{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BCQXY6KHV7XIWWITFW2R45OJHA","short_pith_number":"pith:BCQXY6KH","schema_version":"1.0","canonical_sha256":"08a17c7947afee8b59132db51e75c9380afadec6e5ad2f08a04218158ef4ff74","source":{"kind":"arxiv","id":"2412.16540","version":1},"attestation_state":"computed","paper":{"title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Amit More, Mudit Soni, S Divakar Bhat, Surbhi Agrawal","submitted_at":"2024-12-21T08:49:02Z","abstract_excerpt":"Learning-based solutions for long-tailed recognition face difficulties in generalizing on balanced test datasets. Due to imbalanced data prior, the learned \\textit{a posteriori} distribution is biased toward the most frequent (head) classes, leading to an inferior performance on the least frequent (tail) classes. In general, the performance can be improved by removing such a bias by eliminating the effect of imbalanced prior modeled using the number of class samples (frequencies). We first observe that the \\textit{effective prior} on the classes, learned by the model at the end of the training"},"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":"2412.16540","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-21T08:49:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b1a823b5618a15c7511c0333e525c865ac2f0ada158ccb3cdd8f7ed78b01ed63","abstract_canon_sha256":"925001de4b104e3f0b0eb74d6302e685b8fc11520aba1c0b0da454eb03b4b181"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:49.250436Z","signature_b64":"O6pseWFe/ce2DCzpnPsCfCR8zHFwE5ekgDmB2UDRBGh8qQYuQISySlc3cZtq6ofLFMqTPHsCf3YPPpRnyMr0CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08a17c7947afee8b59132db51e75c9380afadec6e5ad2f08a04218158ef4ff74","last_reissued_at":"2026-07-05T09:52:49.249958Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:49.249958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Amit More, Mudit Soni, S Divakar Bhat, Surbhi Agrawal","submitted_at":"2024-12-21T08:49:02Z","abstract_excerpt":"Learning-based solutions for long-tailed recognition face difficulties in generalizing on balanced test datasets. Due to imbalanced data prior, the learned \\textit{a posteriori} distribution is biased toward the most frequent (head) classes, leading to an inferior performance on the least frequent (tail) classes. In general, the performance can be improved by removing such a bias by eliminating the effect of imbalanced prior modeled using the number of class samples (frequencies). We first observe that the \\textit{effective prior} on the classes, learned by the model at the end of the training"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16540","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/2412.16540/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":"2412.16540","created_at":"2026-07-05T09:52:49.250023+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.16540v1","created_at":"2026-07-05T09:52:49.250023+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16540","created_at":"2026-07-05T09:52:49.250023+00:00"},{"alias_kind":"pith_short_12","alias_value":"BCQXY6KHV7XI","created_at":"2026-07-05T09:52:49.250023+00:00"},{"alias_kind":"pith_short_16","alias_value":"BCQXY6KHV7XIWWIT","created_at":"2026-07-05T09:52:49.250023+00:00"},{"alias_kind":"pith_short_8","alias_value":"BCQXY6KH","created_at":"2026-07-05T09:52:49.250023+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/BCQXY6KHV7XIWWITFW2R45OJHA","json":"https://pith.science/pith/BCQXY6KHV7XIWWITFW2R45OJHA.json","graph_json":"https://pith.science/api/pith-number/BCQXY6KHV7XIWWITFW2R45OJHA/graph.json","events_json":"https://pith.science/api/pith-number/BCQXY6KHV7XIWWITFW2R45OJHA/events.json","paper":"https://pith.science/paper/BCQXY6KH"},"agent_actions":{"view_html":"https://pith.science/pith/BCQXY6KHV7XIWWITFW2R45OJHA","download_json":"https://pith.science/pith/BCQXY6KHV7XIWWITFW2R45OJHA.json","view_paper":"https://pith.science/paper/BCQXY6KH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.16540&json=true","fetch_graph":"https://pith.science/api/pith-number/BCQXY6KHV7XIWWITFW2R45OJHA/graph.json","fetch_events":"https://pith.science/api/pith-number/BCQXY6KHV7XIWWITFW2R45OJHA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BCQXY6KHV7XIWWITFW2R45OJHA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BCQXY6KHV7XIWWITFW2R45OJHA/action/storage_attestation","attest_author":"https://pith.science/pith/BCQXY6KHV7XIWWITFW2R45OJHA/action/author_attestation","sign_citation":"https://pith.science/pith/BCQXY6KHV7XIWWITFW2R45OJHA/action/citation_signature","submit_replication":"https://pith.science/pith/BCQXY6KHV7XIWWITFW2R45OJHA/action/replication_record"}},"created_at":"2026-07-05T09:52:49.250023+00:00","updated_at":"2026-07-05T09:52:49.250023+00:00"}