{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:326EREQXZ4HUOY3AIPR5XXC46Z","short_pith_number":"pith:326EREQX","canonical_record":{"source":{"id":"2501.00418","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-31T12:40:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"346bd1be5d4fac5a07399c296fb43a4f3ad4d8994798b7784dc54c4d8e8fc4a3","abstract_canon_sha256":"552f7437746b14423efffe1933151b71126368992e381952397b0016636532f8"},"schema_version":"1.0"},"canonical_sha256":"debc489217cf0f47636043e3dbdc5cf6759d9d3080568376f96b05b7d930792f","source":{"kind":"arxiv","id":"2501.00418","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.00418","created_at":"2026-07-05T09:56:05Z"},{"alias_kind":"arxiv_version","alias_value":"2501.00418v1","created_at":"2026-07-05T09:56:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00418","created_at":"2026-07-05T09:56:05Z"},{"alias_kind":"pith_short_12","alias_value":"326EREQXZ4HU","created_at":"2026-07-05T09:56:05Z"},{"alias_kind":"pith_short_16","alias_value":"326EREQXZ4HUOY3A","created_at":"2026-07-05T09:56:05Z"},{"alias_kind":"pith_short_8","alias_value":"326EREQX","created_at":"2026-07-05T09:56:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:326EREQXZ4HUOY3AIPR5XXC46Z","target":"record","payload":{"canonical_record":{"source":{"id":"2501.00418","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-31T12:40:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"346bd1be5d4fac5a07399c296fb43a4f3ad4d8994798b7784dc54c4d8e8fc4a3","abstract_canon_sha256":"552f7437746b14423efffe1933151b71126368992e381952397b0016636532f8"},"schema_version":"1.0"},"canonical_sha256":"debc489217cf0f47636043e3dbdc5cf6759d9d3080568376f96b05b7d930792f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:05.623528Z","signature_b64":"4wTuY6esMn9JLzQksz/rpqrmG0+m3RCnZHZ8X9AN4mxuTfzq92jv4k1IxGG98dMmoFu+CtV3cvEKoyCKvEb8DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"debc489217cf0f47636043e3dbdc5cf6759d9d3080568376f96b05b7d930792f","last_reissued_at":"2026-07-05T09:56:05.622956Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:05.622956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.00418","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":"2026-07-05T09:56:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ptIB3rFfTvSaQrzgTMkaMzdF1I0XI4yLzwnG4NalUA8LR8ojvRCt2LToV4ZQOd1HArKqNe/JO1wUjvV4KkqgAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:34:36.670752Z"},"content_sha256":"7cfcb121ac2a4a33581bd9b53d4a749f39010ad2bbf0ef33e1ab2df0c0b16da9","schema_version":"1.0","event_id":"sha256:7cfcb121ac2a4a33581bd9b53d4a749f39010ad2bbf0ef33e1ab2df0c0b16da9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:326EREQXZ4HUOY3AIPR5XXC46Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generalizing Trust: Weak-to-Strong Trustworthiness in Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aounon Kumar, Himabindu Lakkaraju, Lillian Sun, Martin Pawelczyk, Zhenting Qi","submitted_at":"2024-12-31T12:40:02Z","abstract_excerpt":"The rapid proliferation of generative AI, especially large language models, has led to their integration into a variety of applications. A key phenomenon known as weak-to-strong generalization - where a strong model trained on a weak model's outputs surpasses the weak model in task performance - has gained significant attention. Yet, whether critical trustworthiness properties such as robustness, fairness, and privacy can generalize similarly remains an open question. In this work, we study this question by examining if a stronger model can inherit trustworthiness properties when fine-tuned on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00418","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/2501.00418/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":"2026-07-05T09:56:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3I8cv56Rpz6g3ngx7TDnfWiVUR/JXWp1C9LJU99DZ4vFt7rNYFKKsWflK5HVNkB5wLrx89Wd6lej01ODzKyhAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:34:36.671345Z"},"content_sha256":"4bb571995341c6ef9e9b12604fb2956295ca4a2f2402f1b70baba0ce6ba5926f","schema_version":"1.0","event_id":"sha256:4bb571995341c6ef9e9b12604fb2956295ca4a2f2402f1b70baba0ce6ba5926f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/326EREQXZ4HUOY3AIPR5XXC46Z/bundle.json","state_url":"https://pith.science/pith/326EREQXZ4HUOY3AIPR5XXC46Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/326EREQXZ4HUOY3AIPR5XXC46Z/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":"2026-08-08T09:34:36Z","links":{"resolver":"https://pith.science/pith/326EREQXZ4HUOY3AIPR5XXC46Z","bundle":"https://pith.science/pith/326EREQXZ4HUOY3AIPR5XXC46Z/bundle.json","state":"https://pith.science/pith/326EREQXZ4HUOY3AIPR5XXC46Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/326EREQXZ4HUOY3AIPR5XXC46Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:326EREQXZ4HUOY3AIPR5XXC46Z","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":"552f7437746b14423efffe1933151b71126368992e381952397b0016636532f8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-31T12:40:02Z","title_canon_sha256":"346bd1be5d4fac5a07399c296fb43a4f3ad4d8994798b7784dc54c4d8e8fc4a3"},"schema_version":"1.0","source":{"id":"2501.00418","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.00418","created_at":"2026-07-05T09:56:05Z"},{"alias_kind":"arxiv_version","alias_value":"2501.00418v1","created_at":"2026-07-05T09:56:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00418","created_at":"2026-07-05T09:56:05Z"},{"alias_kind":"pith_short_12","alias_value":"326EREQXZ4HU","created_at":"2026-07-05T09:56:05Z"},{"alias_kind":"pith_short_16","alias_value":"326EREQXZ4HUOY3A","created_at":"2026-07-05T09:56:05Z"},{"alias_kind":"pith_short_8","alias_value":"326EREQX","created_at":"2026-07-05T09:56:05Z"}],"graph_snapshots":[{"event_id":"sha256:4bb571995341c6ef9e9b12604fb2956295ca4a2f2402f1b70baba0ce6ba5926f","target":"graph","created_at":"2026-07-05T09:56:05Z","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/2501.00418/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid proliferation of generative AI, especially large language models, has led to their integration into a variety of applications. A key phenomenon known as weak-to-strong generalization - where a strong model trained on a weak model's outputs surpasses the weak model in task performance - has gained significant attention. Yet, whether critical trustworthiness properties such as robustness, fairness, and privacy can generalize similarly remains an open question. In this work, we study this question by examining if a stronger model can inherit trustworthiness properties when fine-tuned on","authors_text":"Aounon Kumar, Himabindu Lakkaraju, Lillian Sun, Martin Pawelczyk, Zhenting Qi","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-31T12:40:02Z","title":"Generalizing Trust: Weak-to-Strong Trustworthiness in Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00418","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":"sha256:7cfcb121ac2a4a33581bd9b53d4a749f39010ad2bbf0ef33e1ab2df0c0b16da9","target":"record","created_at":"2026-07-05T09:56:05Z","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":"552f7437746b14423efffe1933151b71126368992e381952397b0016636532f8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-31T12:40:02Z","title_canon_sha256":"346bd1be5d4fac5a07399c296fb43a4f3ad4d8994798b7784dc54c4d8e8fc4a3"},"schema_version":"1.0","source":{"id":"2501.00418","kind":"arxiv","version":1}},"canonical_sha256":"debc489217cf0f47636043e3dbdc5cf6759d9d3080568376f96b05b7d930792f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"debc489217cf0f47636043e3dbdc5cf6759d9d3080568376f96b05b7d930792f","first_computed_at":"2026-07-05T09:56:05.622956Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:56:05.622956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4wTuY6esMn9JLzQksz/rpqrmG0+m3RCnZHZ8X9AN4mxuTfzq92jv4k1IxGG98dMmoFu+CtV3cvEKoyCKvEb8DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:56:05.623528Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.00418","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7cfcb121ac2a4a33581bd9b53d4a749f39010ad2bbf0ef33e1ab2df0c0b16da9","sha256:4bb571995341c6ef9e9b12604fb2956295ca4a2f2402f1b70baba0ce6ba5926f"],"state_sha256":"b2f1f8553a634ce408fb2983cc04f8c3ee37c6fb266050cc6aab1f7233af3b04"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T2zHtPhPigqU660CgBposw0wJ5Erwi11wes4iqio/dQexRoJopQSGB5OeYAC90hrprSrBtzj0iXPQZaHubNLDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T09:34:36.682369Z","bundle_sha256":"e1be42a7d6ef37ebe8ea319830405034b0c147940836dbe6a44fe830b1f915cb"}}