{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3OSOOW6MR6KN3M3OD4OGZC4BCC","short_pith_number":"pith:3OSOOW6M","schema_version":"1.0","canonical_sha256":"dba4e75bcc8f94ddb36e1f1c6c8b8110af97ecfe0573a7d027bab8e4a08f76e9","source":{"kind":"arxiv","id":"2503.07501","version":1},"attestation_state":"computed","paper":{"title":"Trustworthy Machine Learning via Memorization and the Granular Long-Tail: A Survey on Interactions, Tradeoffs, and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Johannes Bjerva, Qiongxiu Li, Xiaoyu Luo, Yiyi Chen","submitted_at":"2025-03-10T16:20:29Z","abstract_excerpt":"The role of memorization in machine learning (ML) has garnered significant attention, particularly as modern models are empirically observed to memorize fragments of training data. Previous theoretical analyses, such as Feldman's seminal work, attribute memorization to the prevalence of long-tail distributions in training data, proving it unavoidable for samples that lie in the tail of the distribution. However, the intersection of memorization and trustworthy ML research reveals critical gaps. While prior research in memorization in trustworthy ML has solely focused on class imbalance, recent"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2503.07501","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-10T16:20:29Z","cross_cats_sorted":[],"title_canon_sha256":"cb98f35270636ca230d1ba8a1915995844781f174d6be014a2e9c07b786321ae","abstract_canon_sha256":"689950f67bcb6f2542053eaa6829fed889cd8319220be8f30e63b67ebfb5a355"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:57.637392Z","signature_b64":"FcGIMjWwrrrYs5P+ptgcCjcb963cF7L6V++0i2YpgJkjtP6QM6Ci0rn7H/E35nNg5DmR5zbUZxYEH1B5BSeLBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dba4e75bcc8f94ddb36e1f1c6c8b8110af97ecfe0573a7d027bab8e4a08f76e9","last_reissued_at":"2026-07-05T10:27:57.636738Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:57.636738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Trustworthy Machine Learning via Memorization and the Granular Long-Tail: A Survey on Interactions, Tradeoffs, and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Johannes Bjerva, Qiongxiu Li, Xiaoyu Luo, Yiyi Chen","submitted_at":"2025-03-10T16:20:29Z","abstract_excerpt":"The role of memorization in machine learning (ML) has garnered significant attention, particularly as modern models are empirically observed to memorize fragments of training data. Previous theoretical analyses, such as Feldman's seminal work, attribute memorization to the prevalence of long-tail distributions in training data, proving it unavoidable for samples that lie in the tail of the distribution. However, the intersection of memorization and trustworthy ML research reveals critical gaps. While prior research in memorization in trustworthy ML has solely focused on class imbalance, recent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.07501","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/2503.07501/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2503.07501","created_at":"2026-07-05T10:27:57.636811+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.07501v1","created_at":"2026-07-05T10:27:57.636811+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.07501","created_at":"2026-07-05T10:27:57.636811+00:00"},{"alias_kind":"pith_short_12","alias_value":"3OSOOW6MR6KN","created_at":"2026-07-05T10:27:57.636811+00:00"},{"alias_kind":"pith_short_16","alias_value":"3OSOOW6MR6KN3M3O","created_at":"2026-07-05T10:27:57.636811+00:00"},{"alias_kind":"pith_short_8","alias_value":"3OSOOW6M","created_at":"2026-07-05T10:27:57.636811+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.07180","citing_title":"Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3OSOOW6MR6KN3M3OD4OGZC4BCC","json":"https://pith.science/pith/3OSOOW6MR6KN3M3OD4OGZC4BCC.json","graph_json":"https://pith.science/api/pith-number/3OSOOW6MR6KN3M3OD4OGZC4BCC/graph.json","events_json":"https://pith.science/api/pith-number/3OSOOW6MR6KN3M3OD4OGZC4BCC/events.json","paper":"https://pith.science/paper/3OSOOW6M"},"agent_actions":{"view_html":"https://pith.science/pith/3OSOOW6MR6KN3M3OD4OGZC4BCC","download_json":"https://pith.science/pith/3OSOOW6MR6KN3M3OD4OGZC4BCC.json","view_paper":"https://pith.science/paper/3OSOOW6M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.07501&json=true","fetch_graph":"https://pith.science/api/pith-number/3OSOOW6MR6KN3M3OD4OGZC4BCC/graph.json","fetch_events":"https://pith.science/api/pith-number/3OSOOW6MR6KN3M3OD4OGZC4BCC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3OSOOW6MR6KN3M3OD4OGZC4BCC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3OSOOW6MR6KN3M3OD4OGZC4BCC/action/storage_attestation","attest_author":"https://pith.science/pith/3OSOOW6MR6KN3M3OD4OGZC4BCC/action/author_attestation","sign_citation":"https://pith.science/pith/3OSOOW6MR6KN3M3OD4OGZC4BCC/action/citation_signature","submit_replication":"https://pith.science/pith/3OSOOW6MR6KN3M3OD4OGZC4BCC/action/replication_record"}},"created_at":"2026-07-05T10:27:57.636811+00:00","updated_at":"2026-07-05T10:27:57.636811+00:00"}