{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DULYARGIBP7V3A5SRGM7UEOIJT","short_pith_number":"pith:DULYARGI","canonical_record":{"source":{"id":"2406.11715","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-17T16:33:35Z","cross_cats_sorted":["cs.CL","cs.SE"],"title_canon_sha256":"2fd0dfa7733b88fb74b87b86446b6c42ff601e3aa9487fc09fa52b0b70994db3","abstract_canon_sha256":"0c344685a26fa2201ddad5f97c1f61eb6f44a75997aedab070ff3d939d1583f1"},"schema_version":"1.0"},"canonical_sha256":"1d178044c80bff5d83b28999fa11c84ce59ce5efd8a41a9ff923419937e959b3","source":{"kind":"arxiv","id":"2406.11715","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11715","created_at":"2026-07-05T09:25:44Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11715v2","created_at":"2026-07-05T09:25:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11715","created_at":"2026-07-05T09:25:44Z"},{"alias_kind":"pith_short_12","alias_value":"DULYARGIBP7V","created_at":"2026-07-05T09:25:44Z"},{"alias_kind":"pith_short_16","alias_value":"DULYARGIBP7V3A5S","created_at":"2026-07-05T09:25:44Z"},{"alias_kind":"pith_short_8","alias_value":"DULYARGI","created_at":"2026-07-05T09:25:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DULYARGIBP7V3A5SRGM7UEOIJT","target":"record","payload":{"canonical_record":{"source":{"id":"2406.11715","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-17T16:33:35Z","cross_cats_sorted":["cs.CL","cs.SE"],"title_canon_sha256":"2fd0dfa7733b88fb74b87b86446b6c42ff601e3aa9487fc09fa52b0b70994db3","abstract_canon_sha256":"0c344685a26fa2201ddad5f97c1f61eb6f44a75997aedab070ff3d939d1583f1"},"schema_version":"1.0"},"canonical_sha256":"1d178044c80bff5d83b28999fa11c84ce59ce5efd8a41a9ff923419937e959b3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:44.470491Z","signature_b64":"TgpadXrDbhHoYTvOGJd904GzuiMv6QNpkLLDqtFNAG9t67qWb+UxwphlIQiOSV6h30oKzPtM8GwhQb/iNVezDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d178044c80bff5d83b28999fa11c84ce59ce5efd8a41a9ff923419937e959b3","last_reissued_at":"2026-07-05T09:25:44.469978Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:44.469978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.11715","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":"2026-07-05T09:25:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MqExj+pufXYyTPDxpaauQxbTpmZVXxO2scYOtOAmz8WxsYLPQZJXvYiQUdfGlVLAICxWWOV5kIGXvhYGouJiBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T04:53:22.727689Z"},"content_sha256":"ab235813b2d3bd9935d60c99ea97ca50b7f47ce305ba4137caf89856205e055c","schema_version":"1.0","event_id":"sha256:ab235813b2d3bd9935d60c99ea97ca50b7f47ce305ba4137caf89856205e055c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DULYARGIBP7V3A5SRGM7UEOIJT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Measuring memorization in RLHF for code completion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SE"],"primary_cat":"cs.LG","authors_text":"Aneesh Pappu, Billy Porter, Ilia Shumailov, Jamie Hayes","submitted_at":"2024-06-17T16:33:35Z","abstract_excerpt":"Reinforcement learning with human feedback (RLHF) has become the dominant method to align large models to user preferences. Unlike fine-tuning, for which there are many studies regarding training data memorization, it is not clear how memorization is affected by or introduced in the RLHF alignment process. Understanding this relationship is important as real user data may be collected and used to align large models; if user data is memorized during RLHF and later regurgitated, this could raise privacy concerns. In addition to RLHF, other methods such as Direct Preference Optimization (DPO) and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11715","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/2406.11715/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":"2026-07-05T09:25:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HKv1VQm5UkJ8hO8+aZnT0sZdTjNieUEq77gQcZP5QeQQnJTNOZ9YdoMao8Jy0BHrhFA5Rca46AUumWSr4KT6Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T04:53:22.728614Z"},"content_sha256":"cc314cbfe01d4289877a6dc1eb8f4e0a26ad4908e31d65e957d4ef11228c7c8e","schema_version":"1.0","event_id":"sha256:cc314cbfe01d4289877a6dc1eb8f4e0a26ad4908e31d65e957d4ef11228c7c8e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DULYARGIBP7V3A5SRGM7UEOIJT/bundle.json","state_url":"https://pith.science/pith/DULYARGIBP7V3A5SRGM7UEOIJT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DULYARGIBP7V3A5SRGM7UEOIJT/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":"2026-08-11T04:53:22Z","links":{"resolver":"https://pith.science/pith/DULYARGIBP7V3A5SRGM7UEOIJT","bundle":"https://pith.science/pith/DULYARGIBP7V3A5SRGM7UEOIJT/bundle.json","state":"https://pith.science/pith/DULYARGIBP7V3A5SRGM7UEOIJT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DULYARGIBP7V3A5SRGM7UEOIJT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DULYARGIBP7V3A5SRGM7UEOIJT","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":"0c344685a26fa2201ddad5f97c1f61eb6f44a75997aedab070ff3d939d1583f1","cross_cats_sorted":["cs.CL","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-17T16:33:35Z","title_canon_sha256":"2fd0dfa7733b88fb74b87b86446b6c42ff601e3aa9487fc09fa52b0b70994db3"},"schema_version":"1.0","source":{"id":"2406.11715","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11715","created_at":"2026-07-05T09:25:44Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11715v2","created_at":"2026-07-05T09:25:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11715","created_at":"2026-07-05T09:25:44Z"},{"alias_kind":"pith_short_12","alias_value":"DULYARGIBP7V","created_at":"2026-07-05T09:25:44Z"},{"alias_kind":"pith_short_16","alias_value":"DULYARGIBP7V3A5S","created_at":"2026-07-05T09:25:44Z"},{"alias_kind":"pith_short_8","alias_value":"DULYARGI","created_at":"2026-07-05T09:25:44Z"}],"graph_snapshots":[{"event_id":"sha256:cc314cbfe01d4289877a6dc1eb8f4e0a26ad4908e31d65e957d4ef11228c7c8e","target":"graph","created_at":"2026-07-05T09:25:44Z","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/2406.11715/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with human feedback (RLHF) has become the dominant method to align large models to user preferences. Unlike fine-tuning, for which there are many studies regarding training data memorization, it is not clear how memorization is affected by or introduced in the RLHF alignment process. Understanding this relationship is important as real user data may be collected and used to align large models; if user data is memorized during RLHF and later regurgitated, this could raise privacy concerns. In addition to RLHF, other methods such as Direct Preference Optimization (DPO) and","authors_text":"Aneesh Pappu, Billy Porter, Ilia Shumailov, Jamie Hayes","cross_cats":["cs.CL","cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-17T16:33:35Z","title":"Measuring memorization in RLHF for code completion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11715","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:ab235813b2d3bd9935d60c99ea97ca50b7f47ce305ba4137caf89856205e055c","target":"record","created_at":"2026-07-05T09:25:44Z","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":"0c344685a26fa2201ddad5f97c1f61eb6f44a75997aedab070ff3d939d1583f1","cross_cats_sorted":["cs.CL","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-17T16:33:35Z","title_canon_sha256":"2fd0dfa7733b88fb74b87b86446b6c42ff601e3aa9487fc09fa52b0b70994db3"},"schema_version":"1.0","source":{"id":"2406.11715","kind":"arxiv","version":2}},"canonical_sha256":"1d178044c80bff5d83b28999fa11c84ce59ce5efd8a41a9ff923419937e959b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d178044c80bff5d83b28999fa11c84ce59ce5efd8a41a9ff923419937e959b3","first_computed_at":"2026-07-05T09:25:44.469978Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:25:44.469978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TgpadXrDbhHoYTvOGJd904GzuiMv6QNpkLLDqtFNAG9t67qWb+UxwphlIQiOSV6h30oKzPtM8GwhQb/iNVezDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:25:44.470491Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.11715","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ab235813b2d3bd9935d60c99ea97ca50b7f47ce305ba4137caf89856205e055c","sha256:cc314cbfe01d4289877a6dc1eb8f4e0a26ad4908e31d65e957d4ef11228c7c8e"],"state_sha256":"730bca6d2cef4c1ce69343ce26e37a762d0aefabcf6726df8276406fa4dae562"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iRegvj5TIV0bFzTx/K3ZFPq8zQ5jRgBN1KCBeUWNqItBTUOVG8KmpHz8aqtb624Kjn23PY+U+XvlbpEDiaSZAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T04:53:22.734705Z","bundle_sha256":"2ac1b428bbfc3913f3b3f9263933344806a09f067e3f53e5468eb0ed4bf573a0"}}