{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:JPSVGONLMIUEFEPCAQKOAZ76EZ","short_pith_number":"pith:JPSVGONL","canonical_record":{"source":{"id":"2305.10314","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-17T15:53:31Z","cross_cats_sorted":["cs.AI","cs.SE"],"title_canon_sha256":"2a871d937a4d6aad3fdbb8ee8c8f72ce72a91dd3f3b2f70b0d63b1c7b5925743","abstract_canon_sha256":"4a9194e173c28da0976b884ef0d63b0697e3e2502b7cafbdbf1f5f4bc0005b54"},"schema_version":"1.0"},"canonical_sha256":"4be55339ab62284291e20414e067fe267eb9528410b11137f893810806ea25a8","source":{"kind":"arxiv","id":"2305.10314","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.10314","created_at":"2026-07-05T07:57:40Z"},{"alias_kind":"arxiv_version","alias_value":"2305.10314v2","created_at":"2026-07-05T07:57:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10314","created_at":"2026-07-05T07:57:40Z"},{"alias_kind":"pith_short_12","alias_value":"JPSVGONLMIUE","created_at":"2026-07-05T07:57:40Z"},{"alias_kind":"pith_short_16","alias_value":"JPSVGONLMIUEFEPC","created_at":"2026-07-05T07:57:40Z"},{"alias_kind":"pith_short_8","alias_value":"JPSVGONL","created_at":"2026-07-05T07:57:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:JPSVGONLMIUEFEPCAQKOAZ76EZ","target":"record","payload":{"canonical_record":{"source":{"id":"2305.10314","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-17T15:53:31Z","cross_cats_sorted":["cs.AI","cs.SE"],"title_canon_sha256":"2a871d937a4d6aad3fdbb8ee8c8f72ce72a91dd3f3b2f70b0d63b1c7b5925743","abstract_canon_sha256":"4a9194e173c28da0976b884ef0d63b0697e3e2502b7cafbdbf1f5f4bc0005b54"},"schema_version":"1.0"},"canonical_sha256":"4be55339ab62284291e20414e067fe267eb9528410b11137f893810806ea25a8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:57:40.490492Z","signature_b64":"rUikM05j47g4Yan+9IlEcAop6YxqESix39O/5CuBFjduY+rCxQ9Jeh9kdvQKtHaWD2fMhyIn8ILUzI8IYAwVAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4be55339ab62284291e20414e067fe267eb9528410b11137f893810806ea25a8","last_reissued_at":"2026-07-05T07:57:40.489981Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:57:40.489981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.10314","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:57:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XyNWynhSp9G5b/D3sWS4ZqNwTD8b4UTdJxvpPoTKnD18pyYfQ4FdqG1qumejjx3gDEmnnsE9m0OIDO802E5FBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T20:43:48.042609Z"},"content_sha256":"db3908e8e29743bd6a39a7efc688bcfbab6db0217bf2a5e17a164f5925244bb1","schema_version":"1.0","event_id":"sha256:db3908e8e29743bd6a39a7efc688bcfbab6db0217bf2a5e17a164f5925244bb1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:JPSVGONLMIUEFEPCAQKOAZ76EZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LeTI: Learning to Generate from Textual Interactions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.CL","authors_text":"Hao Peng, Heng Ji, Reyhaneh Jabbarvand, Xingyao Wang","submitted_at":"2023-05-17T15:53:31Z","abstract_excerpt":"Fine-tuning pre-trained language models (LMs) is essential for enhancing their capabilities. Existing techniques commonly fine-tune on input-output pairs (e.g., instruction tuning) or with numerical rewards that gauge the output quality (e.g., RLHF). We explore LMs' potential to learn from textual interactions (LETI) that not only check their correctness with binary labels but also pinpoint and explain errors in their outputs through textual feedback. Our focus is the code generation task, where the model produces code based on natural language instructions. This setting invites a natural and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10314","kind":"arxiv","version":2},"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/2305.10314/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":"2026-07-05T07:57:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AF0GdO4WeXc4WyQBbfHOy4hshxLOFwUETqbqbGziWSbZuk8TymCh37jviGQuO2PoUmct7yJDwEdiT7IlVrrOCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T20:43:48.043124Z"},"content_sha256":"db01d7726c01cfad6d1a6ccb6bca54187f6d8bfd765079d6577381b8e1512aea","schema_version":"1.0","event_id":"sha256:db01d7726c01cfad6d1a6ccb6bca54187f6d8bfd765079d6577381b8e1512aea"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JPSVGONLMIUEFEPCAQKOAZ76EZ/bundle.json","state_url":"https://pith.science/pith/JPSVGONLMIUEFEPCAQKOAZ76EZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JPSVGONLMIUEFEPCAQKOAZ76EZ/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":"2026-08-11T20:43:48Z","links":{"resolver":"https://pith.science/pith/JPSVGONLMIUEFEPCAQKOAZ76EZ","bundle":"https://pith.science/pith/JPSVGONLMIUEFEPCAQKOAZ76EZ/bundle.json","state":"https://pith.science/pith/JPSVGONLMIUEFEPCAQKOAZ76EZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JPSVGONLMIUEFEPCAQKOAZ76EZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JPSVGONLMIUEFEPCAQKOAZ76EZ","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":"4a9194e173c28da0976b884ef0d63b0697e3e2502b7cafbdbf1f5f4bc0005b54","cross_cats_sorted":["cs.AI","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-17T15:53:31Z","title_canon_sha256":"2a871d937a4d6aad3fdbb8ee8c8f72ce72a91dd3f3b2f70b0d63b1c7b5925743"},"schema_version":"1.0","source":{"id":"2305.10314","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.10314","created_at":"2026-07-05T07:57:40Z"},{"alias_kind":"arxiv_version","alias_value":"2305.10314v2","created_at":"2026-07-05T07:57:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10314","created_at":"2026-07-05T07:57:40Z"},{"alias_kind":"pith_short_12","alias_value":"JPSVGONLMIUE","created_at":"2026-07-05T07:57:40Z"},{"alias_kind":"pith_short_16","alias_value":"JPSVGONLMIUEFEPC","created_at":"2026-07-05T07:57:40Z"},{"alias_kind":"pith_short_8","alias_value":"JPSVGONL","created_at":"2026-07-05T07:57:40Z"}],"graph_snapshots":[{"event_id":"sha256:db01d7726c01cfad6d1a6ccb6bca54187f6d8bfd765079d6577381b8e1512aea","target":"graph","created_at":"2026-07-05T07:57:40Z","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/2305.10314/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-tuning pre-trained language models (LMs) is essential for enhancing their capabilities. Existing techniques commonly fine-tune on input-output pairs (e.g., instruction tuning) or with numerical rewards that gauge the output quality (e.g., RLHF). We explore LMs' potential to learn from textual interactions (LETI) that not only check their correctness with binary labels but also pinpoint and explain errors in their outputs through textual feedback. Our focus is the code generation task, where the model produces code based on natural language instructions. This setting invites a natural and ","authors_text":"Hao Peng, Heng Ji, Reyhaneh Jabbarvand, Xingyao Wang","cross_cats":["cs.AI","cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-17T15:53:31Z","title":"LeTI: Learning to Generate from Textual Interactions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10314","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:db3908e8e29743bd6a39a7efc688bcfbab6db0217bf2a5e17a164f5925244bb1","target":"record","created_at":"2026-07-05T07:57:40Z","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":"4a9194e173c28da0976b884ef0d63b0697e3e2502b7cafbdbf1f5f4bc0005b54","cross_cats_sorted":["cs.AI","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-17T15:53:31Z","title_canon_sha256":"2a871d937a4d6aad3fdbb8ee8c8f72ce72a91dd3f3b2f70b0d63b1c7b5925743"},"schema_version":"1.0","source":{"id":"2305.10314","kind":"arxiv","version":2}},"canonical_sha256":"4be55339ab62284291e20414e067fe267eb9528410b11137f893810806ea25a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4be55339ab62284291e20414e067fe267eb9528410b11137f893810806ea25a8","first_computed_at":"2026-07-05T07:57:40.489981Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:57:40.489981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rUikM05j47g4Yan+9IlEcAop6YxqESix39O/5CuBFjduY+rCxQ9Jeh9kdvQKtHaWD2fMhyIn8ILUzI8IYAwVAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:57:40.490492Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.10314","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db3908e8e29743bd6a39a7efc688bcfbab6db0217bf2a5e17a164f5925244bb1","sha256:db01d7726c01cfad6d1a6ccb6bca54187f6d8bfd765079d6577381b8e1512aea"],"state_sha256":"36899421a0339929b9a4766bcf8121a31a52d19f9c6bbc69b0e3d9c8911e4503"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r6ZoqIzHYaVDNsH01mxAOkcigQa3AgaimyqWCIkgJkyCVtKmkpBHLcpnZ4haePmhHp5HvQr2UX5cjj92YFPgDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T20:43:48.049422Z","bundle_sha256":"56b53fedd297a36831e172dbc5dffa5bbc66c798260acbdaced03e3c73d4d14e"}}