{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:UAEJWXKKHPHQRKS6YXTQWHYGTT","short_pith_number":"pith:UAEJWXKK","canonical_record":{"source":{"id":"1808.04285","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-08-13T15:21:22Z","cross_cats_sorted":[],"title_canon_sha256":"006e96d8addbb41eadb4b82956af691e00aa40768cec9378ba0f0f83e04cec29","abstract_canon_sha256":"0c30c0ac05e56500ec5622e48569b32e15ac7ba642beefdaef55ef7693e77959"},"schema_version":"1.0"},"canonical_sha256":"a0089b5d4a3bcf08aa5ec5e70b1f069cf7d604305566c4220c51ae627ed0b476","source":{"kind":"arxiv","id":"1808.04285","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.04285","created_at":"2026-05-18T00:08:18Z"},{"alias_kind":"arxiv_version","alias_value":"1808.04285v1","created_at":"2026-05-18T00:08:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.04285","created_at":"2026-05-18T00:08:18Z"},{"alias_kind":"pith_short_12","alias_value":"UAEJWXKKHPHQ","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"UAEJWXKKHPHQRKS6","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"UAEJWXKK","created_at":"2026-05-18T12:32:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:UAEJWXKKHPHQRKS6YXTQWHYGTT","target":"record","payload":{"canonical_record":{"source":{"id":"1808.04285","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-08-13T15:21:22Z","cross_cats_sorted":[],"title_canon_sha256":"006e96d8addbb41eadb4b82956af691e00aa40768cec9378ba0f0f83e04cec29","abstract_canon_sha256":"0c30c0ac05e56500ec5622e48569b32e15ac7ba642beefdaef55ef7693e77959"},"schema_version":"1.0"},"canonical_sha256":"a0089b5d4a3bcf08aa5ec5e70b1f069cf7d604305566c4220c51ae627ed0b476","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:08:18.415468Z","signature_b64":"q7umsdRlB5Zn0AqDG4bDM/lpNG/KOXwdCUAzGd2a0WK697fIAvSQH4OQjx2Wi7RBnGFHPr6QiOVCpo1wJ6FsAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0089b5d4a3bcf08aa5ec5e70b1f069cf7d604305566c4220c51ae627ed0b476","last_reissued_at":"2026-05-18T00:08:18.415113Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:08:18.415113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1808.04285","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":"2026-05-18T00:08:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cMuWuQ7jgkXnGUgGpOp5f6yfhodDLoHbhXDSwhgD7VBW5hjKXz2ieWJ5Fy0OqiMkw1YS6ioYpSfpQw67PngEDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T19:47:21.710077Z"},"content_sha256":"39aa9d40dc34c700d825ff26a53b188e16cc96088260690199a4e15b90475931","schema_version":"1.0","event_id":"sha256:39aa9d40dc34c700d825ff26a53b188e16cc96088260690199a4e15b90475931"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:UAEJWXKKHPHQRKS6YXTQWHYGTT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unsupervised Hard Example Mining from Videos for Improved Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aditya Prasad, Aruni RoyChowdhury, Ashish Singh, Deep Chakraborty, Erik Learned-Miller, Huaizu Jiang, SouYoung Jin","submitted_at":"2018-08-13T15:21:22Z","abstract_excerpt":"Important gains have recently been obtained in object detection by using training objectives that focus on {\\em hard negative} examples, i.e., negative examples that are currently rated as positive or ambiguous by the detector. These examples can strongly influence parameters when the network is trained to correct them. Unfortunately, they are often sparse in the training data, and are expensive to obtain. In this work, we show how large numbers of hard negatives can be obtained {\\em automatically} by analyzing the output of a trained detector on video sequences. In particular, detections that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.04285","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":"2026-05-18T00:08:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GpVPPb2IHR8L5+5RFEHo5fyR7gAJx4l7lK+OGC90x4P5sRWJgB/hhjewIhoBqfprQsrK6vWNG4LzEfwJ1LfAAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T19:47:21.710439Z"},"content_sha256":"320559097329ac29ff9108c92b9bbb3fe201b4b55792c99f009d05f56bd07fb6","schema_version":"1.0","event_id":"sha256:320559097329ac29ff9108c92b9bbb3fe201b4b55792c99f009d05f56bd07fb6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UAEJWXKKHPHQRKS6YXTQWHYGTT/bundle.json","state_url":"https://pith.science/pith/UAEJWXKKHPHQRKS6YXTQWHYGTT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UAEJWXKKHPHQRKS6YXTQWHYGTT/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":"2026-06-03T19:47:21Z","links":{"resolver":"https://pith.science/pith/UAEJWXKKHPHQRKS6YXTQWHYGTT","bundle":"https://pith.science/pith/UAEJWXKKHPHQRKS6YXTQWHYGTT/bundle.json","state":"https://pith.science/pith/UAEJWXKKHPHQRKS6YXTQWHYGTT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UAEJWXKKHPHQRKS6YXTQWHYGTT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:UAEJWXKKHPHQRKS6YXTQWHYGTT","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":"0c30c0ac05e56500ec5622e48569b32e15ac7ba642beefdaef55ef7693e77959","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-08-13T15:21:22Z","title_canon_sha256":"006e96d8addbb41eadb4b82956af691e00aa40768cec9378ba0f0f83e04cec29"},"schema_version":"1.0","source":{"id":"1808.04285","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.04285","created_at":"2026-05-18T00:08:18Z"},{"alias_kind":"arxiv_version","alias_value":"1808.04285v1","created_at":"2026-05-18T00:08:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.04285","created_at":"2026-05-18T00:08:18Z"},{"alias_kind":"pith_short_12","alias_value":"UAEJWXKKHPHQ","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"UAEJWXKKHPHQRKS6","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"UAEJWXKK","created_at":"2026-05-18T12:32:56Z"}],"graph_snapshots":[{"event_id":"sha256:320559097329ac29ff9108c92b9bbb3fe201b4b55792c99f009d05f56bd07fb6","target":"graph","created_at":"2026-05-18T00:08:18Z","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":"Important gains have recently been obtained in object detection by using training objectives that focus on {\\em hard negative} examples, i.e., negative examples that are currently rated as positive or ambiguous by the detector. These examples can strongly influence parameters when the network is trained to correct them. Unfortunately, they are often sparse in the training data, and are expensive to obtain. In this work, we show how large numbers of hard negatives can be obtained {\\em automatically} by analyzing the output of a trained detector on video sequences. In particular, detections that","authors_text":"Aditya Prasad, Aruni RoyChowdhury, Ashish Singh, Deep Chakraborty, Erik Learned-Miller, Huaizu Jiang, SouYoung Jin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-08-13T15:21:22Z","title":"Unsupervised Hard Example Mining from Videos for Improved Object Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.04285","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":"sha256:39aa9d40dc34c700d825ff26a53b188e16cc96088260690199a4e15b90475931","target":"record","created_at":"2026-05-18T00:08:18Z","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":"0c30c0ac05e56500ec5622e48569b32e15ac7ba642beefdaef55ef7693e77959","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-08-13T15:21:22Z","title_canon_sha256":"006e96d8addbb41eadb4b82956af691e00aa40768cec9378ba0f0f83e04cec29"},"schema_version":"1.0","source":{"id":"1808.04285","kind":"arxiv","version":1}},"canonical_sha256":"a0089b5d4a3bcf08aa5ec5e70b1f069cf7d604305566c4220c51ae627ed0b476","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a0089b5d4a3bcf08aa5ec5e70b1f069cf7d604305566c4220c51ae627ed0b476","first_computed_at":"2026-05-18T00:08:18.415113Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:08:18.415113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q7umsdRlB5Zn0AqDG4bDM/lpNG/KOXwdCUAzGd2a0WK697fIAvSQH4OQjx2Wi7RBnGFHPr6QiOVCpo1wJ6FsAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:08:18.415468Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.04285","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:39aa9d40dc34c700d825ff26a53b188e16cc96088260690199a4e15b90475931","sha256:320559097329ac29ff9108c92b9bbb3fe201b4b55792c99f009d05f56bd07fb6"],"state_sha256":"93eebcf062a630648bf445c380f70e689a6ed2c0929dca9670a3f72f6b1ab792"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5p9yC9W+6R88bHAZolwY5QRHhJ86qWngzZ/4dQumD1LZ0bIVAIx0U5RbZ6kTnKmPfbSH8B25CJpPtD4rBr5vDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T19:47:21.712622Z","bundle_sha256":"c2865a0240b5e885c1fb2055b6f68f87e792f98a4e1d2c2ea1e3be9e37307a7f"}}