{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:3DT63T45P34XREG7ZUT3YU5JVN","short_pith_number":"pith:3DT63T45","canonical_record":{"source":{"id":"2303.16749","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2023-03-28T16:15:31Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"562aab13794d589110cba4f7ef4ff0440a4741c37b2496b3668c4a3cfb37f669","abstract_canon_sha256":"3f5073ffc8493ab2d73fe315c9143dfc2301ff7a44ab94c67d205f4a18d5dea1"},"schema_version":"1.0"},"canonical_sha256":"d8e7edcf9d7ef97890dfcd27bc53a9ab4b939b47f2a41707817fcf4bfec8c319","source":{"kind":"arxiv","id":"2303.16749","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.16749","created_at":"2026-07-05T07:48:16Z"},{"alias_kind":"arxiv_version","alias_value":"2303.16749v2","created_at":"2026-07-05T07:48:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.16749","created_at":"2026-07-05T07:48:16Z"},{"alias_kind":"pith_short_12","alias_value":"3DT63T45P34X","created_at":"2026-07-05T07:48:16Z"},{"alias_kind":"pith_short_16","alias_value":"3DT63T45P34XREG7","created_at":"2026-07-05T07:48:16Z"},{"alias_kind":"pith_short_8","alias_value":"3DT63T45","created_at":"2026-07-05T07:48:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:3DT63T45P34XREG7ZUT3YU5JVN","target":"record","payload":{"canonical_record":{"source":{"id":"2303.16749","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2023-03-28T16:15:31Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"562aab13794d589110cba4f7ef4ff0440a4741c37b2496b3668c4a3cfb37f669","abstract_canon_sha256":"3f5073ffc8493ab2d73fe315c9143dfc2301ff7a44ab94c67d205f4a18d5dea1"},"schema_version":"1.0"},"canonical_sha256":"d8e7edcf9d7ef97890dfcd27bc53a9ab4b939b47f2a41707817fcf4bfec8c319","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:16.012997Z","signature_b64":"VwI+LUM6oHenUCQ3tGCbZHRd3fChX39zYEuyKiMhlu1+Nk90oB+7zLIeheoRs2/HGxygfEgnsdA4xS0VvX8vDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8e7edcf9d7ef97890dfcd27bc53a9ab4b939b47f2a41707817fcf4bfec8c319","last_reissued_at":"2026-07-05T07:48:16.012508Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:16.012508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.16749","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":"2026-07-05T07:48:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k+bwQtbkeG6edFfTjL1VpQEE0QydS3MSNToHe1AzhzAOjV3E3ZjdZ5BRM95+HAQSefwJ3SnTYqCReIMkLdSXAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:33:33.164238Z"},"content_sha256":"57d150ebfd54d7ad828b53d5a9c46ecc420fb557d20e5d44a9a2556bdca6a086","schema_version":"1.0","event_id":"sha256:57d150ebfd54d7ad828b53d5a9c46ecc420fb557d20e5d44a9a2556bdca6a086"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:3DT63T45P34XREG7ZUT3YU5JVN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Code Generation by Training with Natural Language Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.SE","authors_text":"Angelica Chen, Ethan Perez, J\\'er\\'emy Scheurer, Jon Ander Campos, Jun Shern Chan, Kyunghyun Cho, Samuel R. Bowman, Tomasz Korbak","submitted_at":"2023-03-28T16:15:31Z","abstract_excerpt":"The potential for pre-trained large language models (LLMs) to use natural language feedback at inference time has been an exciting recent development. We build upon this observation by formalizing an algorithm for learning from natural language feedback at training time instead, which we call Imitation learning from Language Feedback (ILF). ILF requires only a small amount of human-written feedback during training and does not require the same feedback at test time, making it both user-friendly and sample-efficient. We further show that ILF can be seen as a form of minimizing the KL divergence"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.16749","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/2303.16749/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":"2026-07-05T07:48:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aRQUk+W/u4cc8iOFZuadaQ3+/nlIxHxpC6/0CHe5YWpXSQr7rbQLpIKtl82WXY1BRcpOHj4bZ7IWGYfCX3MTDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:33:33.165141Z"},"content_sha256":"c6bb74171df6c49df160ff42fa2cb3f2f3e271f37a49634d5d44d1ca4e5c7eb0","schema_version":"1.0","event_id":"sha256:c6bb74171df6c49df160ff42fa2cb3f2f3e271f37a49634d5d44d1ca4e5c7eb0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3DT63T45P34XREG7ZUT3YU5JVN/bundle.json","state_url":"https://pith.science/pith/3DT63T45P34XREG7ZUT3YU5JVN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3DT63T45P34XREG7ZUT3YU5JVN/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":"2026-08-08T13:33:33Z","links":{"resolver":"https://pith.science/pith/3DT63T45P34XREG7ZUT3YU5JVN","bundle":"https://pith.science/pith/3DT63T45P34XREG7ZUT3YU5JVN/bundle.json","state":"https://pith.science/pith/3DT63T45P34XREG7ZUT3YU5JVN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3DT63T45P34XREG7ZUT3YU5JVN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3DT63T45P34XREG7ZUT3YU5JVN","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":"3f5073ffc8493ab2d73fe315c9143dfc2301ff7a44ab94c67d205f4a18d5dea1","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2023-03-28T16:15:31Z","title_canon_sha256":"562aab13794d589110cba4f7ef4ff0440a4741c37b2496b3668c4a3cfb37f669"},"schema_version":"1.0","source":{"id":"2303.16749","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.16749","created_at":"2026-07-05T07:48:16Z"},{"alias_kind":"arxiv_version","alias_value":"2303.16749v2","created_at":"2026-07-05T07:48:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.16749","created_at":"2026-07-05T07:48:16Z"},{"alias_kind":"pith_short_12","alias_value":"3DT63T45P34X","created_at":"2026-07-05T07:48:16Z"},{"alias_kind":"pith_short_16","alias_value":"3DT63T45P34XREG7","created_at":"2026-07-05T07:48:16Z"},{"alias_kind":"pith_short_8","alias_value":"3DT63T45","created_at":"2026-07-05T07:48:16Z"}],"graph_snapshots":[{"event_id":"sha256:c6bb74171df6c49df160ff42fa2cb3f2f3e271f37a49634d5d44d1ca4e5c7eb0","target":"graph","created_at":"2026-07-05T07:48:16Z","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/2303.16749/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The potential for pre-trained large language models (LLMs) to use natural language feedback at inference time has been an exciting recent development. We build upon this observation by formalizing an algorithm for learning from natural language feedback at training time instead, which we call Imitation learning from Language Feedback (ILF). ILF requires only a small amount of human-written feedback during training and does not require the same feedback at test time, making it both user-friendly and sample-efficient. We further show that ILF can be seen as a form of minimizing the KL divergence","authors_text":"Angelica Chen, Ethan Perez, J\\'er\\'emy Scheurer, Jon Ander Campos, Jun Shern Chan, Kyunghyun Cho, Samuel R. Bowman, Tomasz Korbak","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2023-03-28T16:15:31Z","title":"Improving Code Generation by Training with Natural Language Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.16749","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":"sha256:57d150ebfd54d7ad828b53d5a9c46ecc420fb557d20e5d44a9a2556bdca6a086","target":"record","created_at":"2026-07-05T07:48:16Z","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":"3f5073ffc8493ab2d73fe315c9143dfc2301ff7a44ab94c67d205f4a18d5dea1","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2023-03-28T16:15:31Z","title_canon_sha256":"562aab13794d589110cba4f7ef4ff0440a4741c37b2496b3668c4a3cfb37f669"},"schema_version":"1.0","source":{"id":"2303.16749","kind":"arxiv","version":2}},"canonical_sha256":"d8e7edcf9d7ef97890dfcd27bc53a9ab4b939b47f2a41707817fcf4bfec8c319","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d8e7edcf9d7ef97890dfcd27bc53a9ab4b939b47f2a41707817fcf4bfec8c319","first_computed_at":"2026-07-05T07:48:16.012508Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:48:16.012508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VwI+LUM6oHenUCQ3tGCbZHRd3fChX39zYEuyKiMhlu1+Nk90oB+7zLIeheoRs2/HGxygfEgnsdA4xS0VvX8vDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:48:16.012997Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.16749","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:57d150ebfd54d7ad828b53d5a9c46ecc420fb557d20e5d44a9a2556bdca6a086","sha256:c6bb74171df6c49df160ff42fa2cb3f2f3e271f37a49634d5d44d1ca4e5c7eb0"],"state_sha256":"90c159c6c7fc8a23d73ed0020a53883a6e6b67b2cf5e15b6845c08801a86e894"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YlEuMe8EiIZwQJY+lriLa/bY0RSEZ5is2yH71/unnuL2Q75rqOrtwYGkYdhe6Vy1pBK/rKC5N/M547EM+YGMBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T13:33:33.170758Z","bundle_sha256":"5f0c487d11653f77fe57a45baba3c93a44ef0ec9eb7cffb38eb8e9e846612f46"}}