{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2XF7V3ZK222GXKEDBVGVHV32QT","short_pith_number":"pith:2XF7V3ZK","canonical_record":{"source":{"id":"2506.09591","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-11T10:42:27Z","cross_cats_sorted":[],"title_canon_sha256":"97a166f6f72ffc6e08a165e67b7d137494aa1b9f45f04d7ee50742cf713c1134","abstract_canon_sha256":"439a3c9d305ac8818a839b67997bd2b0668820d352ebba5f712e250d78393871"},"schema_version":"1.0"},"canonical_sha256":"d5cbfaef2ad6b46ba8830d4d53d77a84e7c0faef89dd1b22337edc1dd1ee4047","source":{"kind":"arxiv","id":"2506.09591","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.09591","created_at":"2026-07-05T11:19:39Z"},{"alias_kind":"arxiv_version","alias_value":"2506.09591v1","created_at":"2026-07-05T11:19:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.09591","created_at":"2026-07-05T11:19:39Z"},{"alias_kind":"pith_short_12","alias_value":"2XF7V3ZK222G","created_at":"2026-07-05T11:19:39Z"},{"alias_kind":"pith_short_16","alias_value":"2XF7V3ZK222GXKED","created_at":"2026-07-05T11:19:39Z"},{"alias_kind":"pith_short_8","alias_value":"2XF7V3ZK","created_at":"2026-07-05T11:19:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2XF7V3ZK222GXKEDBVGVHV32QT","target":"record","payload":{"canonical_record":{"source":{"id":"2506.09591","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-11T10:42:27Z","cross_cats_sorted":[],"title_canon_sha256":"97a166f6f72ffc6e08a165e67b7d137494aa1b9f45f04d7ee50742cf713c1134","abstract_canon_sha256":"439a3c9d305ac8818a839b67997bd2b0668820d352ebba5f712e250d78393871"},"schema_version":"1.0"},"canonical_sha256":"d5cbfaef2ad6b46ba8830d4d53d77a84e7c0faef89dd1b22337edc1dd1ee4047","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:39.446500Z","signature_b64":"k9rjp5uFKHHHC6g10ay8TJJkY7AVHGU8spxGq7CppYUJhdQbfVH/ZyPCpJ7wZ4dqlivsXsVmTi4GUEjPMSTiAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5cbfaef2ad6b46ba8830d4d53d77a84e7c0faef89dd1b22337edc1dd1ee4047","last_reissued_at":"2026-07-05T11:19:39.446080Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:39.446080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.09591","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":"2026-07-05T11:19:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s1ITTXW7MMd/DCqX9kBVTssn8Y/8gOCx93QgD2JEsNJysY72MNOLQ9VtzWUsVc9ilpzJkvMXX3T5OcO9ksKvBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T15:01:07.589180Z"},"content_sha256":"a4117a4c256bc0249062aa259febaf3bb32e94a5a250e2ba12d25ada95158367","schema_version":"1.0","event_id":"sha256:a4117a4c256bc0249062aa259febaf3bb32e94a5a250e2ba12d25ada95158367"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2XF7V3ZK222GXKEDBVGVHV32QT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Memorization in Language Models through the Lens of Intrinsic Dimension","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Stefan Arnold","submitted_at":"2025-06-11T10:42:27Z","abstract_excerpt":"Language Models (LMs) are prone to memorizing parts of their data during training and unintentionally emitting them at generation time, raising concerns about privacy leakage and disclosure of intellectual property. While previous research has identified properties such as context length, parameter size, and duplication frequency, as key drivers of unintended memorization, little is known about how the latent structure modulates this rate of memorization. We investigate the role of Intrinsic Dimension (ID), a geometric proxy for the structural complexity of a sequence in latent space, in modul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.09591","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/2506.09591/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":"2026-07-05T11:19:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R2vnWj/z9e87vFFqj+hEL40sxy2eTq56jovjH5v/ii6vDSpCxwbhqTy/AAoehZNqqq5jI/aoTImfPeq8mkwlAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T15:01:07.589720Z"},"content_sha256":"ac62827e3ac8df384c61c24cbbb5adce61aec26c2f873efe6bbf031f66d59107","schema_version":"1.0","event_id":"sha256:ac62827e3ac8df384c61c24cbbb5adce61aec26c2f873efe6bbf031f66d59107"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2XF7V3ZK222GXKEDBVGVHV32QT/bundle.json","state_url":"https://pith.science/pith/2XF7V3ZK222GXKEDBVGVHV32QT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2XF7V3ZK222GXKEDBVGVHV32QT/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":"2026-08-15T15:01:07Z","links":{"resolver":"https://pith.science/pith/2XF7V3ZK222GXKEDBVGVHV32QT","bundle":"https://pith.science/pith/2XF7V3ZK222GXKEDBVGVHV32QT/bundle.json","state":"https://pith.science/pith/2XF7V3ZK222GXKEDBVGVHV32QT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2XF7V3ZK222GXKEDBVGVHV32QT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2XF7V3ZK222GXKEDBVGVHV32QT","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":"439a3c9d305ac8818a839b67997bd2b0668820d352ebba5f712e250d78393871","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-11T10:42:27Z","title_canon_sha256":"97a166f6f72ffc6e08a165e67b7d137494aa1b9f45f04d7ee50742cf713c1134"},"schema_version":"1.0","source":{"id":"2506.09591","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.09591","created_at":"2026-07-05T11:19:39Z"},{"alias_kind":"arxiv_version","alias_value":"2506.09591v1","created_at":"2026-07-05T11:19:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.09591","created_at":"2026-07-05T11:19:39Z"},{"alias_kind":"pith_short_12","alias_value":"2XF7V3ZK222G","created_at":"2026-07-05T11:19:39Z"},{"alias_kind":"pith_short_16","alias_value":"2XF7V3ZK222GXKED","created_at":"2026-07-05T11:19:39Z"},{"alias_kind":"pith_short_8","alias_value":"2XF7V3ZK","created_at":"2026-07-05T11:19:39Z"}],"graph_snapshots":[{"event_id":"sha256:ac62827e3ac8df384c61c24cbbb5adce61aec26c2f873efe6bbf031f66d59107","target":"graph","created_at":"2026-07-05T11:19:39Z","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/2506.09591/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language Models (LMs) are prone to memorizing parts of their data during training and unintentionally emitting them at generation time, raising concerns about privacy leakage and disclosure of intellectual property. While previous research has identified properties such as context length, parameter size, and duplication frequency, as key drivers of unintended memorization, little is known about how the latent structure modulates this rate of memorization. We investigate the role of Intrinsic Dimension (ID), a geometric proxy for the structural complexity of a sequence in latent space, in modul","authors_text":"Stefan Arnold","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-11T10:42:27Z","title":"Memorization in Language Models through the Lens of Intrinsic Dimension"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.09591","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:a4117a4c256bc0249062aa259febaf3bb32e94a5a250e2ba12d25ada95158367","target":"record","created_at":"2026-07-05T11:19:39Z","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":"439a3c9d305ac8818a839b67997bd2b0668820d352ebba5f712e250d78393871","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-11T10:42:27Z","title_canon_sha256":"97a166f6f72ffc6e08a165e67b7d137494aa1b9f45f04d7ee50742cf713c1134"},"schema_version":"1.0","source":{"id":"2506.09591","kind":"arxiv","version":1}},"canonical_sha256":"d5cbfaef2ad6b46ba8830d4d53d77a84e7c0faef89dd1b22337edc1dd1ee4047","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d5cbfaef2ad6b46ba8830d4d53d77a84e7c0faef89dd1b22337edc1dd1ee4047","first_computed_at":"2026-07-05T11:19:39.446080Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:39.446080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k9rjp5uFKHHHC6g10ay8TJJkY7AVHGU8spxGq7CppYUJhdQbfVH/ZyPCpJ7wZ4dqlivsXsVmTi4GUEjPMSTiAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:39.446500Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.09591","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a4117a4c256bc0249062aa259febaf3bb32e94a5a250e2ba12d25ada95158367","sha256:ac62827e3ac8df384c61c24cbbb5adce61aec26c2f873efe6bbf031f66d59107"],"state_sha256":"aebf4f7e392ca47c1fe943e665d4145020cc86cd6f7f8134813bd6402f89f318"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"00fckGcPuz5Fps7fH16eOF7J89JBO1WOUVGX5Zl8fMJ7VIxx7eXZaxZjz+3nwC2z9MYA1VJzEp6NIihfATpoAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T15:01:07.597493Z","bundle_sha256":"edd6dd4b5d4ab5ff73858d42304a61d84e21729c63f4183d297f7100ac583add"}}