{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3AWA6UMQQ5D7UWYSVGMZMVLXO7","short_pith_number":"pith:3AWA6UMQ","canonical_record":{"source":{"id":"2402.07282","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-11T19:13:26Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"45754d95e0cd0de44398c447f2724ce11023ba2e4304c904230e9cc84ef0b4b7","abstract_canon_sha256":"d50dc16320455aba45c955fd1f381ac86c929b3b0c2182a4b84e4f11d5719c7d"},"schema_version":"1.0"},"canonical_sha256":"d82c0f51908747fa5b12a99996557777c31cfa76981b9f279d30425e1df2f87b","source":{"kind":"arxiv","id":"2402.07282","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.07282","created_at":"2026-07-05T07:44:46Z"},{"alias_kind":"arxiv_version","alias_value":"2402.07282v2","created_at":"2026-07-05T07:44:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07282","created_at":"2026-07-05T07:44:46Z"},{"alias_kind":"pith_short_12","alias_value":"3AWA6UMQQ5D7","created_at":"2026-07-05T07:44:46Z"},{"alias_kind":"pith_short_16","alias_value":"3AWA6UMQQ5D7UWYS","created_at":"2026-07-05T07:44:46Z"},{"alias_kind":"pith_short_8","alias_value":"3AWA6UMQ","created_at":"2026-07-05T07:44:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3AWA6UMQQ5D7UWYSVGMZMVLXO7","target":"record","payload":{"canonical_record":{"source":{"id":"2402.07282","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-11T19:13:26Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"45754d95e0cd0de44398c447f2724ce11023ba2e4304c904230e9cc84ef0b4b7","abstract_canon_sha256":"d50dc16320455aba45c955fd1f381ac86c929b3b0c2182a4b84e4f11d5719c7d"},"schema_version":"1.0"},"canonical_sha256":"d82c0f51908747fa5b12a99996557777c31cfa76981b9f279d30425e1df2f87b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:44:46.853359Z","signature_b64":"o/N9CSOMVY47I4pHUFSWWzOUYwGU+dmHJn+mGVSD3ekIfDoiiRNv1AX2zARBNmcujeR+O82MdOW/9MdkcjTxBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d82c0f51908747fa5b12a99996557777c31cfa76981b9f279d30425e1df2f87b","last_reissued_at":"2026-07-05T07:44:46.852906Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:44:46.852906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.07282","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":"2026-07-05T07:44:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UEW36/7tQCVGmZuzMapHK6T/0cGKnnp+5Z++XO4Pt4W+Fsb79dg6S8HVpi0lbhxa9fXcOpAaiOMgNk8Ykwc1Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T03:13:56.541029Z"},"content_sha256":"f3a4eddd67d26a5dd17d0b61f576aafad67b5dde11064ec4cf3f8f56ef32d2fa","schema_version":"1.0","event_id":"sha256:f3a4eddd67d26a5dd17d0b61f576aafad67b5dde11064ec4cf3f8f56ef32d2fa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3AWA6UMQQ5D7UWYSVGMZMVLXO7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How do Large Language Models Navigate Conflicts between Honesty and Helpfulness?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ishita Dasgupta, Ryan Liu, Theodore R. Sumers, Thomas L. Griffiths","submitted_at":"2024-02-11T19:13:26Z","abstract_excerpt":"In day-to-day communication, people often approximate the truth - for example, rounding the time or omitting details - in order to be maximally helpful to the listener. How do large language models (LLMs) handle such nuanced trade-offs? To address this question, we use psychological models and experiments designed to characterize human behavior to analyze LLMs. We test a range of LLMs and explore how optimization for human preferences or inference-time reasoning affects these trade-offs. We find that reinforcement learning from human feedback improves both honesty and helpfulness, while chain-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07282","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/2402.07282/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":"2026-07-05T07:44:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2r0IbVyqLvt9Uy1hKhLC3Yo6PzEjb8bUumogxM6CEAyjIKU9UUcMOH+b4GerE3GRNtsGOc4dfFGMP1t4tDwUCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T03:13:56.541585Z"},"content_sha256":"854a6b42b058bd9ef458345b07c65e1f29440fff9aa20e8b97cddb0927e18e4a","schema_version":"1.0","event_id":"sha256:854a6b42b058bd9ef458345b07c65e1f29440fff9aa20e8b97cddb0927e18e4a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3AWA6UMQQ5D7UWYSVGMZMVLXO7/bundle.json","state_url":"https://pith.science/pith/3AWA6UMQQ5D7UWYSVGMZMVLXO7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3AWA6UMQQ5D7UWYSVGMZMVLXO7/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":"2026-08-22T03:13:56Z","links":{"resolver":"https://pith.science/pith/3AWA6UMQQ5D7UWYSVGMZMVLXO7","bundle":"https://pith.science/pith/3AWA6UMQQ5D7UWYSVGMZMVLXO7/bundle.json","state":"https://pith.science/pith/3AWA6UMQQ5D7UWYSVGMZMVLXO7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3AWA6UMQQ5D7UWYSVGMZMVLXO7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3AWA6UMQQ5D7UWYSVGMZMVLXO7","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":"d50dc16320455aba45c955fd1f381ac86c929b3b0c2182a4b84e4f11d5719c7d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-11T19:13:26Z","title_canon_sha256":"45754d95e0cd0de44398c447f2724ce11023ba2e4304c904230e9cc84ef0b4b7"},"schema_version":"1.0","source":{"id":"2402.07282","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.07282","created_at":"2026-07-05T07:44:46Z"},{"alias_kind":"arxiv_version","alias_value":"2402.07282v2","created_at":"2026-07-05T07:44:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07282","created_at":"2026-07-05T07:44:46Z"},{"alias_kind":"pith_short_12","alias_value":"3AWA6UMQQ5D7","created_at":"2026-07-05T07:44:46Z"},{"alias_kind":"pith_short_16","alias_value":"3AWA6UMQQ5D7UWYS","created_at":"2026-07-05T07:44:46Z"},{"alias_kind":"pith_short_8","alias_value":"3AWA6UMQ","created_at":"2026-07-05T07:44:46Z"}],"graph_snapshots":[{"event_id":"sha256:854a6b42b058bd9ef458345b07c65e1f29440fff9aa20e8b97cddb0927e18e4a","target":"graph","created_at":"2026-07-05T07:44:46Z","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/2402.07282/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In day-to-day communication, people often approximate the truth - for example, rounding the time or omitting details - in order to be maximally helpful to the listener. How do large language models (LLMs) handle such nuanced trade-offs? To address this question, we use psychological models and experiments designed to characterize human behavior to analyze LLMs. We test a range of LLMs and explore how optimization for human preferences or inference-time reasoning affects these trade-offs. We find that reinforcement learning from human feedback improves both honesty and helpfulness, while chain-","authors_text":"Ishita Dasgupta, Ryan Liu, Theodore R. Sumers, Thomas L. Griffiths","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-11T19:13:26Z","title":"How do Large Language Models Navigate Conflicts between Honesty and Helpfulness?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07282","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:f3a4eddd67d26a5dd17d0b61f576aafad67b5dde11064ec4cf3f8f56ef32d2fa","target":"record","created_at":"2026-07-05T07:44:46Z","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":"d50dc16320455aba45c955fd1f381ac86c929b3b0c2182a4b84e4f11d5719c7d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-11T19:13:26Z","title_canon_sha256":"45754d95e0cd0de44398c447f2724ce11023ba2e4304c904230e9cc84ef0b4b7"},"schema_version":"1.0","source":{"id":"2402.07282","kind":"arxiv","version":2}},"canonical_sha256":"d82c0f51908747fa5b12a99996557777c31cfa76981b9f279d30425e1df2f87b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d82c0f51908747fa5b12a99996557777c31cfa76981b9f279d30425e1df2f87b","first_computed_at":"2026-07-05T07:44:46.852906Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:44:46.852906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o/N9CSOMVY47I4pHUFSWWzOUYwGU+dmHJn+mGVSD3ekIfDoiiRNv1AX2zARBNmcujeR+O82MdOW/9MdkcjTxBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:44:46.853359Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.07282","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f3a4eddd67d26a5dd17d0b61f576aafad67b5dde11064ec4cf3f8f56ef32d2fa","sha256:854a6b42b058bd9ef458345b07c65e1f29440fff9aa20e8b97cddb0927e18e4a"],"state_sha256":"e27c0692a82821ab08603443733851a18d21f53ffe77caac9e2423cb8c6bc699"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+n3NedaMv1jOs5EkWiKCvASXwx6+sURSgsEmYD5UAzrP8a8VjQmjo/f/AY0IQnLs47qn1VfzKBHNFiSVF35CCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T03:13:56.546087Z","bundle_sha256":"3a72d297c854a497e4c482db740c35d0f32246513d00db548a7b068dbc030250"}}