{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:NDTVP56IEH4EX4HGQLPZQ72UDJ","short_pith_number":"pith:NDTVP56I","schema_version":"1.0","canonical_sha256":"68e757f7c821f84bf0e682df987f541a5258e341c9267291574b7e96cf01e520","source":{"kind":"arxiv","id":"1604.02135","version":2},"attestation_state":"computed","paper":{"title":"A MultiPath Network for Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adam Lerer, Pedro O. Pinheiro, Piotr Doll\\'ar, Sam Gross, Sergey Zagoruyko, Soumith Chintala, Tsung-Yi Lin","submitted_at":"2016-04-07T19:43:47Z","abstract_excerpt":"The recent COCO object detection dataset presents several new challenges for object detection. In particular, it contains objects at a broad range of scales, less prototypical images, and requires more precise localization. To address these challenges, we test three modifications to the standard Fast R-CNN object detector: (1) skip connections that give the detector access to features at multiple network layers, (2) a foveal structure to exploit object context at multiple object resolutions, and (3) an integral loss function and corresponding network adjustment that improve localization. The r"},"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":"1604.02135","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-04-07T19:43:47Z","cross_cats_sorted":[],"title_canon_sha256":"069162631487b228c80fbc7577d3e3d4252fb5aba451e6f7ac8aa1eb002a1608","abstract_canon_sha256":"6ce4a45190028cd867d0b1750ac6fd4e69d1fd130f831aaf1cdafa6fe0ae19b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:09:41.610971Z","signature_b64":"uOR1jWRmsssoNgvPAKa8b7K/dzmRn4UqqUMkI6LZZmIUgPBM/HPI4j15g6rYLAiwKjbG1/mm4MBNbeWZxEwfAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68e757f7c821f84bf0e682df987f541a5258e341c9267291574b7e96cf01e520","last_reissued_at":"2026-05-18T01:09:41.610330Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:09:41.610330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A MultiPath Network for Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adam Lerer, Pedro O. Pinheiro, Piotr Doll\\'ar, Sam Gross, Sergey Zagoruyko, Soumith Chintala, Tsung-Yi Lin","submitted_at":"2016-04-07T19:43:47Z","abstract_excerpt":"The recent COCO object detection dataset presents several new challenges for object detection. In particular, it contains objects at a broad range of scales, less prototypical images, and requires more precise localization. To address these challenges, we test three modifications to the standard Fast R-CNN object detector: (1) skip connections that give the detector access to features at multiple network layers, (2) a foveal structure to exploit object context at multiple object resolutions, and (3) an integral loss function and corresponding network adjustment that improve localization. The r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.02135","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":"1604.02135","created_at":"2026-05-18T01:09:41.610423+00:00"},{"alias_kind":"arxiv_version","alias_value":"1604.02135v2","created_at":"2026-05-18T01:09:41.610423+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.02135","created_at":"2026-05-18T01:09:41.610423+00:00"},{"alias_kind":"pith_short_12","alias_value":"NDTVP56IEH4E","created_at":"2026-05-18T12:30:32.724797+00:00"},{"alias_kind":"pith_short_16","alias_value":"NDTVP56IEH4EX4HG","created_at":"2026-05-18T12:30:32.724797+00:00"},{"alias_kind":"pith_short_8","alias_value":"NDTVP56I","created_at":"2026-05-18T12:30:32.724797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.10346","citing_title":"Delving Deep into Liver Focal Lesion Detection: A Preliminary Study","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NDTVP56IEH4EX4HGQLPZQ72UDJ","json":"https://pith.science/pith/NDTVP56IEH4EX4HGQLPZQ72UDJ.json","graph_json":"https://pith.science/api/pith-number/NDTVP56IEH4EX4HGQLPZQ72UDJ/graph.json","events_json":"https://pith.science/api/pith-number/NDTVP56IEH4EX4HGQLPZQ72UDJ/events.json","paper":"https://pith.science/paper/NDTVP56I"},"agent_actions":{"view_html":"https://pith.science/pith/NDTVP56IEH4EX4HGQLPZQ72UDJ","download_json":"https://pith.science/pith/NDTVP56IEH4EX4HGQLPZQ72UDJ.json","view_paper":"https://pith.science/paper/NDTVP56I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1604.02135&json=true","fetch_graph":"https://pith.science/api/pith-number/NDTVP56IEH4EX4HGQLPZQ72UDJ/graph.json","fetch_events":"https://pith.science/api/pith-number/NDTVP56IEH4EX4HGQLPZQ72UDJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NDTVP56IEH4EX4HGQLPZQ72UDJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NDTVP56IEH4EX4HGQLPZQ72UDJ/action/storage_attestation","attest_author":"https://pith.science/pith/NDTVP56IEH4EX4HGQLPZQ72UDJ/action/author_attestation","sign_citation":"https://pith.science/pith/NDTVP56IEH4EX4HGQLPZQ72UDJ/action/citation_signature","submit_replication":"https://pith.science/pith/NDTVP56IEH4EX4HGQLPZQ72UDJ/action/replication_record"}},"created_at":"2026-05-18T01:09:41.610423+00:00","updated_at":"2026-05-18T01:09:41.610423+00:00"}