{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:P5LKU6IDQZXHAQOE2ZNBRL7LMI","short_pith_number":"pith:P5LKU6ID","canonical_record":{"source":{"id":"2404.15146","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-23T15:49:37Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"9e8a0db429e4b3605dd081228adcd2ab54cfcdd44954c653d548d71970e9e4c5","abstract_canon_sha256":"cb00f2b02b0a259c479e527751c9d798c9124c2773e9939aa0c178a56c616b60"},"schema_version":"1.0"},"canonical_sha256":"7f56aa7903866e7041c4d65a18afeb621b1f2875ea326c7b172906802ce69ba8","source":{"kind":"arxiv","id":"2404.15146","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.15146","created_at":"2026-07-05T09:33:59Z"},{"alias_kind":"arxiv_version","alias_value":"2404.15146v3","created_at":"2026-07-05T09:33:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.15146","created_at":"2026-07-05T09:33:59Z"},{"alias_kind":"pith_short_12","alias_value":"P5LKU6IDQZXH","created_at":"2026-07-05T09:33:59Z"},{"alias_kind":"pith_short_16","alias_value":"P5LKU6IDQZXHAQOE","created_at":"2026-07-05T09:33:59Z"},{"alias_kind":"pith_short_8","alias_value":"P5LKU6ID","created_at":"2026-07-05T09:33:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:P5LKU6IDQZXHAQOE2ZNBRL7LMI","target":"record","payload":{"canonical_record":{"source":{"id":"2404.15146","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-23T15:49:37Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"9e8a0db429e4b3605dd081228adcd2ab54cfcdd44954c653d548d71970e9e4c5","abstract_canon_sha256":"cb00f2b02b0a259c479e527751c9d798c9124c2773e9939aa0c178a56c616b60"},"schema_version":"1.0"},"canonical_sha256":"7f56aa7903866e7041c4d65a18afeb621b1f2875ea326c7b172906802ce69ba8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:33:59.891793Z","signature_b64":"WLjC+gIMhNwnAnkxSXSBcBC+oQzu0btYnPwLX6FgpXmldwZAZNc/bsYolQKJfi3H0vpBJbI9yqiTyuVAAQYEDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f56aa7903866e7041c4d65a18afeb621b1f2875ea326c7b172906802ce69ba8","last_reissued_at":"2026-07-05T09:33:59.891220Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:33:59.891220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.15146","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:33:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ksBgQ+cmLri79HeYOyliWzWz37gdaO1ouLqyQ3xtDiOaI7/e6jqYzWTPfBZmk8RnI2rmZQc/4V/81fPz0dFCDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:15:39.333746Z"},"content_sha256":"e8d880f075ee2940c3e304ec3f42d559ca2ecc39127a528dc52bc7f1e360f390","schema_version":"1.0","event_id":"sha256:e8d880f075ee2940c3e304ec3f42d559ca2ecc39127a528dc52bc7f1e360f390"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:P5LKU6IDQZXHAQOE2ZNBRL7LMI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rethinking LLM Memorization through the Lens of Adversarial Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Avi Schwarzschild, J. Zico Kolter, Pratyush Maini, Zachary C. Lipton, Zhili Feng","submitted_at":"2024-04-23T15:49:37Z","abstract_excerpt":"Large language models (LLMs) trained on web-scale datasets raise substantial concerns regarding permissible data usage. One major question is whether these models \"memorize\" all their training data or they integrate many data sources in some way more akin to how a human would learn and synthesize information. The answer hinges, to a large degree, on how we define memorization. In this work, we propose the Adversarial Compression Ratio (ACR) as a metric for assessing memorization in LLMs. A given string from the training data is considered memorized if it can be elicited by a prompt (much) shor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.15146","kind":"arxiv","version":3},"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/2404.15146/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":"2026-07-05T09:33:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sO160MqefWEN3kTneh/ypFRF1Y2QjH9IRL8XE/TxgT+3rslfDuAuzCLTowgaZiHWVgXqrj+73ScnNwkU5x7TDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:15:39.334249Z"},"content_sha256":"25d0de40fee67a8ed164e2f79bef4c20611d56f1245e766a73c62eacc4d6301c","schema_version":"1.0","event_id":"sha256:25d0de40fee67a8ed164e2f79bef4c20611d56f1245e766a73c62eacc4d6301c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P5LKU6IDQZXHAQOE2ZNBRL7LMI/bundle.json","state_url":"https://pith.science/pith/P5LKU6IDQZXHAQOE2ZNBRL7LMI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P5LKU6IDQZXHAQOE2ZNBRL7LMI/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":"2026-08-05T08:15:39Z","links":{"resolver":"https://pith.science/pith/P5LKU6IDQZXHAQOE2ZNBRL7LMI","bundle":"https://pith.science/pith/P5LKU6IDQZXHAQOE2ZNBRL7LMI/bundle.json","state":"https://pith.science/pith/P5LKU6IDQZXHAQOE2ZNBRL7LMI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P5LKU6IDQZXHAQOE2ZNBRL7LMI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:P5LKU6IDQZXHAQOE2ZNBRL7LMI","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":"cb00f2b02b0a259c479e527751c9d798c9124c2773e9939aa0c178a56c616b60","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-23T15:49:37Z","title_canon_sha256":"9e8a0db429e4b3605dd081228adcd2ab54cfcdd44954c653d548d71970e9e4c5"},"schema_version":"1.0","source":{"id":"2404.15146","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.15146","created_at":"2026-07-05T09:33:59Z"},{"alias_kind":"arxiv_version","alias_value":"2404.15146v3","created_at":"2026-07-05T09:33:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.15146","created_at":"2026-07-05T09:33:59Z"},{"alias_kind":"pith_short_12","alias_value":"P5LKU6IDQZXH","created_at":"2026-07-05T09:33:59Z"},{"alias_kind":"pith_short_16","alias_value":"P5LKU6IDQZXHAQOE","created_at":"2026-07-05T09:33:59Z"},{"alias_kind":"pith_short_8","alias_value":"P5LKU6ID","created_at":"2026-07-05T09:33:59Z"}],"graph_snapshots":[{"event_id":"sha256:25d0de40fee67a8ed164e2f79bef4c20611d56f1245e766a73c62eacc4d6301c","target":"graph","created_at":"2026-07-05T09:33:59Z","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/2404.15146/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) trained on web-scale datasets raise substantial concerns regarding permissible data usage. One major question is whether these models \"memorize\" all their training data or they integrate many data sources in some way more akin to how a human would learn and synthesize information. The answer hinges, to a large degree, on how we define memorization. In this work, we propose the Adversarial Compression Ratio (ACR) as a metric for assessing memorization in LLMs. A given string from the training data is considered memorized if it can be elicited by a prompt (much) shor","authors_text":"Avi Schwarzschild, J. Zico Kolter, Pratyush Maini, Zachary C. Lipton, Zhili Feng","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-23T15:49:37Z","title":"Rethinking LLM Memorization through the Lens of Adversarial Compression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.15146","kind":"arxiv","version":3},"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:e8d880f075ee2940c3e304ec3f42d559ca2ecc39127a528dc52bc7f1e360f390","target":"record","created_at":"2026-07-05T09:33:59Z","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":"cb00f2b02b0a259c479e527751c9d798c9124c2773e9939aa0c178a56c616b60","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-23T15:49:37Z","title_canon_sha256":"9e8a0db429e4b3605dd081228adcd2ab54cfcdd44954c653d548d71970e9e4c5"},"schema_version":"1.0","source":{"id":"2404.15146","kind":"arxiv","version":3}},"canonical_sha256":"7f56aa7903866e7041c4d65a18afeb621b1f2875ea326c7b172906802ce69ba8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7f56aa7903866e7041c4d65a18afeb621b1f2875ea326c7b172906802ce69ba8","first_computed_at":"2026-07-05T09:33:59.891220Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:33:59.891220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WLjC+gIMhNwnAnkxSXSBcBC+oQzu0btYnPwLX6FgpXmldwZAZNc/bsYolQKJfi3H0vpBJbI9yqiTyuVAAQYEDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:33:59.891793Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.15146","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e8d880f075ee2940c3e304ec3f42d559ca2ecc39127a528dc52bc7f1e360f390","sha256:25d0de40fee67a8ed164e2f79bef4c20611d56f1245e766a73c62eacc4d6301c"],"state_sha256":"01a904ea82456a2726297c9c91bda2f59ab0170b444ae3f8b8c8205886998c06"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qyBwvykk3Pn8lKIB2St8WyxZvIJwPz0fBE+OVoDV5j4n5/+KskxquleaBX5E3wmR+Nt3yj2wO4nos+Y8O8PyDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T08:15:39.341492Z","bundle_sha256":"dea097f7561949cb0282070ea881fb53906df23a11e216b25dfcce28a864eda5"}}