{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MTPRZJ4G7HJSVWXZBOAOLB3L5L","short_pith_number":"pith:MTPRZJ4G","canonical_record":{"source":{"id":"2412.01014","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-02T00:17:43Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"5c481f9acca49335b68ea2fad35d39ab47338fe8ad8ad5ac02bc197afc642840","abstract_canon_sha256":"e5f12da5fdb251dfc28c5cc7e70773fa8093a062ce5a2399d22328570c492d99"},"schema_version":"1.0"},"canonical_sha256":"64df1ca786f9d32adaf90b80e5876beaf65afa3084a3ccfef4a47e3c32c9d541","source":{"kind":"arxiv","id":"2412.01014","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.01014","created_at":"2026-07-05T09:42:52Z"},{"alias_kind":"arxiv_version","alias_value":"2412.01014v1","created_at":"2026-07-05T09:42:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01014","created_at":"2026-07-05T09:42:52Z"},{"alias_kind":"pith_short_12","alias_value":"MTPRZJ4G7HJS","created_at":"2026-07-05T09:42:52Z"},{"alias_kind":"pith_short_16","alias_value":"MTPRZJ4G7HJSVWXZ","created_at":"2026-07-05T09:42:52Z"},{"alias_kind":"pith_short_8","alias_value":"MTPRZJ4G","created_at":"2026-07-05T09:42:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MTPRZJ4G7HJSVWXZBOAOLB3L5L","target":"record","payload":{"canonical_record":{"source":{"id":"2412.01014","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-02T00:17:43Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"5c481f9acca49335b68ea2fad35d39ab47338fe8ad8ad5ac02bc197afc642840","abstract_canon_sha256":"e5f12da5fdb251dfc28c5cc7e70773fa8093a062ce5a2399d22328570c492d99"},"schema_version":"1.0"},"canonical_sha256":"64df1ca786f9d32adaf90b80e5876beaf65afa3084a3ccfef4a47e3c32c9d541","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:52.089079Z","signature_b64":"uK7YziV0fjqEzXQzb3qWwCcqqpq9vTk09rUKsU76jZ/7Xlk8eIIU7RB+vq6Yl8LQnDLdgptwt/fPpmUY9OMWAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64df1ca786f9d32adaf90b80e5876beaf65afa3084a3ccfef4a47e3c32c9d541","last_reissued_at":"2026-07-05T09:42:52.088535Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:52.088535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.01014","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":"2026-07-05T09:42:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NezRTRlODxskKuVwFmEXnAwGpDXgQwtAQ15rlzFrRHp20XRkXrM1BZyeUE4KKGl3gxM36JIN5rvQoNDnd/6lCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T07:29:13.029977Z"},"content_sha256":"76805c8fa17e33730b907076267268c40a8c818621d28d8d1c395ece69ea9ef5","schema_version":"1.0","event_id":"sha256:76805c8fa17e33730b907076267268c40a8c818621d28d8d1c395ece69ea9ef5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MTPRZJ4G7HJSVWXZBOAOLB3L5L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Detecting Memorization in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Eduardo Slonski","submitted_at":"2024-12-02T00:17:43Z","abstract_excerpt":"Large language models (LLMs) have achieved impressive results in natural language processing but are prone to memorizing portions of their training data, which can compromise evaluation metrics, raise privacy concerns, and limit generalization. Traditional methods for detecting memorization rely on output probabilities or loss functions, often lacking precision due to confounding factors like common language patterns. In this paper, we introduce an analytical method that precisely detects memorization by examining neuron activations within the LLM. By identifying specific activation patterns t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01014","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/2412.01014/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":"2026-07-05T09:42:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qHmApqBiJtLkEhcafJleB2zCOZN/znQg/8cSY8snY+DIvxKn94f12dwDEpij+y+du9wlBOqjHpg0pmmQcR3jCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T07:29:13.030882Z"},"content_sha256":"853c47b0943373c51e18a0f6d5d9f68905c5bafb7bb59410bbcd8e9006337fbf","schema_version":"1.0","event_id":"sha256:853c47b0943373c51e18a0f6d5d9f68905c5bafb7bb59410bbcd8e9006337fbf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MTPRZJ4G7HJSVWXZBOAOLB3L5L/bundle.json","state_url":"https://pith.science/pith/MTPRZJ4G7HJSVWXZBOAOLB3L5L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MTPRZJ4G7HJSVWXZBOAOLB3L5L/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":"2026-08-13T07:29:13Z","links":{"resolver":"https://pith.science/pith/MTPRZJ4G7HJSVWXZBOAOLB3L5L","bundle":"https://pith.science/pith/MTPRZJ4G7HJSVWXZBOAOLB3L5L/bundle.json","state":"https://pith.science/pith/MTPRZJ4G7HJSVWXZBOAOLB3L5L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MTPRZJ4G7HJSVWXZBOAOLB3L5L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MTPRZJ4G7HJSVWXZBOAOLB3L5L","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":"e5f12da5fdb251dfc28c5cc7e70773fa8093a062ce5a2399d22328570c492d99","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-02T00:17:43Z","title_canon_sha256":"5c481f9acca49335b68ea2fad35d39ab47338fe8ad8ad5ac02bc197afc642840"},"schema_version":"1.0","source":{"id":"2412.01014","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.01014","created_at":"2026-07-05T09:42:52Z"},{"alias_kind":"arxiv_version","alias_value":"2412.01014v1","created_at":"2026-07-05T09:42:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01014","created_at":"2026-07-05T09:42:52Z"},{"alias_kind":"pith_short_12","alias_value":"MTPRZJ4G7HJS","created_at":"2026-07-05T09:42:52Z"},{"alias_kind":"pith_short_16","alias_value":"MTPRZJ4G7HJSVWXZ","created_at":"2026-07-05T09:42:52Z"},{"alias_kind":"pith_short_8","alias_value":"MTPRZJ4G","created_at":"2026-07-05T09:42:52Z"}],"graph_snapshots":[{"event_id":"sha256:853c47b0943373c51e18a0f6d5d9f68905c5bafb7bb59410bbcd8e9006337fbf","target":"graph","created_at":"2026-07-05T09:42:52Z","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/2412.01014/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have achieved impressive results in natural language processing but are prone to memorizing portions of their training data, which can compromise evaluation metrics, raise privacy concerns, and limit generalization. Traditional methods for detecting memorization rely on output probabilities or loss functions, often lacking precision due to confounding factors like common language patterns. In this paper, we introduce an analytical method that precisely detects memorization by examining neuron activations within the LLM. By identifying specific activation patterns t","authors_text":"Eduardo Slonski","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-02T00:17:43Z","title":"Detecting Memorization in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01014","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":"sha256:76805c8fa17e33730b907076267268c40a8c818621d28d8d1c395ece69ea9ef5","target":"record","created_at":"2026-07-05T09:42:52Z","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":"e5f12da5fdb251dfc28c5cc7e70773fa8093a062ce5a2399d22328570c492d99","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-02T00:17:43Z","title_canon_sha256":"5c481f9acca49335b68ea2fad35d39ab47338fe8ad8ad5ac02bc197afc642840"},"schema_version":"1.0","source":{"id":"2412.01014","kind":"arxiv","version":1}},"canonical_sha256":"64df1ca786f9d32adaf90b80e5876beaf65afa3084a3ccfef4a47e3c32c9d541","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"64df1ca786f9d32adaf90b80e5876beaf65afa3084a3ccfef4a47e3c32c9d541","first_computed_at":"2026-07-05T09:42:52.088535Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:42:52.088535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uK7YziV0fjqEzXQzb3qWwCcqqpq9vTk09rUKsU76jZ/7Xlk8eIIU7RB+vq6Yl8LQnDLdgptwt/fPpmUY9OMWAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:42:52.089079Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.01014","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:76805c8fa17e33730b907076267268c40a8c818621d28d8d1c395ece69ea9ef5","sha256:853c47b0943373c51e18a0f6d5d9f68905c5bafb7bb59410bbcd8e9006337fbf"],"state_sha256":"d17196ed3b2d8d27cfb10ef67ca117fec597ddfc5d2ed280cfd31e1109940a7c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xALoi9jHFZz5OcCMJh0BsucbuzqzcdMlq8VIl7n+K4jcMHXe5AqidrvV9Sz2O7qQUug7jFHz4HT1QRC3XfsaBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T07:29:13.039189Z","bundle_sha256":"d45beea8a95f7af46ee7d7b4e70a60fabd85ca9dee1077dcecd1e9a567bc37d2"}}