{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BUZTD6GGFTXHTRIC2PTCBSO2XQ","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":"4746e18c85b6a39fe72b20c419676927d1a30a7c67f4e6b0d465f7badfd1d2e6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-14T17:44:22Z","title_canon_sha256":"1b42ee53e86e3b6e030eb3fd4195249bcf2c1c2a97631e79f9e169e3f7712fa9"},"schema_version":"1.0","source":{"id":"2406.10209","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10209","created_at":"2026-07-05T09:30:17Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10209v2","created_at":"2026-07-05T09:30:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10209","created_at":"2026-07-05T09:30:17Z"},{"alias_kind":"pith_short_12","alias_value":"BUZTD6GGFTXH","created_at":"2026-07-05T09:30:17Z"},{"alias_kind":"pith_short_16","alias_value":"BUZTD6GGFTXHTRIC","created_at":"2026-07-05T09:30:17Z"},{"alias_kind":"pith_short_8","alias_value":"BUZTD6GG","created_at":"2026-07-05T09:30:17Z"}],"graph_snapshots":[{"event_id":"sha256:89887ce62958685f511c2e00ed26c8c0dc85f14ed0c2b37ed5f44fd2740676f9","target":"graph","created_at":"2026-07-05T09:30:17Z","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/2406.10209/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models can memorize and repeat their training data, causing privacy and copyright risks. To mitigate memorization, we introduce a subtle modification to the next-token training objective that we call the goldfish loss. During training, randomly sampled subsets of tokens are excluded from the loss computation. These dropped tokens are not memorized by the model, which prevents verbatim reproduction of a complete chain of tokens from the training set. We run extensive experiments training billion-scale Llama-2 models, both pre-trained and trained from scratch, and demonstrate sign","authors_text":"Abhimanyu Hans, Abhinav Bhatele, Gowthami Somepalli, Hamid Kazemi, John Kirchenbauer, Jonas Geiping, Neel Jain, Prajwal Singhania, Siddharth Singh, Tom Goldstein, Yuxin Wen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-14T17:44:22Z","title":"Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10209","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:fefead2370e8e41cf89a63c594e2bdae0fffea5794e805a739279c377136f835","target":"record","created_at":"2026-07-05T09:30:17Z","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":"4746e18c85b6a39fe72b20c419676927d1a30a7c67f4e6b0d465f7badfd1d2e6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-14T17:44:22Z","title_canon_sha256":"1b42ee53e86e3b6e030eb3fd4195249bcf2c1c2a97631e79f9e169e3f7712fa9"},"schema_version":"1.0","source":{"id":"2406.10209","kind":"arxiv","version":2}},"canonical_sha256":"0d3331f8c62cee79c502d3e620c9dabc1a1c0c9033cf88cbedda84abba9fc1b5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d3331f8c62cee79c502d3e620c9dabc1a1c0c9033cf88cbedda84abba9fc1b5","first_computed_at":"2026-07-05T09:30:17.238708Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:30:17.238708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4BcNL5dc7hZfugyV0jRNcwffe3FAmnPjmALOXYdR5krvmJ8em7aWN1sxgwU6ZcOkzdU6+QLNlkas6pVYVhM0Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:30:17.239202Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.10209","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fefead2370e8e41cf89a63c594e2bdae0fffea5794e805a739279c377136f835","sha256:89887ce62958685f511c2e00ed26c8c0dc85f14ed0c2b37ed5f44fd2740676f9"],"state_sha256":"ada53fc99e5688b5aca49090590fdaf3c09d94ba51b943eacf936a7bd732d371"}