{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:2CI2L3ZKALWBGSOGYSQJC4VVVG","short_pith_number":"pith:2CI2L3ZK","canonical_record":{"source":{"id":"2211.05750","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-10T18:31:56Z","cross_cats_sorted":[],"title_canon_sha256":"be3fb0a85b7af66f6fc417eef5e86874ae3ab7f706ce33d54b8e96e27d810e8b","abstract_canon_sha256":"2fa51adf459597aa600cb42e75fb97a20b98ceb07c59b11de362b049c891588d"},"schema_version":"1.0"},"canonical_sha256":"d091a5ef2a02ec1349c6c4a09172b5a9bffde2d88a2e95ac7e4a344232599764","source":{"kind":"arxiv","id":"2211.05750","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.05750","created_at":"2026-07-05T06:53:32Z"},{"alias_kind":"arxiv_version","alias_value":"2211.05750v3","created_at":"2026-07-05T06:53:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.05750","created_at":"2026-07-05T06:53:32Z"},{"alias_kind":"pith_short_12","alias_value":"2CI2L3ZKALWB","created_at":"2026-07-05T06:53:32Z"},{"alias_kind":"pith_short_16","alias_value":"2CI2L3ZKALWBGSOG","created_at":"2026-07-05T06:53:32Z"},{"alias_kind":"pith_short_8","alias_value":"2CI2L3ZK","created_at":"2026-07-05T06:53:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:2CI2L3ZKALWBGSOGYSQJC4VVVG","target":"record","payload":{"canonical_record":{"source":{"id":"2211.05750","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-10T18:31:56Z","cross_cats_sorted":[],"title_canon_sha256":"be3fb0a85b7af66f6fc417eef5e86874ae3ab7f706ce33d54b8e96e27d810e8b","abstract_canon_sha256":"2fa51adf459597aa600cb42e75fb97a20b98ceb07c59b11de362b049c891588d"},"schema_version":"1.0"},"canonical_sha256":"d091a5ef2a02ec1349c6c4a09172b5a9bffde2d88a2e95ac7e4a344232599764","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:53:32.138956Z","signature_b64":"+iqbZqHUcxSJubdJt+ZYukDt2h10/nHeYYFOCe6f6xBh1r9onr8FSRDA0AyT3LIhrYkRhSxGVoRMkYKIZh0cBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d091a5ef2a02ec1349c6c4a09172b5a9bffde2d88a2e95ac7e4a344232599764","last_reissued_at":"2026-07-05T06:53:32.138361Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:53:32.138361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.05750","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:53:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hba073Hvu7aq25lfsdVmi6MEvgPLcQFIuIQaWtliDzi6fauCqhJw5uzHhYEwBo9t5IRL5QgQObf3cASUEOuiCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T01:18:52.546539Z"},"content_sha256":"30c7fbe5582147776f94a6946093cbe3d819dbd61f3ac6748cc7ca564e4b5fdb","schema_version":"1.0","event_id":"sha256:30c7fbe5582147776f94a6946093cbe3d819dbd61f3ac6748cc7ca564e4b5fdb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:2CI2L3ZKALWBGSOGYSQJC4VVVG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Nano: Nested Human-in-the-Loop Reward Learning for Few-shot Language Model Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Louis-Philippe Morency, Paul Pu Liang, Ruslan Salakhutdinov, Xiang Fan, Yiwei Lyu","submitted_at":"2022-11-10T18:31:56Z","abstract_excerpt":"Pretrained language models have demonstrated extraordinary capabilities in language generation. However, real-world tasks often require controlling the distribution of generated text in order to mitigate bias, promote fairness, and achieve personalization. Existing techniques for controlling the distribution of generated text only work with quantified distributions, which require pre-defined categories, proportions of the distribution, or an existing corpus following the desired distributions. However, many important distributions, such as personal preferences, are unquantified. In this work, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.05750","kind":"arxiv","version":3},"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/2211.05750/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":"2026-07-05T06:53:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dai4s6P7R1cThWciqbdWHDU7TjROb9Yc027+HHZ0v0VQjB/sQALFoMMADJfioVPvMgbuZ64jWG6UUnXaC8SqBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T01:18:52.547047Z"},"content_sha256":"07c243da9c9852fcf12ad34073facf4ca41ffa0bbef26b5f244cdca8b8882914","schema_version":"1.0","event_id":"sha256:07c243da9c9852fcf12ad34073facf4ca41ffa0bbef26b5f244cdca8b8882914"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2CI2L3ZKALWBGSOGYSQJC4VVVG/bundle.json","state_url":"https://pith.science/pith/2CI2L3ZKALWBGSOGYSQJC4VVVG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2CI2L3ZKALWBGSOGYSQJC4VVVG/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":"2026-08-11T01:18:52Z","links":{"resolver":"https://pith.science/pith/2CI2L3ZKALWBGSOGYSQJC4VVVG","bundle":"https://pith.science/pith/2CI2L3ZKALWBGSOGYSQJC4VVVG/bundle.json","state":"https://pith.science/pith/2CI2L3ZKALWBGSOGYSQJC4VVVG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2CI2L3ZKALWBGSOGYSQJC4VVVG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:2CI2L3ZKALWBGSOGYSQJC4VVVG","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":"2fa51adf459597aa600cb42e75fb97a20b98ceb07c59b11de362b049c891588d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-10T18:31:56Z","title_canon_sha256":"be3fb0a85b7af66f6fc417eef5e86874ae3ab7f706ce33d54b8e96e27d810e8b"},"schema_version":"1.0","source":{"id":"2211.05750","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.05750","created_at":"2026-07-05T06:53:32Z"},{"alias_kind":"arxiv_version","alias_value":"2211.05750v3","created_at":"2026-07-05T06:53:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.05750","created_at":"2026-07-05T06:53:32Z"},{"alias_kind":"pith_short_12","alias_value":"2CI2L3ZKALWB","created_at":"2026-07-05T06:53:32Z"},{"alias_kind":"pith_short_16","alias_value":"2CI2L3ZKALWBGSOG","created_at":"2026-07-05T06:53:32Z"},{"alias_kind":"pith_short_8","alias_value":"2CI2L3ZK","created_at":"2026-07-05T06:53:32Z"}],"graph_snapshots":[{"event_id":"sha256:07c243da9c9852fcf12ad34073facf4ca41ffa0bbef26b5f244cdca8b8882914","target":"graph","created_at":"2026-07-05T06:53:32Z","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/2211.05750/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pretrained language models have demonstrated extraordinary capabilities in language generation. However, real-world tasks often require controlling the distribution of generated text in order to mitigate bias, promote fairness, and achieve personalization. Existing techniques for controlling the distribution of generated text only work with quantified distributions, which require pre-defined categories, proportions of the distribution, or an existing corpus following the desired distributions. However, many important distributions, such as personal preferences, are unquantified. In this work, ","authors_text":"Louis-Philippe Morency, Paul Pu Liang, Ruslan Salakhutdinov, Xiang Fan, Yiwei Lyu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-10T18:31:56Z","title":"Nano: Nested Human-in-the-Loop Reward Learning for Few-shot Language Model Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.05750","kind":"arxiv","version":3},"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":"sha256:30c7fbe5582147776f94a6946093cbe3d819dbd61f3ac6748cc7ca564e4b5fdb","target":"record","created_at":"2026-07-05T06:53:32Z","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":"2fa51adf459597aa600cb42e75fb97a20b98ceb07c59b11de362b049c891588d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-10T18:31:56Z","title_canon_sha256":"be3fb0a85b7af66f6fc417eef5e86874ae3ab7f706ce33d54b8e96e27d810e8b"},"schema_version":"1.0","source":{"id":"2211.05750","kind":"arxiv","version":3}},"canonical_sha256":"d091a5ef2a02ec1349c6c4a09172b5a9bffde2d88a2e95ac7e4a344232599764","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d091a5ef2a02ec1349c6c4a09172b5a9bffde2d88a2e95ac7e4a344232599764","first_computed_at":"2026-07-05T06:53:32.138361Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:53:32.138361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+iqbZqHUcxSJubdJt+ZYukDt2h10/nHeYYFOCe6f6xBh1r9onr8FSRDA0AyT3LIhrYkRhSxGVoRMkYKIZh0cBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:53:32.138956Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.05750","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:30c7fbe5582147776f94a6946093cbe3d819dbd61f3ac6748cc7ca564e4b5fdb","sha256:07c243da9c9852fcf12ad34073facf4ca41ffa0bbef26b5f244cdca8b8882914"],"state_sha256":"cc9d148b7ecefa9b22c8028b48262582c28be9173af0bc332cfd226b64c3000f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cP0ROJuq6iru+eE837wr3mWJg7Hx9ReopNiLU5VV4MahVC+0ZhMRs70KNbnLNeBSXYROwLWNBEVGpLE+DO77Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T01:18:52.551747Z","bundle_sha256":"af0c4546de63dd499361016f398ddea1d95ee815591bc2fc15fd2d423ae253b2"}}