{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PBQMKTSOADE6E2P2SJHYVCAC6W","short_pith_number":"pith:PBQMKTSO","canonical_record":{"source":{"id":"2402.10893","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-16T18:50:24Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"5aaf4123d661aef6336c8f20328bbf04db19afa2e61f2d7ff7983edbaaf74ed5","abstract_canon_sha256":"13d47524bb81d0e5a173b75dbe4c9b7eb2730e8e59d5af842369367044a97240"},"schema_version":"1.0"},"canonical_sha256":"7860c54e4e00c9e269fa924f8a8802f589121963e30d080d10e948be641226c2","source":{"kind":"arxiv","id":"2402.10893","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.10893","created_at":"2026-07-05T07:46:02Z"},{"alias_kind":"arxiv_version","alias_value":"2402.10893v1","created_at":"2026-07-05T07:46:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.10893","created_at":"2026-07-05T07:46:02Z"},{"alias_kind":"pith_short_12","alias_value":"PBQMKTSOADE6","created_at":"2026-07-05T07:46:02Z"},{"alias_kind":"pith_short_16","alias_value":"PBQMKTSOADE6E2P2","created_at":"2026-07-05T07:46:02Z"},{"alias_kind":"pith_short_8","alias_value":"PBQMKTSO","created_at":"2026-07-05T07:46:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PBQMKTSOADE6E2P2SJHYVCAC6W","target":"record","payload":{"canonical_record":{"source":{"id":"2402.10893","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-16T18:50:24Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"5aaf4123d661aef6336c8f20328bbf04db19afa2e61f2d7ff7983edbaaf74ed5","abstract_canon_sha256":"13d47524bb81d0e5a173b75dbe4c9b7eb2730e8e59d5af842369367044a97240"},"schema_version":"1.0"},"canonical_sha256":"7860c54e4e00c9e269fa924f8a8802f589121963e30d080d10e948be641226c2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:46:02.161723Z","signature_b64":"p8Ck5AkppmGe/vH0eZ2XZtv2DifXsx+kpu2xtBuokTXwUVMwTFQ+9VyIGiaCSpN9phZuVwu0Tna/nHfuipgvAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7860c54e4e00c9e269fa924f8a8802f589121963e30d080d10e948be641226c2","last_reissued_at":"2026-07-05T07:46:02.161286Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:46:02.161286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.10893","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":"2026-07-05T07:46:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8Y1KWppXegf9yy3z7rQH/gNFsdHGOrr4OfzB9Cc7JvXZ2pnlb5V6Yp9qOTQu3cOhcdkkwHeaMcjsS29tBZDIBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:08:06.387486Z"},"content_sha256":"1ebc466ae68a976e5e54141fe289cacb1b68a112f9aba6325e73f17eed93e46d","schema_version":"1.0","event_id":"sha256:1ebc466ae68a976e5e54141fe289cacb1b68a112f9aba6325e73f17eed93e46d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PBQMKTSOADE6E2P2SJHYVCAC6W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RLVF: Learning from Verbal Feedback without Overgeneralization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Alexander Khazatsky, Annie S Chen, Archit Sharma, Chelsea Finn, Eric Mitchell, Moritz Stephan, Sheryl Hsu","submitted_at":"2024-02-16T18:50:24Z","abstract_excerpt":"The diversity of contexts in which large language models (LLMs) are deployed requires the ability to modify or customize default model behaviors to incorporate nuanced requirements and preferences. A convenient interface to specify such model adjustments is high-level verbal feedback, such as \"Don't use emojis when drafting emails to my boss.\" However, while writing high-level feedback is far simpler than collecting annotations for reinforcement learning from human feedback (RLHF), we find that simply prompting a model with such feedback leads to overgeneralization of the feedback to contexts "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.10893","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/2402.10893/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":"2026-07-05T07:46:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NFpoRv5uDr1NGEc/AFKlkBr7bZHnEP8rHy1YN87a0uhzHdpEMSonBV07jEYFYgYXvd4YJwkucnTe/td0tRMmBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:08:06.388001Z"},"content_sha256":"1b7d23aa17a8771a7a5338df8fbbd0b3dbe2839f6e1b9bcd8781c50709807cd4","schema_version":"1.0","event_id":"sha256:1b7d23aa17a8771a7a5338df8fbbd0b3dbe2839f6e1b9bcd8781c50709807cd4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PBQMKTSOADE6E2P2SJHYVCAC6W/bundle.json","state_url":"https://pith.science/pith/PBQMKTSOADE6E2P2SJHYVCAC6W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PBQMKTSOADE6E2P2SJHYVCAC6W/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":"2026-08-06T06:08:06Z","links":{"resolver":"https://pith.science/pith/PBQMKTSOADE6E2P2SJHYVCAC6W","bundle":"https://pith.science/pith/PBQMKTSOADE6E2P2SJHYVCAC6W/bundle.json","state":"https://pith.science/pith/PBQMKTSOADE6E2P2SJHYVCAC6W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PBQMKTSOADE6E2P2SJHYVCAC6W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PBQMKTSOADE6E2P2SJHYVCAC6W","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":"13d47524bb81d0e5a173b75dbe4c9b7eb2730e8e59d5af842369367044a97240","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-16T18:50:24Z","title_canon_sha256":"5aaf4123d661aef6336c8f20328bbf04db19afa2e61f2d7ff7983edbaaf74ed5"},"schema_version":"1.0","source":{"id":"2402.10893","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.10893","created_at":"2026-07-05T07:46:02Z"},{"alias_kind":"arxiv_version","alias_value":"2402.10893v1","created_at":"2026-07-05T07:46:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.10893","created_at":"2026-07-05T07:46:02Z"},{"alias_kind":"pith_short_12","alias_value":"PBQMKTSOADE6","created_at":"2026-07-05T07:46:02Z"},{"alias_kind":"pith_short_16","alias_value":"PBQMKTSOADE6E2P2","created_at":"2026-07-05T07:46:02Z"},{"alias_kind":"pith_short_8","alias_value":"PBQMKTSO","created_at":"2026-07-05T07:46:02Z"}],"graph_snapshots":[{"event_id":"sha256:1b7d23aa17a8771a7a5338df8fbbd0b3dbe2839f6e1b9bcd8781c50709807cd4","target":"graph","created_at":"2026-07-05T07:46:02Z","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/2402.10893/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The diversity of contexts in which large language models (LLMs) are deployed requires the ability to modify or customize default model behaviors to incorporate nuanced requirements and preferences. A convenient interface to specify such model adjustments is high-level verbal feedback, such as \"Don't use emojis when drafting emails to my boss.\" However, while writing high-level feedback is far simpler than collecting annotations for reinforcement learning from human feedback (RLHF), we find that simply prompting a model with such feedback leads to overgeneralization of the feedback to contexts ","authors_text":"Alexander Khazatsky, Annie S Chen, Archit Sharma, Chelsea Finn, Eric Mitchell, Moritz Stephan, Sheryl Hsu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-16T18:50:24Z","title":"RLVF: Learning from Verbal Feedback without Overgeneralization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.10893","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":"sha256:1ebc466ae68a976e5e54141fe289cacb1b68a112f9aba6325e73f17eed93e46d","target":"record","created_at":"2026-07-05T07:46:02Z","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":"13d47524bb81d0e5a173b75dbe4c9b7eb2730e8e59d5af842369367044a97240","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-16T18:50:24Z","title_canon_sha256":"5aaf4123d661aef6336c8f20328bbf04db19afa2e61f2d7ff7983edbaaf74ed5"},"schema_version":"1.0","source":{"id":"2402.10893","kind":"arxiv","version":1}},"canonical_sha256":"7860c54e4e00c9e269fa924f8a8802f589121963e30d080d10e948be641226c2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7860c54e4e00c9e269fa924f8a8802f589121963e30d080d10e948be641226c2","first_computed_at":"2026-07-05T07:46:02.161286Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:46:02.161286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p8Ck5AkppmGe/vH0eZ2XZtv2DifXsx+kpu2xtBuokTXwUVMwTFQ+9VyIGiaCSpN9phZuVwu0Tna/nHfuipgvAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:46:02.161723Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.10893","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ebc466ae68a976e5e54141fe289cacb1b68a112f9aba6325e73f17eed93e46d","sha256:1b7d23aa17a8771a7a5338df8fbbd0b3dbe2839f6e1b9bcd8781c50709807cd4"],"state_sha256":"c0eb24d4572b9f8b5c35fdc8e7dc22aeb69b1abf2e5014352c2a1634492bf8f2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zPt/E7kgeo9vEuq5XY3nP50aXlo1RoVlnXcrKR4PnJQ04XLdqgVGzTHCsWveyG8NtdS6O+yEvHlJkbGwZi9dCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T06:08:06.393615Z","bundle_sha256":"6b5738d079772c25846a1c7d75fe3d973948fee9b2c1251279293e76b95402d7"}}