{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YWP6SHMGEDFZPI3O7JKERS752S","short_pith_number":"pith:YWP6SHMG","schema_version":"1.0","canonical_sha256":"c59fe91d8620cb97a36efa5448cbfdd49f228c400efe4ae3723c548f31720c1f","source":{"kind":"arxiv","id":"2606.02526","version":1},"attestation_state":"computed","paper":{"title":"Why Not Hyperparameter-Friendly Optimisation? A Monotonic Adaptive Norm Rescaling Approach For Long-Tailed Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chenqi Li, Shuo Zhang, Tingting Zhu","submitted_at":"2026-06-01T17:34:38Z","abstract_excerpt":"Long-tailed recognition poses a significant challenge for deep learning. The two-stage decoupling paradigm, which separates representation learning from classifier retraining, offers a promising solution. During the classifier retraining stage, adaptive norm rescaling is a popular technique. It adjusts the per-class weight norms via parameter regularization, which inevitably introduces hyperparameters. However, many studies report that long-tailed recognition is sensitive to these hyperparameters, as their setup significantly impacts performance. In this paper, we first provide a class-conditi"},"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":"2606.02526","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T17:34:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"09f5171dadbb4f096291bbdae3916d6d1b42bd768dc81808ab450f20ff599f50","abstract_canon_sha256":"eb7532148049931f069af2ab8313ce575c2b68874c3fdc22e77bab47d818d4fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T03:05:08.612523Z","signature_b64":"lEOih20AC1woPtrPZA5jSHQ4O+qnmfoyUkjrXA1+r8TZBizMz4e0mi853LJbDblLqoOMwp6ck86e9X+nN70XCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c59fe91d8620cb97a36efa5448cbfdd49f228c400efe4ae3723c548f31720c1f","last_reissued_at":"2026-06-02T03:05:08.612169Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T03:05:08.612169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Why Not Hyperparameter-Friendly Optimisation? A Monotonic Adaptive Norm Rescaling Approach For Long-Tailed Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chenqi Li, Shuo Zhang, Tingting Zhu","submitted_at":"2026-06-01T17:34:38Z","abstract_excerpt":"Long-tailed recognition poses a significant challenge for deep learning. The two-stage decoupling paradigm, which separates representation learning from classifier retraining, offers a promising solution. During the classifier retraining stage, adaptive norm rescaling is a popular technique. It adjusts the per-class weight norms via parameter regularization, which inevitably introduces hyperparameters. However, many studies report that long-tailed recognition is sensitive to these hyperparameters, as their setup significantly impacts performance. In this paper, we first provide a class-conditi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02526","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/2606.02526/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":"2606.02526","created_at":"2026-06-02T03:05:08.612226+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.02526v1","created_at":"2026-06-02T03:05:08.612226+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02526","created_at":"2026-06-02T03:05:08.612226+00:00"},{"alias_kind":"pith_short_12","alias_value":"YWP6SHMGEDFZ","created_at":"2026-06-02T03:05:08.612226+00:00"},{"alias_kind":"pith_short_16","alias_value":"YWP6SHMGEDFZPI3O","created_at":"2026-06-02T03:05:08.612226+00:00"},{"alias_kind":"pith_short_8","alias_value":"YWP6SHMG","created_at":"2026-06-02T03:05:08.612226+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/YWP6SHMGEDFZPI3O7JKERS752S","json":"https://pith.science/pith/YWP6SHMGEDFZPI3O7JKERS752S.json","graph_json":"https://pith.science/api/pith-number/YWP6SHMGEDFZPI3O7JKERS752S/graph.json","events_json":"https://pith.science/api/pith-number/YWP6SHMGEDFZPI3O7JKERS752S/events.json","paper":"https://pith.science/paper/YWP6SHMG"},"agent_actions":{"view_html":"https://pith.science/pith/YWP6SHMGEDFZPI3O7JKERS752S","download_json":"https://pith.science/pith/YWP6SHMGEDFZPI3O7JKERS752S.json","view_paper":"https://pith.science/paper/YWP6SHMG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.02526&json=true","fetch_graph":"https://pith.science/api/pith-number/YWP6SHMGEDFZPI3O7JKERS752S/graph.json","fetch_events":"https://pith.science/api/pith-number/YWP6SHMGEDFZPI3O7JKERS752S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YWP6SHMGEDFZPI3O7JKERS752S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YWP6SHMGEDFZPI3O7JKERS752S/action/storage_attestation","attest_author":"https://pith.science/pith/YWP6SHMGEDFZPI3O7JKERS752S/action/author_attestation","sign_citation":"https://pith.science/pith/YWP6SHMGEDFZPI3O7JKERS752S/action/citation_signature","submit_replication":"https://pith.science/pith/YWP6SHMGEDFZPI3O7JKERS752S/action/replication_record"}},"created_at":"2026-06-02T03:05:08.612226+00:00","updated_at":"2026-06-02T03:05:08.612226+00:00"}