{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZJU6JFDOMYKV6UKJATU5HP5Y7E","short_pith_number":"pith:ZJU6JFDO","canonical_record":{"source":{"id":"2506.12321","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-14T03:02:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"98e877620c1108d5cf17a1d8b4ac5b40ccbcd530dd650950075bd6dbce076ad5","abstract_canon_sha256":"477e17414c283f916a603623940ca100af2882850b05a9f72723f45e207a6d85"},"schema_version":"1.0"},"canonical_sha256":"ca69e4946e66155f514904e9d3bfb8f90b0edae7d593274f5968134328a00122","source":{"kind":"arxiv","id":"2506.12321","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.12321","created_at":"2026-07-05T12:01:23Z"},{"alias_kind":"arxiv_version","alias_value":"2506.12321v2","created_at":"2026-07-05T12:01:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12321","created_at":"2026-07-05T12:01:23Z"},{"alias_kind":"pith_short_12","alias_value":"ZJU6JFDOMYKV","created_at":"2026-07-05T12:01:23Z"},{"alias_kind":"pith_short_16","alias_value":"ZJU6JFDOMYKV6UKJ","created_at":"2026-07-05T12:01:23Z"},{"alias_kind":"pith_short_8","alias_value":"ZJU6JFDO","created_at":"2026-07-05T12:01:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZJU6JFDOMYKV6UKJATU5HP5Y7E","target":"record","payload":{"canonical_record":{"source":{"id":"2506.12321","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-14T03:02:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"98e877620c1108d5cf17a1d8b4ac5b40ccbcd530dd650950075bd6dbce076ad5","abstract_canon_sha256":"477e17414c283f916a603623940ca100af2882850b05a9f72723f45e207a6d85"},"schema_version":"1.0"},"canonical_sha256":"ca69e4946e66155f514904e9d3bfb8f90b0edae7d593274f5968134328a00122","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:23.943763Z","signature_b64":"gqrbOLgr+gPwmhXUZLxRC+/NXbmihjfy6DxP6ocmGp82HQbvq2Wdhspyy8rzlGNiTqOAwVG6w0Z0lIRpRYeRCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca69e4946e66155f514904e9d3bfb8f90b0edae7d593274f5968134328a00122","last_reissued_at":"2026-07-05T12:01:23.943260Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:23.943260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.12321","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":"2026-07-05T12:01:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F5f6ZYbed3UB6D4gNgztf6NahcjnKrAVNKaXXDeytqcFexPQ6bNCppGhIv1rJ9+ZfAuz8tBpIia7gW4zytPpCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:01:47.017756Z"},"content_sha256":"60c6caeeb0429945d9393b2af2a9f4660367e2361edcd7d0c243e54726986fcb","schema_version":"1.0","event_id":"sha256:60c6caeeb0429945d9393b2af2a9f4660367e2361edcd7d0c243e54726986fcb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZJU6JFDOMYKV6UKJATU5HP5Y7E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Frequency: The Role of Redundancy in Large Language Model Memorization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chi-ho Lin, Jie Zhang, Lei Li, Qinghua Zhao, Zhongfeng Kang","submitted_at":"2025-06-14T03:02:42Z","abstract_excerpt":"Memorization in large language models poses critical risks for privacy and fairness as these systems scale to billions of parameters. While previous studies established correlations between memorization and factors like token frequency and repetition patterns, we revealed distinct response patterns: frequency increases minimally impact memorized samples (e.g. 0.09) while substantially affecting non-memorized samples (e.g., 0.25), with consistency observed across model scales. Through counterfactual analysis by perturbing sample prefixes and quantifying perturbation strength through token posit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12321","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/2506.12321/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":"2026-07-05T12:01:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5CQZmqXqqCNOaI9yVpridchGy1dk2sgABKGN3ptP1Jk+q0CXq2qgGMNMYMw8Da74dUtp2D6vwzVPWPZZoUq+Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:01:47.018307Z"},"content_sha256":"ea6b6e81501d0bcd228ec850702626c126dab904c95033540937ecb2d4cfd9f4","schema_version":"1.0","event_id":"sha256:ea6b6e81501d0bcd228ec850702626c126dab904c95033540937ecb2d4cfd9f4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZJU6JFDOMYKV6UKJATU5HP5Y7E/bundle.json","state_url":"https://pith.science/pith/ZJU6JFDOMYKV6UKJATU5HP5Y7E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZJU6JFDOMYKV6UKJATU5HP5Y7E/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":"2026-08-09T18:01:47Z","links":{"resolver":"https://pith.science/pith/ZJU6JFDOMYKV6UKJATU5HP5Y7E","bundle":"https://pith.science/pith/ZJU6JFDOMYKV6UKJATU5HP5Y7E/bundle.json","state":"https://pith.science/pith/ZJU6JFDOMYKV6UKJATU5HP5Y7E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZJU6JFDOMYKV6UKJATU5HP5Y7E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZJU6JFDOMYKV6UKJATU5HP5Y7E","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":"477e17414c283f916a603623940ca100af2882850b05a9f72723f45e207a6d85","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-14T03:02:42Z","title_canon_sha256":"98e877620c1108d5cf17a1d8b4ac5b40ccbcd530dd650950075bd6dbce076ad5"},"schema_version":"1.0","source":{"id":"2506.12321","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.12321","created_at":"2026-07-05T12:01:23Z"},{"alias_kind":"arxiv_version","alias_value":"2506.12321v2","created_at":"2026-07-05T12:01:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12321","created_at":"2026-07-05T12:01:23Z"},{"alias_kind":"pith_short_12","alias_value":"ZJU6JFDOMYKV","created_at":"2026-07-05T12:01:23Z"},{"alias_kind":"pith_short_16","alias_value":"ZJU6JFDOMYKV6UKJ","created_at":"2026-07-05T12:01:23Z"},{"alias_kind":"pith_short_8","alias_value":"ZJU6JFDO","created_at":"2026-07-05T12:01:23Z"}],"graph_snapshots":[{"event_id":"sha256:ea6b6e81501d0bcd228ec850702626c126dab904c95033540937ecb2d4cfd9f4","target":"graph","created_at":"2026-07-05T12:01:23Z","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/2506.12321/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Memorization in large language models poses critical risks for privacy and fairness as these systems scale to billions of parameters. While previous studies established correlations between memorization and factors like token frequency and repetition patterns, we revealed distinct response patterns: frequency increases minimally impact memorized samples (e.g. 0.09) while substantially affecting non-memorized samples (e.g., 0.25), with consistency observed across model scales. Through counterfactual analysis by perturbing sample prefixes and quantifying perturbation strength through token posit","authors_text":"Chi-ho Lin, Jie Zhang, Lei Li, Qinghua Zhao, Zhongfeng Kang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-14T03:02:42Z","title":"Beyond Frequency: The Role of Redundancy in Large Language Model Memorization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12321","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":"sha256:60c6caeeb0429945d9393b2af2a9f4660367e2361edcd7d0c243e54726986fcb","target":"record","created_at":"2026-07-05T12:01:23Z","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":"477e17414c283f916a603623940ca100af2882850b05a9f72723f45e207a6d85","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-14T03:02:42Z","title_canon_sha256":"98e877620c1108d5cf17a1d8b4ac5b40ccbcd530dd650950075bd6dbce076ad5"},"schema_version":"1.0","source":{"id":"2506.12321","kind":"arxiv","version":2}},"canonical_sha256":"ca69e4946e66155f514904e9d3bfb8f90b0edae7d593274f5968134328a00122","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca69e4946e66155f514904e9d3bfb8f90b0edae7d593274f5968134328a00122","first_computed_at":"2026-07-05T12:01:23.943260Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:01:23.943260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gqrbOLgr+gPwmhXUZLxRC+/NXbmihjfy6DxP6ocmGp82HQbvq2Wdhspyy8rzlGNiTqOAwVG6w0Z0lIRpRYeRCA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:01:23.943763Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.12321","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:60c6caeeb0429945d9393b2af2a9f4660367e2361edcd7d0c243e54726986fcb","sha256:ea6b6e81501d0bcd228ec850702626c126dab904c95033540937ecb2d4cfd9f4"],"state_sha256":"ad326729dd4a4475e448d8b8c8a9db4778e1d4fbc7a1a7d243dcf3bf638f8148"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FSLwX54VqGxkuGdi9hhrLHT0bSC08sD9lbtdEvqVZpzM4TyKUzemiOdteAR4RTtxTY+2hs2s1aE9XGU3nxiFDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T18:01:47.022275Z","bundle_sha256":"664c44e40a094159eefef74eba2646fbce2c1b493c051b459110e8adac9a8647"}}