{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:EZBVVIK74L6ENSP7VVBXWTRWRQ","short_pith_number":"pith:EZBVVIK7","schema_version":"1.0","canonical_sha256":"26435aa15fe2fc46c9ffad437b4e368c2378ed65a0468446de6015fbe5c3cbb8","source":{"kind":"arxiv","id":"1704.04503","version":2},"attestation_state":"computed","paper":{"title":"Soft-NMS -- Improving Object Detection With One Line of Code","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bharat Singh, Larry S. Davis, Navaneeth Bodla, Rama Chellappa","submitted_at":"2017-04-14T18:00:03Z","abstract_excerpt":"Non-maximum suppression is an integral part of the object detection pipeline. First, it sorts all detection boxes on the basis of their scores. The detection box M with the maximum score is selected and all other detection boxes with a significant overlap (using a pre-defined threshold) with M are suppressed. This process is recursively applied on the remaining boxes. As per the design of the algorithm, if an object lies within the predefined overlap threshold, it leads to a miss. To this end, we propose Soft-NMS, an algorithm which decays the detection scores of all other objects as a continu"},"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":"1704.04503","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-14T18:00:03Z","cross_cats_sorted":[],"title_canon_sha256":"daa3002dbcbe8373e02ee102d2cd24b27b58c0aa0a05e7e19b8f070e9eebfb33","abstract_canon_sha256":"f1b424b75f2ce61d5a0a9b2f57435f8737f6d7e7d85187300268242171f8cce5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:27.646804Z","signature_b64":"WmZteuCuN6rS6kqVENOfXSVzuhu9CKLOoT3H02UWztpUH1TNJvSc44UH+e1jy3CSvDzXQzOzpqxz9pvtNohMAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26435aa15fe2fc46c9ffad437b4e368c2378ed65a0468446de6015fbe5c3cbb8","last_reissued_at":"2026-05-18T00:38:27.646024Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:27.646024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Soft-NMS -- Improving Object Detection With One Line of Code","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bharat Singh, Larry S. Davis, Navaneeth Bodla, Rama Chellappa","submitted_at":"2017-04-14T18:00:03Z","abstract_excerpt":"Non-maximum suppression is an integral part of the object detection pipeline. First, it sorts all detection boxes on the basis of their scores. The detection box M with the maximum score is selected and all other detection boxes with a significant overlap (using a pre-defined threshold) with M are suppressed. This process is recursively applied on the remaining boxes. As per the design of the algorithm, if an object lies within the predefined overlap threshold, it leads to a miss. To this end, we propose Soft-NMS, an algorithm which decays the detection scores of all other objects as a continu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.04503","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":""},"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":"1704.04503","created_at":"2026-05-18T00:38:27.646115+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.04503v2","created_at":"2026-05-18T00:38:27.646115+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.04503","created_at":"2026-05-18T00:38:27.646115+00:00"},{"alias_kind":"pith_short_12","alias_value":"EZBVVIK74L6E","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_16","alias_value":"EZBVVIK74L6ENSP7","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_8","alias_value":"EZBVVIK7","created_at":"2026-05-18T12:31:12.930513+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.17591","citing_title":"Error-Decomposed Class-Conditional Fusion for Statistically Guaranteed Hard-Category Robust Perception","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EZBVVIK74L6ENSP7VVBXWTRWRQ","json":"https://pith.science/pith/EZBVVIK74L6ENSP7VVBXWTRWRQ.json","graph_json":"https://pith.science/api/pith-number/EZBVVIK74L6ENSP7VVBXWTRWRQ/graph.json","events_json":"https://pith.science/api/pith-number/EZBVVIK74L6ENSP7VVBXWTRWRQ/events.json","paper":"https://pith.science/paper/EZBVVIK7"},"agent_actions":{"view_html":"https://pith.science/pith/EZBVVIK74L6ENSP7VVBXWTRWRQ","download_json":"https://pith.science/pith/EZBVVIK74L6ENSP7VVBXWTRWRQ.json","view_paper":"https://pith.science/paper/EZBVVIK7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.04503&json=true","fetch_graph":"https://pith.science/api/pith-number/EZBVVIK74L6ENSP7VVBXWTRWRQ/graph.json","fetch_events":"https://pith.science/api/pith-number/EZBVVIK74L6ENSP7VVBXWTRWRQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EZBVVIK74L6ENSP7VVBXWTRWRQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EZBVVIK74L6ENSP7VVBXWTRWRQ/action/storage_attestation","attest_author":"https://pith.science/pith/EZBVVIK74L6ENSP7VVBXWTRWRQ/action/author_attestation","sign_citation":"https://pith.science/pith/EZBVVIK74L6ENSP7VVBXWTRWRQ/action/citation_signature","submit_replication":"https://pith.science/pith/EZBVVIK74L6ENSP7VVBXWTRWRQ/action/replication_record"}},"created_at":"2026-05-18T00:38:27.646115+00:00","updated_at":"2026-05-18T00:38:27.646115+00:00"}