_sha256":"337c26d59a2f81e5bb00cfab9ea9b386ae0ae36000604086aa5c36d447f795cd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:17:19.169816Z","signature_b64":"YgKFmm4iY/EpCZJjNx9yAj7CbqeOQXDQS94KGb8Y+JROrNsD8VJS0T45vkcMA5iKW/PHM/tnsGrgjxvyV0bSAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"337c26d59a2f81e5bb00cfab9ea9b386ae0ae36000604086aa5c36d447f795cd","last_reissued_at":"2026-07-05T09:17:19.169335Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:17:19.169335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.05434","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:17:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zqdpYq+YibKJlyNEAITXirJSi90r92YgSFsdB0w5xgTtrldPS516ZaqPNcwQLKy6KMBog4x03IF8Z7yJFLXpCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T10:18:01.029518Z"},"content_sha256":"ee86d6bd55fcb0bcc4651a075654c5399393f13395e7077e93ef6ebed00bbfdb","schema_version":"1.0","event_id":"sha256:ee86d6bd55fcb0bcc4651a075654c5399393f13395e7077e93ef6ebed00bbfdb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GN6CNVM2F6A6LOYAZ6VZ5KNTQ2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Better than Your Teacher: LLM Agents that learn from Privileged AI Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Paloma Sodhi, Sanjiban Choudhury","submitted_at":"2024-10-07T18:55:53Z","abstract_excerpt":"While large language models (LLMs) show impressive decision-making abilities, current methods lack a mechanism for automatic self-improvement from errors during task execution. We propose LEAP, an iterative fine-tuning framework that continually improves LLM agents using feedback from AI expert teachers. Our key insight is to equip the expert teachers with a privileged state -- information that is available during training but hidden at test time. This allows even weak experts to provide precise guidance, significantly improving the student agent's performance without access to privileged info"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.05434","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.05434/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:17:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vww7fLfGprP1xgUP0kPQr2JjCFjuGcYHoXvzZL0J8NrDhihIt1FzE/cx7er7NRRDun8Y2f5djQ68ZfJhil6hDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T10:18:01.029999Z"},"content_sha256":"cb89b8e6ddb044d7a26e9855037133eafb2650d9eda4955cfc75b6b8e96c2b66","schema_version":"1.0","event_id":"sha256:cb89b8e6ddb044d7a26e9855037133eafb2650d9eda4955cfc75b6b8e96c2b66"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GN6CNVM2F6A6LOYAZ6VZ5KNTQ2/bundle.json","state_url":"https://pith.science/pith/GN6CNVM2F6A6LOYAZ6VZ5KNTQ2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GN6CNVM2F6A6LOYAZ6VZ5KNTQ2/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-15T10:18:01Z","links":{"resolver":"https://pith.science/pith/GN6CNVM2F6A6LOYAZ6VZ5KNTQ2","bundle":"https://pith.science/pith/GN6CNVM2F6A6LOYAZ6VZ5KNTQ2/bundle.json","state":"https://pith.science/pith/GN6CNVM2F6A6LOYAZ6VZ5KNTQ2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GN6CNVM2F6A6LOYAZ6VZ5KNTQ2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GN6CNVM2F6A6LOYAZ6VZ5KNTQ2","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":"ed54c75195ee4ff4c21cc38134058c7befb8d9e51d61d254b3c8736425425960","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-07T18:55:53Z","title_canon_sha256":"6d011a5df2f7c5bb821288a2df20b2f58cb7e29d132226e638dd319898a770f2"},"schema_version":"1.0","source":{"id":"2410.05434","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.05434","created_at":"2026-07-05T09:17:19Z"},{"alias_kind":"arxiv_version","alias_value":"2410.05434v1","created_at":"2026-07-05T09:17:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.05434","created_at":"2026-07-05T09:17:19Z"},{"alias_kind":"pith_short_12","alias_value":"GN6CNVM2F6A6","created_at":"2026-07-05T09:17:19Z"},{"alias_kind":"pith_short_16","alias_value":"GN6CNVM2F6A6LOYA","created_at":"2026-07-05T09:17:19Z"},{"alias_kind":"pith_short_8","alias_value":"GN6CNVM2","created_at":"2026-07-05T09:17:19Z"}],"graph_snapshots":[{"event_id":"sha256:cb89b8e6ddb044d7a26e9855037133eafb2650d9eda4955cfc75b6b8e96c2b66","target":"graph","created_at":"2026-07-05T09:17:19Z","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/2410.05434/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While large language models (LLMs) show impressive decision-making abilities, current methods lack a mechanism for automatic self-improvement from errors during task execution. We propose LEAP, an iterative fine-tuning framework that continually improves LLM agents using feedback from AI expert teachers. Our key insight is to equip the expert teachers with a privileged state -- information that is available during training but hidden at test time. This allows even weak experts to provide precise guidance, significantly improving the student agent's performance without access to privileged info","authors_text":"Paloma Sodhi, Sanjiban Choudhury","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-07T18:55:53Z","title":"Better than Your Teacher: LLM Agents that learn from Privileged AI Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.05434","kind":"arxiv","version":1},"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:ee86d6bd55fcb0bcc4651a075654c5399393f13395e7077e93ef6ebed00bbfdb","target":"record","created_at":"2026-07-05T09:17:19Z","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":"ed54c75195ee4ff4c21cc38134058c7befb8d9e51d61d254b3c8736425425960","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-07T18:55:53Z","title_canon_sha256":"6d011a5df2f7c5bb821288a2df20b2f58cb7e29d132226e638dd319898a770f2"},"schema_version":"1.0","source":{"id":"2410.05434","kind":"arxiv","version":1}},"canonical_sha256":"337c26d59a2f81e5bb00cfab9ea9b386ae0ae36000604086aa5c36d447f795cd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"337c26d59a2f81e5bb00cfab9ea9b386ae0ae36000604086aa5c36d447f795cd","first_computed_at":"2026-07-05T09:17:19.169335Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:17:19.169335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YgKFmm4iY/EpCZJjNx9yAj7CbqeOQXDQS94KGb8Y+JROrNsD8VJS0T45vkcMA5iKW/PHM/tnsGrgjxvyV0bSAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:17:19.169816Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.05434","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee86d6bd55fcb0bcc4651a075654c5399393f13395e7077e93ef6ebed00bbfdb","sha256:cb89b8e6ddb044d7a26e9855037133eafb2650d9eda4955cfc75b6b8e96c2b66"],"state_sha256":"9c5e9724f18d8f762c0fc28b1f9d9f822facc5d2123b916f281c7f0856406b50"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bO20tUrXKNf+aTHDrJFVgUMZ8o8XtC97s2jBVMncE8ULMx6Ibdg66qIb4FCpTTamDGNBfzHuZqP4v/2LRz9yBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T10:18:01.034674Z","bundle_sha256":"bca119f0b904386ab5a6b299b743d1f5f664ffb447dedc8e9490f0b47b335e70"}}