{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:N3ZRWJJS6ZJEJURNQE5VNJ22ET","short_pith_number":"pith:N3ZRWJJS","canonical_record":{"source":{"id":"2007.12163","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-07-23T17:52:03Z","cross_cats_sorted":[],"title_canon_sha256":"b8582c98ea811d797168e6a6ba0bca166d4eeffea352bbb070f9060e64c91058","abstract_canon_sha256":"aafedc75801323c92e3e7aa132d35a5ce2dc90626dc5ab3b1ea5ec2f3a24b5ad"},"schema_version":"1.0"},"canonical_sha256":"6ef31b2532f65244d22d813b56a75a24dde3f6e02787e7c970feea8114586fd9","source":{"kind":"arxiv","id":"2007.12163","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.12163","created_at":"2026-07-05T01:34:11Z"},{"alias_kind":"arxiv_version","alias_value":"2007.12163v2","created_at":"2026-07-05T01:34:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.12163","created_at":"2026-07-05T01:34:11Z"},{"alias_kind":"pith_short_12","alias_value":"N3ZRWJJS6ZJE","created_at":"2026-07-05T01:34:11Z"},{"alias_kind":"pith_short_16","alias_value":"N3ZRWJJS6ZJEJURN","created_at":"2026-07-05T01:34:11Z"},{"alias_kind":"pith_short_8","alias_value":"N3ZRWJJS","created_at":"2026-07-05T01:34:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:N3ZRWJJS6ZJEJURNQE5VNJ22ET","target":"record","payload":{"canonical_record":{"source":{"id":"2007.12163","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-07-23T17:52:03Z","cross_cats_sorted":[],"title_canon_sha256":"b8582c98ea811d797168e6a6ba0bca166d4eeffea352bbb070f9060e64c91058","abstract_canon_sha256":"aafedc75801323c92e3e7aa132d35a5ce2dc90626dc5ab3b1ea5ec2f3a24b5ad"},"schema_version":"1.0"},"canonical_sha256":"6ef31b2532f65244d22d813b56a75a24dde3f6e02787e7c970feea8114586fd9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:34:11.214275Z","signature_b64":"t4CToSHovBFgL8nynZwfuF9a7wbQHT/wibzYPXOpkLz8EOXtSTSzR91AIzsuP28sSS3GO0jWcebxeZfSu+CTCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ef31b2532f65244d22d813b56a75a24dde3f6e02787e7c970feea8114586fd9","last_reissued_at":"2026-07-05T01:34:11.213740Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:34:11.213740Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.12163","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:34:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rPr/l9NHYWWQoEq5k/jdBwMwmyFslNq7388LqPAYZEykNBKgiy6rxg9birDfsbmuAr7a75WmeTg3UY5oqvQyBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T23:27:04.935183Z"},"content_sha256":"421852592d93f4ca4f4d0c2e39488be965031f5e7ad53b9f85ecaef30fc822a7","schema_version":"1.0","event_id":"sha256:421852592d93f4ca4f4d0c2e39488be965031f5e7ad53b9f85ecaef30fc822a7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:N3ZRWJJS6ZJEJURNQE5VNJ22ET","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Brown, Andrew Zisserman, Vicky Kalogeiton, Weidi Xie","submitted_at":"2020-07-23T17:52:03Z","abstract_excerpt":"Optimising a ranking-based metric, such as Average Precision (AP), is notoriously challenging due to the fact that it is non-differentiable, and hence cannot be optimised directly using gradient-descent methods. To this end, we introduce an objective that optimises instead a smoothed approximation of AP, coined Smooth-AP. Smooth-AP is a plug-and-play objective function that allows for end-to-end training of deep networks with a simple and elegant implementation. We also present an analysis for why directly optimising the ranking based metric of AP offers benefits over other deep metric learnin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.12163","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2007.12163/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:34:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UELp8l1PCEJOTsIKV2z7GCtyhQLcbM0h/avi4k+YFQBaBdGNzhQjPamSS+svvkWPRs2XbLyZLnB0RSLZKmRACQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T23:27:04.937051Z"},"content_sha256":"8d8aeb91dc7950ef506cdb46bb434089b1501670e3a8310750d2b7825325f604","schema_version":"1.0","event_id":"sha256:8d8aeb91dc7950ef506cdb46bb434089b1501670e3a8310750d2b7825325f604"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N3ZRWJJS6ZJEJURNQE5VNJ22ET/bundle.json","state_url":"https://pith.science/pith/N3ZRWJJS6ZJEJURNQE5VNJ22ET/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N3ZRWJJS6ZJEJURNQE5VNJ22ET/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":"2026-08-10T23:27:04Z","links":{"resolver":"https://pith.science/pith/N3ZRWJJS6ZJEJURNQE5VNJ22ET","bundle":"https://pith.science/pith/N3ZRWJJS6ZJEJURNQE5VNJ22ET/bundle.json","state":"https://pith.science/pith/N3ZRWJJS6ZJEJURNQE5VNJ22ET/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N3ZRWJJS6ZJEJURNQE5VNJ22ET/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:N3ZRWJJS6ZJEJURNQE5VNJ22ET","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":"aafedc75801323c92e3e7aa132d35a5ce2dc90626dc5ab3b1ea5ec2f3a24b5ad","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-07-23T17:52:03Z","title_canon_sha256":"b8582c98ea811d797168e6a6ba0bca166d4eeffea352bbb070f9060e64c91058"},"schema_version":"1.0","source":{"id":"2007.12163","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.12163","created_at":"2026-07-05T01:34:11Z"},{"alias_kind":"arxiv_version","alias_value":"2007.12163v2","created_at":"2026-07-05T01:34:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.12163","created_at":"2026-07-05T01:34:11Z"},{"alias_kind":"pith_short_12","alias_value":"N3ZRWJJS6ZJE","created_at":"2026-07-05T01:34:11Z"},{"alias_kind":"pith_short_16","alias_value":"N3ZRWJJS6ZJEJURN","created_at":"2026-07-05T01:34:11Z"},{"alias_kind":"pith_short_8","alias_value":"N3ZRWJJS","created_at":"2026-07-05T01:34:11Z"}],"graph_snapshots":[{"event_id":"sha256:8d8aeb91dc7950ef506cdb46bb434089b1501670e3a8310750d2b7825325f604","target":"graph","created_at":"2026-07-05T01:34:11Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2007.12163/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Optimising a ranking-based metric, such as Average Precision (AP), is notoriously challenging due to the fact that it is non-differentiable, and hence cannot be optimised directly using gradient-descent methods. To this end, we introduce an objective that optimises instead a smoothed approximation of AP, coined Smooth-AP. Smooth-AP is a plug-and-play objective function that allows for end-to-end training of deep networks with a simple and elegant implementation. We also present an analysis for why directly optimising the ranking based metric of AP offers benefits over other deep metric learnin","authors_text":"Andrew Brown, Andrew Zisserman, Vicky Kalogeiton, Weidi Xie","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-07-23T17:52:03Z","title":"Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.12163","kind":"arxiv","version":2},"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":"sha256:421852592d93f4ca4f4d0c2e39488be965031f5e7ad53b9f85ecaef30fc822a7","target":"record","created_at":"2026-07-05T01:34:11Z","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":"aafedc75801323c92e3e7aa132d35a5ce2dc90626dc5ab3b1ea5ec2f3a24b5ad","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-07-23T17:52:03Z","title_canon_sha256":"b8582c98ea811d797168e6a6ba0bca166d4eeffea352bbb070f9060e64c91058"},"schema_version":"1.0","source":{"id":"2007.12163","kind":"arxiv","version":2}},"canonical_sha256":"6ef31b2532f65244d22d813b56a75a24dde3f6e02787e7c970feea8114586fd9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ef31b2532f65244d22d813b56a75a24dde3f6e02787e7c970feea8114586fd9","first_computed_at":"2026-07-05T01:34:11.213740Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:34:11.213740Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t4CToSHovBFgL8nynZwfuF9a7wbQHT/wibzYPXOpkLz8EOXtSTSzR91AIzsuP28sSS3GO0jWcebxeZfSu+CTCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:34:11.214275Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.12163","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:421852592d93f4ca4f4d0c2e39488be965031f5e7ad53b9f85ecaef30fc822a7","sha256:8d8aeb91dc7950ef506cdb46bb434089b1501670e3a8310750d2b7825325f604"],"state_sha256":"029988354cb9c6f4fb456263514b56a63b2daf6a024f5db28a040e30e3aa40a0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EEK4fmG50YzwHtVh5RBMdMTSPFI/r757CKwkBHs5PWM88LVARWi4JkKUa5eJeFDw6hT3WUQR0M7kHaQIbcYoDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T23:27:04.942037Z","bundle_sha256":"4d0e58e353010edfb791e78d982bae25cb75095d73bb2ade6de117843134459d"}}