{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:B4TLLDPRZZA64A64T46LHGT4YM","short_pith_number":"pith:B4TLLDPR","schema_version":"1.0","canonical_sha256":"0f26b58df1ce41ee03dc9f3cb39a7cc33c4b3a9cfab685be6b82179a20d32aec","source":{"kind":"arxiv","id":"2504.20602","version":1},"attestation_state":"computed","paper":{"title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liujuan Cao, Rongrong Ji, Siwei Wang, Zhiwei Chen","submitted_at":"2025-04-29T10:11:03Z","abstract_excerpt":"Small object detection is a broadly investigated research task and is commonly conceptualized as a \"pipeline-style\" engineering process. In the upstream, images serve as raw materials for processing in the detection pipeline, where pre-trained models are employed to generate initial feature maps. In the midstream, an assigner selects training positive and negative samples. Subsequently, these samples and features are fed into the downstream for classification and regression. Previous small object detection methods often focused on improving isolated stages of the pipeline, thereby neglecting h"},"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":"2504.20602","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-29T10:11:03Z","cross_cats_sorted":[],"title_canon_sha256":"d855724d34da53beb44eb5022f26dcc2ad8b9a0bcf24f8c1477c3fd0e0134804","abstract_canon_sha256":"2ad5b1e2ff3dd83648bee3170134055e89ecdf711226aff15a096eb3ec8948f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:55:45.366596Z","signature_b64":"dkhMgbgmghl0biggahkaSwuSTMxZsQrm8fJiJg1YVZp6KApINX7W4R5Uz1cx4EVlm2ae5gGjHjVS57GxjrhNAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f26b58df1ce41ee03dc9f3cb39a7cc33c4b3a9cfab685be6b82179a20d32aec","last_reissued_at":"2026-07-05T10:55:45.366090Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:55:45.366090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liujuan Cao, Rongrong Ji, Siwei Wang, Zhiwei Chen","submitted_at":"2025-04-29T10:11:03Z","abstract_excerpt":"Small object detection is a broadly investigated research task and is commonly conceptualized as a \"pipeline-style\" engineering process. In the upstream, images serve as raw materials for processing in the detection pipeline, where pre-trained models are employed to generate initial feature maps. In the midstream, an assigner selects training positive and negative samples. Subsequently, these samples and features are fed into the downstream for classification and regression. Previous small object detection methods often focused on improving isolated stages of the pipeline, thereby neglecting h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.20602","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/2504.20602/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":"2504.20602","created_at":"2026-07-05T10:55:45.366150+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.20602v1","created_at":"2026-07-05T10:55:45.366150+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.20602","created_at":"2026-07-05T10:55:45.366150+00:00"},{"alias_kind":"pith_short_12","alias_value":"B4TLLDPRZZA6","created_at":"2026-07-05T10:55:45.366150+00:00"},{"alias_kind":"pith_short_16","alias_value":"B4TLLDPRZZA64A64","created_at":"2026-07-05T10:55:45.366150+00:00"},{"alias_kind":"pith_short_8","alias_value":"B4TLLDPR","created_at":"2026-07-05T10:55:45.366150+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/B4TLLDPRZZA64A64T46LHGT4YM","json":"https://pith.science/pith/B4TLLDPRZZA64A64T46LHGT4YM.json","graph_json":"https://pith.science/api/pith-number/B4TLLDPRZZA64A64T46LHGT4YM/graph.json","events_json":"https://pith.science/api/pith-number/B4TLLDPRZZA64A64T46LHGT4YM/events.json","paper":"https://pith.science/paper/B4TLLDPR"},"agent_actions":{"view_html":"https://pith.science/pith/B4TLLDPRZZA64A64T46LHGT4YM","download_json":"https://pith.science/pith/B4TLLDPRZZA64A64T46LHGT4YM.json","view_paper":"https://pith.science/paper/B4TLLDPR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.20602&json=true","fetch_graph":"https://pith.science/api/pith-number/B4TLLDPRZZA64A64T46LHGT4YM/graph.json","fetch_events":"https://pith.science/api/pith-number/B4TLLDPRZZA64A64T46LHGT4YM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B4TLLDPRZZA64A64T46LHGT4YM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B4TLLDPRZZA64A64T46LHGT4YM/action/storage_attestation","attest_author":"https://pith.science/pith/B4TLLDPRZZA64A64T46LHGT4YM/action/author_attestation","sign_citation":"https://pith.science/pith/B4TLLDPRZZA64A64T46LHGT4YM/action/citation_signature","submit_replication":"https://pith.science/pith/B4TLLDPRZZA64A64T46LHGT4YM/action/replication_record"}},"created_at":"2026-07-05T10:55:45.366150+00:00","updated_at":"2026-07-05T10:55:45.366150+00:00"}