{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:SST7HM33CFX3JV4WXXQWX2QW7J","short_pith_number":"pith:SST7HM33","schema_version":"1.0","canonical_sha256":"94a7f3b37b116fb4d796bde16bea16fa675641e3c480b433ce113b5fde0a9ee9","source":{"kind":"arxiv","id":"1811.09347","version":2},"attestation_state":"computed","paper":{"title":"A Simple Non-i.i.d. Sampling Approach for Efficient Training and Better Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bowen Cheng, Humphrey Shi, Jiahui Yu, Jinjun Xiong, Shiyu Chang, Thomas S. Huang, Wen-Mei Hwu, Yunchao Wei","submitted_at":"2018-11-23T02:49:47Z","abstract_excerpt":"While training on samples drawn from independent and identical distribution has been a de facto paradigm for optimizing image classification networks, humans learn new concepts in an easy-to-hard manner and on the selected examples progressively. Driven by this fact, we investigate the training paradigms where the samples are not drawn from independent and identical distribution. We propose a data sampling strategy, named Drop-and-Refresh (DaR), motivated by the learning behaviors of humans that selectively drop easy samples and refresh them only periodically. We show in our experiments that t"},"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":"1811.09347","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-23T02:49:47Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b62158ad89512e1c3a25bda75e16d1c29918fcb4fc736b435fabbc36f545590d","abstract_canon_sha256":"5541ea73196c5e94b88250f37cda3786a37f9cd29e67ea04f531a47698268605"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:43:12.427187Z","signature_b64":"zXslNX88m3ETxm6Wcmau36Dpp4HIU85LhzIo1yDcLYI2gCTQpdY5LpwScpismFrPpQ9e+VrHsRmI3sPjb4V5AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94a7f3b37b116fb4d796bde16bea16fa675641e3c480b433ce113b5fde0a9ee9","last_reissued_at":"2026-07-05T01:43:12.426767Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:43:12.426767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Simple Non-i.i.d. Sampling Approach for Efficient Training and Better Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bowen Cheng, Humphrey Shi, Jiahui Yu, Jinjun Xiong, Shiyu Chang, Thomas S. Huang, Wen-Mei Hwu, Yunchao Wei","submitted_at":"2018-11-23T02:49:47Z","abstract_excerpt":"While training on samples drawn from independent and identical distribution has been a de facto paradigm for optimizing image classification networks, humans learn new concepts in an easy-to-hard manner and on the selected examples progressively. Driven by this fact, we investigate the training paradigms where the samples are not drawn from independent and identical distribution. We propose a data sampling strategy, named Drop-and-Refresh (DaR), motivated by the learning behaviors of humans that selectively drop easy samples and refresh them only periodically. We show in our experiments that t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.09347","kind":"arxiv","version":2},"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/1811.09347/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":"1811.09347","created_at":"2026-07-05T01:43:12.426834+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.09347v2","created_at":"2026-07-05T01:43:12.426834+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.09347","created_at":"2026-07-05T01:43:12.426834+00:00"},{"alias_kind":"pith_short_12","alias_value":"SST7HM33CFX3","created_at":"2026-07-05T01:43:12.426834+00:00"},{"alias_kind":"pith_short_16","alias_value":"SST7HM33CFX3JV4W","created_at":"2026-07-05T01:43:12.426834+00:00"},{"alias_kind":"pith_short_8","alias_value":"SST7HM33","created_at":"2026-07-05T01:43:12.426834+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/SST7HM33CFX3JV4WXXQWX2QW7J","json":"https://pith.science/pith/SST7HM33CFX3JV4WXXQWX2QW7J.json","graph_json":"https://pith.science/api/pith-number/SST7HM33CFX3JV4WXXQWX2QW7J/graph.json","events_json":"https://pith.science/api/pith-number/SST7HM33CFX3JV4WXXQWX2QW7J/events.json","paper":"https://pith.science/paper/SST7HM33"},"agent_actions":{"view_html":"https://pith.science/pith/SST7HM33CFX3JV4WXXQWX2QW7J","download_json":"https://pith.science/pith/SST7HM33CFX3JV4WXXQWX2QW7J.json","view_paper":"https://pith.science/paper/SST7HM33","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.09347&json=true","fetch_graph":"https://pith.science/api/pith-number/SST7HM33CFX3JV4WXXQWX2QW7J/graph.json","fetch_events":"https://pith.science/api/pith-number/SST7HM33CFX3JV4WXXQWX2QW7J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SST7HM33CFX3JV4WXXQWX2QW7J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SST7HM33CFX3JV4WXXQWX2QW7J/action/storage_attestation","attest_author":"https://pith.science/pith/SST7HM33CFX3JV4WXXQWX2QW7J/action/author_attestation","sign_citation":"https://pith.science/pith/SST7HM33CFX3JV4WXXQWX2QW7J/action/citation_signature","submit_replication":"https://pith.science/pith/SST7HM33CFX3JV4WXXQWX2QW7J/action/replication_record"}},"created_at":"2026-07-05T01:43:12.426834+00:00","updated_at":"2026-07-05T01:43:12.426834+00:00"}