{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:NVXCHIII5KMRSSEJF4WILDSJHI","short_pith_number":"pith:NVXCHIII","canonical_record":{"source":{"id":"1906.07589","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-18T13:59:34Z","cross_cats_sorted":[],"title_canon_sha256":"911d99a0876682d96456604b74768c69e09b8b68d3479c783d30db10f3df1c29","abstract_canon_sha256":"71e39ce37e9332eb2d7025f0dd92a129dece751cc4d4c293702996f3384f0444"},"schema_version":"1.0"},"canonical_sha256":"6d6e23a108ea991948892f2c858e493a3d4a1fd1a428d0fff15e0f84bc8034db","source":{"kind":"arxiv","id":"1906.07589","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.07589","created_at":"2026-05-17T23:43:07Z"},{"alias_kind":"arxiv_version","alias_value":"1906.07589v1","created_at":"2026-05-17T23:43:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.07589","created_at":"2026-05-17T23:43:07Z"},{"alias_kind":"pith_short_12","alias_value":"NVXCHIII5KMR","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"NVXCHIII5KMRSSEJ","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"NVXCHIII","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:NVXCHIII5KMRSSEJF4WILDSJHI","target":"record","payload":{"canonical_record":{"source":{"id":"1906.07589","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-18T13:59:34Z","cross_cats_sorted":[],"title_canon_sha256":"911d99a0876682d96456604b74768c69e09b8b68d3479c783d30db10f3df1c29","abstract_canon_sha256":"71e39ce37e9332eb2d7025f0dd92a129dece751cc4d4c293702996f3384f0444"},"schema_version":"1.0"},"canonical_sha256":"6d6e23a108ea991948892f2c858e493a3d4a1fd1a428d0fff15e0f84bc8034db","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:07.412837Z","signature_b64":"yhXOGYsuZ/06xaEe4tjUndmxZjcWWf+7WFag0d19cGKy9kH8YHmSS0GH4MKSECHLG3DBO+oQIwoWYE5ZMX72Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d6e23a108ea991948892f2c858e493a3d4a1fd1a428d0fff15e0f84bc8034db","last_reissued_at":"2026-05-17T23:43:07.412218Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:07.412218Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.07589","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":"2026-05-17T23:43:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JigJAMh2WYPP3JQ4qiz7flDaeB1kTqnoVMoRzVArsq/olvkgADL+rXcQzN8LzniWdW9o0umTJTHXcxkGq7u9Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T21:32:47.360572Z"},"content_sha256":"1b7df7e4b79cb75cff5151d0dd220120b69f17bd8353499c40ee6936992807cb","schema_version":"1.0","event_id":"sha256:1b7df7e4b79cb75cff5151d0dd220120b69f17bd8353499c40ee6936992807cb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:NVXCHIII5KMRSSEJF4WILDSJHI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning with Average Precision: Training Image Retrieval with a Listwise Loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cesar Roberto de Souza, Jerome Revaud, Jon Almazan, Rafael Sampaio de Rezende","submitted_at":"2019-06-18T13:59:34Z","abstract_excerpt":"Image retrieval can be formulated as a ranking problem where the goal is to order database images by decreasing similarity to the query. Recent deep models for image retrieval have outperformed traditional methods by leveraging ranking-tailored loss functions, but important theoretical and practical problems remain. First, rather than directly optimizing the global ranking, they minimize an upper-bound on the essential loss, which does not necessarily result in an optimal mean average precision (mAP). Second, these methods require significant engineering efforts to work well, e.g. special pre-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.07589","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":"2026-05-17T23:43:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EFbU+C4ozJKJLyaKwK7ZNm5f3CtGTq181cZ7hqJii3+eEN0oOuIbo9gUPsd81RyPS5h/RIdoK8zdAOUhxJSrDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T21:32:47.360933Z"},"content_sha256":"76b06491de7a54557cff34778c7ac911c47283971b28d8e27a09488bf3521215","schema_version":"1.0","event_id":"sha256:76b06491de7a54557cff34778c7ac911c47283971b28d8e27a09488bf3521215"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NVXCHIII5KMRSSEJF4WILDSJHI/bundle.json","state_url":"https://pith.science/pith/NVXCHIII5KMRSSEJF4WILDSJHI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NVXCHIII5KMRSSEJF4WILDSJHI/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":"2026-06-05T21:32:47Z","links":{"resolver":"https://pith.science/pith/NVXCHIII5KMRSSEJF4WILDSJHI","bundle":"https://pith.science/pith/NVXCHIII5KMRSSEJF4WILDSJHI/bundle.json","state":"https://pith.science/pith/NVXCHIII5KMRSSEJF4WILDSJHI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NVXCHIII5KMRSSEJF4WILDSJHI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:NVXCHIII5KMRSSEJF4WILDSJHI","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":"71e39ce37e9332eb2d7025f0dd92a129dece751cc4d4c293702996f3384f0444","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-18T13:59:34Z","title_canon_sha256":"911d99a0876682d96456604b74768c69e09b8b68d3479c783d30db10f3df1c29"},"schema_version":"1.0","source":{"id":"1906.07589","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.07589","created_at":"2026-05-17T23:43:07Z"},{"alias_kind":"arxiv_version","alias_value":"1906.07589v1","created_at":"2026-05-17T23:43:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.07589","created_at":"2026-05-17T23:43:07Z"},{"alias_kind":"pith_short_12","alias_value":"NVXCHIII5KMR","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"NVXCHIII5KMRSSEJ","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"NVXCHIII","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:76b06491de7a54557cff34778c7ac911c47283971b28d8e27a09488bf3521215","target":"graph","created_at":"2026-05-17T23:43:07Z","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":"Image retrieval can be formulated as a ranking problem where the goal is to order database images by decreasing similarity to the query. Recent deep models for image retrieval have outperformed traditional methods by leveraging ranking-tailored loss functions, but important theoretical and practical problems remain. First, rather than directly optimizing the global ranking, they minimize an upper-bound on the essential loss, which does not necessarily result in an optimal mean average precision (mAP). Second, these methods require significant engineering efforts to work well, e.g. special pre-","authors_text":"Cesar Roberto de Souza, Jerome Revaud, Jon Almazan, Rafael Sampaio de Rezende","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-18T13:59:34Z","title":"Learning with Average Precision: Training Image Retrieval with a Listwise Loss"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.07589","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":"sha256:1b7df7e4b79cb75cff5151d0dd220120b69f17bd8353499c40ee6936992807cb","target":"record","created_at":"2026-05-17T23:43:07Z","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":"71e39ce37e9332eb2d7025f0dd92a129dece751cc4d4c293702996f3384f0444","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-18T13:59:34Z","title_canon_sha256":"911d99a0876682d96456604b74768c69e09b8b68d3479c783d30db10f3df1c29"},"schema_version":"1.0","source":{"id":"1906.07589","kind":"arxiv","version":1}},"canonical_sha256":"6d6e23a108ea991948892f2c858e493a3d4a1fd1a428d0fff15e0f84bc8034db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6d6e23a108ea991948892f2c858e493a3d4a1fd1a428d0fff15e0f84bc8034db","first_computed_at":"2026-05-17T23:43:07.412218Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:07.412218Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yhXOGYsuZ/06xaEe4tjUndmxZjcWWf+7WFag0d19cGKy9kH8YHmSS0GH4MKSECHLG3DBO+oQIwoWYE5ZMX72Ag==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:07.412837Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.07589","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1b7df7e4b79cb75cff5151d0dd220120b69f17bd8353499c40ee6936992807cb","sha256:76b06491de7a54557cff34778c7ac911c47283971b28d8e27a09488bf3521215"],"state_sha256":"ed732fd2b8343a813a234a15e23117996a32eb955389acb4a39708f887f92133"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UIoMWrP5qGnXKgXIcJ49NC7KSDqvJ28pi7faJxAFhTJcbi1KzQJj4eHiH/73O2Vf1JfTqp17Ik2rMN+fjefBCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T21:32:47.363148Z","bundle_sha256":"cd0822a1b568cb9f5f198dc18993a9a2c5926eb1d9d02d2d909c2c8b9fca2028"}}