{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:USR5VYP45665XA2WXCTRJQ3VMV","short_pith_number":"pith:USR5VYP4","canonical_record":{"source":{"id":"1604.03540","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-04-12T19:44:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"068f70be7949a4ced423bdb14a7eff529288964e60c26f3359e24ab5460ff3f9","abstract_canon_sha256":"f003449df414fbe221b162c9425e3c397eac39b1ecad8eedf61060ecb9cef6cd"},"schema_version":"1.0"},"canonical_sha256":"a4a3dae1fcefbddb8356b8a714c375657d5121a1c7fd1508a2dfbaa2bfe98943","source":{"kind":"arxiv","id":"1604.03540","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1604.03540","created_at":"2026-05-18T01:17:13Z"},{"alias_kind":"arxiv_version","alias_value":"1604.03540v1","created_at":"2026-05-18T01:17:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.03540","created_at":"2026-05-18T01:17:13Z"},{"alias_kind":"pith_short_12","alias_value":"USR5VYP45665","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_16","alias_value":"USR5VYP45665XA2W","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_8","alias_value":"USR5VYP4","created_at":"2026-05-18T12:30:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:USR5VYP45665XA2WXCTRJQ3VMV","target":"record","payload":{"canonical_record":{"source":{"id":"1604.03540","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-04-12T19:44:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"068f70be7949a4ced423bdb14a7eff529288964e60c26f3359e24ab5460ff3f9","abstract_canon_sha256":"f003449df414fbe221b162c9425e3c397eac39b1ecad8eedf61060ecb9cef6cd"},"schema_version":"1.0"},"canonical_sha256":"a4a3dae1fcefbddb8356b8a714c375657d5121a1c7fd1508a2dfbaa2bfe98943","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:17:13.216690Z","signature_b64":"nk5LY3V99PwluCOKIYWzG6AOlROtspmPJK5dPT3HL6ISg77wzFJFCEurZJEle+4Y+rdmLP89G7BDNuFAcwutCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4a3dae1fcefbddb8356b8a714c375657d5121a1c7fd1508a2dfbaa2bfe98943","last_reissued_at":"2026-05-18T01:17:13.215949Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:17:13.215949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1604.03540","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:17:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zN4vUw0UWQXAe5MVG08GcFw3EtKWo5TpkMH1P4iU/mS6pqKjbT2XAsObgPSzSRZlM094Bl6AQyPlUTyJdPbcCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T15:48:19.204725Z"},"content_sha256":"65317cca0f7f0baa52c1891f659ef18d99e0d9eea381997deb87c462dafa8d73","schema_version":"1.0","event_id":"sha256:65317cca0f7f0baa52c1891f659ef18d99e0d9eea381997deb87c462dafa8d73"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:USR5VYP45665XA2WXCTRJQ3VMV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Training Region-based Object Detectors with Online Hard Example Mining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Abhinav Gupta, Abhinav Shrivastava, Ross Girshick","submitted_at":"2016-04-12T19:44:13Z","abstract_excerpt":"The field of object detection has made significant advances riding on the wave of region-based ConvNets, but their training procedure still includes many heuristics and hyperparameters that are costly to tune. We present a simple yet surprisingly effective online hard example mining (OHEM) algorithm for training region-based ConvNet detectors. Our motivation is the same as it has always been -- detection datasets contain an overwhelming number of easy examples and a small number of hard examples. Automatic selection of these hard examples can make training more effective and efficient. OHEM is"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.03540","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":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:17:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xm2xk77JiY+ZoLkc+baphM9aIKPQ9slyafaJgBep995T07AYXsIo2onKkB2jBrW+dBJss69zJAHwythz7yY/Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T15:48:19.205372Z"},"content_sha256":"ecaf37394b0c9b3faf0bdbae644f104cbd3cf3b1bfd6660c1e94103fea52d42c","schema_version":"1.0","event_id":"sha256:ecaf37394b0c9b3faf0bdbae644f104cbd3cf3b1bfd6660c1e94103fea52d42c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/USR5VYP45665XA2WXCTRJQ3VMV/bundle.json","state_url":"https://pith.science/pith/USR5VYP45665XA2WXCTRJQ3VMV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/USR5VYP45665XA2WXCTRJQ3VMV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-25T15:48:19Z","links":{"resolver":"https://pith.science/pith/USR5VYP45665XA2WXCTRJQ3VMV","bundle":"https://pith.science/pith/USR5VYP45665XA2WXCTRJQ3VMV/bundle.json","state":"https://pith.science/pith/USR5VYP45665XA2WXCTRJQ3VMV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/USR5VYP45665XA2WXCTRJQ3VMV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:USR5VYP45665XA2WXCTRJQ3VMV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f003449df414fbe221b162c9425e3c397eac39b1ecad8eedf61060ecb9cef6cd","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-04-12T19:44:13Z","title_canon_sha256":"068f70be7949a4ced423bdb14a7eff529288964e60c26f3359e24ab5460ff3f9"},"schema_version":"1.0","source":{"id":"1604.03540","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1604.03540","created_at":"2026-05-18T01:17:13Z"},{"alias_kind":"arxiv_version","alias_value":"1604.03540v1","created_at":"2026-05-18T01:17:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.03540","created_at":"2026-05-18T01:17:13Z"},{"alias_kind":"pith_short_12","alias_value":"USR5VYP45665","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_16","alias_value":"USR5VYP45665XA2W","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_8","alias_value":"USR5VYP4","created_at":"2026-05-18T12:30:46Z"}],"graph_snapshots":[{"event_id":"sha256:ecaf37394b0c9b3faf0bdbae644f104cbd3cf3b1bfd6660c1e94103fea52d42c","target":"graph","created_at":"2026-05-18T01:17:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"The field of object detection has made significant advances riding on the wave of region-based ConvNets, but their training procedure still includes many heuristics and hyperparameters that are costly to tune. We present a simple yet surprisingly effective online hard example mining (OHEM) algorithm for training region-based ConvNet detectors. Our motivation is the same as it has always been -- detection datasets contain an overwhelming number of easy examples and a small number of hard examples. Automatic selection of these hard examples can make training more effective and efficient. OHEM is","authors_text":"Abhinav Gupta, Abhinav Shrivastava, Ross Girshick","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-04-12T19:44:13Z","title":"Training Region-based Object Detectors with Online Hard Example Mining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.03540","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:65317cca0f7f0baa52c1891f659ef18d99e0d9eea381997deb87c462dafa8d73","target":"record","created_at":"2026-05-18T01:17:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f003449df414fbe221b162c9425e3c397eac39b1ecad8eedf61060ecb9cef6cd","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-04-12T19:44:13Z","title_canon_sha256":"068f70be7949a4ced423bdb14a7eff529288964e60c26f3359e24ab5460ff3f9"},"schema_version":"1.0","source":{"id":"1604.03540","kind":"arxiv","version":1}},"canonical_sha256":"a4a3dae1fcefbddb8356b8a714c375657d5121a1c7fd1508a2dfbaa2bfe98943","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a4a3dae1fcefbddb8356b8a714c375657d5121a1c7fd1508a2dfbaa2bfe98943","first_computed_at":"2026-05-18T01:17:13.215949Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:17:13.215949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nk5LY3V99PwluCOKIYWzG6AOlROtspmPJK5dPT3HL6ISg77wzFJFCEurZJEle+4Y+rdmLP89G7BDNuFAcwutCA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:17:13.216690Z","signed_message":"canonical_sha256_bytes"},"source_id":"1604.03540","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:65317cca0f7f0baa52c1891f659ef18d99e0d9eea381997deb87c462dafa8d73","sha256:ecaf37394b0c9b3faf0bdbae644f104cbd3cf3b1bfd6660c1e94103fea52d42c"],"state_sha256":"a6bf27821318354f58e11f15887042558adffb44947eebb73cbc11c8b728ae72"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bvit5j43lIufoLQYf4sTx1iHVz5OHLeqXgjCjbzeEo3b7CqixM0bJH8DNdGpdi0F1juU0LCWsmGybj45E6VLCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T15:48:19.208307Z","bundle_sha256":"3901b5ffff79a6e185263191e5a9d3deafc6d9914cdeb087b23a7b2f5ccd3993"}}