{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KEDTEL7JOQGT2NCIDO2DCTW4GZ","short_pith_number":"pith:KEDTEL7J","schema_version":"1.0","canonical_sha256":"5107322fe9740d3d34481bb4314edc364f28b7df0ab7820a70b8c4032372a8d5","source":{"kind":"arxiv","id":"2607.21999","version":1},"attestation_state":"computed","paper":{"title":"From Perturbation Correction to Geometry-Aware Sampling: Sharpness-Guided Equilibrium Sampling for Balanced Flat Minima in Long-Tailed Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jiaxin Deng, Junbiao Pang","submitted_at":"2026-07-24T05:56:00Z","abstract_excerpt":"Long-tailed learning couples two sources of poor generalization: head classes dominate training exposure, while under-represented classes often converge to sharper regions of the loss landscape. Conventional re-sampling addresses the former without considering geometry, whereas existing long-tailed sharpness-aware minimization (SAM) methods modify losses or perturbations only after biased mini-batches have been drawn. We introduce Sharpness-Guided Equilibrium Sampling (SGS), which treats the sampling distribution as an active control variable for optimization geometry. SGS dynamically adjusts "},"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":"2607.21999","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-24T05:56:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e4171dcfc4549051ead5707c09435ccd273453ead411f6baaba6d76989329822","abstract_canon_sha256":"c99fb3df0942f6a11490c6de5a03971d10c9edaef5b38fd51a1f4829aed6f7db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-27T01:20:42.462371Z","signature_b64":"SRXTSjHzD8bP8Hh2ODfCVlroCZm2kb5cORKHz9gsXL5Lg/zQC4zW1sfQcY844KkG2snMBoRVi8wW2P/2sY0tBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5107322fe9740d3d34481bb4314edc364f28b7df0ab7820a70b8c4032372a8d5","last_reissued_at":"2026-07-27T01:20:42.461384Z","signature_status":"signed_v1","first_computed_at":"2026-07-27T01:20:42.461384Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Perturbation Correction to Geometry-Aware Sampling: Sharpness-Guided Equilibrium Sampling for Balanced Flat Minima in Long-Tailed Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jiaxin Deng, Junbiao Pang","submitted_at":"2026-07-24T05:56:00Z","abstract_excerpt":"Long-tailed learning couples two sources of poor generalization: head classes dominate training exposure, while under-represented classes often converge to sharper regions of the loss landscape. Conventional re-sampling addresses the former without considering geometry, whereas existing long-tailed sharpness-aware minimization (SAM) methods modify losses or perturbations only after biased mini-batches have been drawn. We introduce Sharpness-Guided Equilibrium Sampling (SGS), which treats the sampling distribution as an active control variable for optimization geometry. SGS dynamically adjusts "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21999","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/2607.21999/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":"2607.21999","created_at":"2026-07-27T01:20:42.461821+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.21999v1","created_at":"2026-07-27T01:20:42.461821+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21999","created_at":"2026-07-27T01:20:42.461821+00:00"},{"alias_kind":"pith_short_12","alias_value":"KEDTEL7JOQGT","created_at":"2026-07-27T01:20:42.461821+00:00"},{"alias_kind":"pith_short_16","alias_value":"KEDTEL7JOQGT2NCI","created_at":"2026-07-27T01:20:42.461821+00:00"},{"alias_kind":"pith_short_8","alias_value":"KEDTEL7J","created_at":"2026-07-27T01:20:42.461821+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KEDTEL7JOQGT2NCIDO2DCTW4GZ","json":"https://pith.science/pith/KEDTEL7JOQGT2NCIDO2DCTW4GZ.json","graph_json":"https://pith.science/api/pith-number/KEDTEL7JOQGT2NCIDO2DCTW4GZ/graph.json","events_json":"https://pith.science/api/pith-number/KEDTEL7JOQGT2NCIDO2DCTW4GZ/events.json","paper":"https://pith.science/paper/KEDTEL7J"},"agent_actions":{"view_html":"https://pith.science/pith/KEDTEL7JOQGT2NCIDO2DCTW4GZ","download_json":"https://pith.science/pith/KEDTEL7JOQGT2NCIDO2DCTW4GZ.json","view_paper":"https://pith.science/paper/KEDTEL7J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.21999&json=true","fetch_graph":"https://pith.science/api/pith-number/KEDTEL7JOQGT2NCIDO2DCTW4GZ/graph.json","fetch_events":"https://pith.science/api/pith-number/KEDTEL7JOQGT2NCIDO2DCTW4GZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KEDTEL7JOQGT2NCIDO2DCTW4GZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KEDTEL7JOQGT2NCIDO2DCTW4GZ/action/storage_attestation","attest_author":"https://pith.science/pith/KEDTEL7JOQGT2NCIDO2DCTW4GZ/action/author_attestation","sign_citation":"https://pith.science/pith/KEDTEL7JOQGT2NCIDO2DCTW4GZ/action/citation_signature","submit_replication":"https://pith.science/pith/KEDTEL7JOQGT2NCIDO2DCTW4GZ/action/replication_record"}},"created_at":"2026-07-27T01:20:42.461821+00:00","updated_at":"2026-07-27T01:20:42.461821+00:00"}