{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:ZQPSMRYT76ZZPSICVMZGY5WLYX","short_pith_number":"pith:ZQPSMRYT","canonical_record":{"source":{"id":"2210.04180","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-09T06:17:31Z","cross_cats_sorted":[],"title_canon_sha256":"cdf9155ff8a5018e55b1d46fc43dcf53f458e1ce5799498481332b1ecef83aef","abstract_canon_sha256":"a65539024ace35715dbf1edbe870b6797154e129edad49d9c8d6380e2cb4e391"},"schema_version":"1.0"},"canonical_sha256":"cc1f264713ffb397c902ab326c76cbc5fedefba20409a4371b085a0d236f6627","source":{"kind":"arxiv","id":"2210.04180","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.04180","created_at":"2026-07-05T05:04:37Z"},{"alias_kind":"arxiv_version","alias_value":"2210.04180v1","created_at":"2026-07-05T05:04:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.04180","created_at":"2026-07-05T05:04:37Z"},{"alias_kind":"pith_short_12","alias_value":"ZQPSMRYT76ZZ","created_at":"2026-07-05T05:04:37Z"},{"alias_kind":"pith_short_16","alias_value":"ZQPSMRYT76ZZPSIC","created_at":"2026-07-05T05:04:37Z"},{"alias_kind":"pith_short_8","alias_value":"ZQPSMRYT","created_at":"2026-07-05T05:04:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:ZQPSMRYT76ZZPSICVMZGY5WLYX","target":"record","payload":{"canonical_record":{"source":{"id":"2210.04180","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-09T06:17:31Z","cross_cats_sorted":[],"title_canon_sha256":"cdf9155ff8a5018e55b1d46fc43dcf53f458e1ce5799498481332b1ecef83aef","abstract_canon_sha256":"a65539024ace35715dbf1edbe870b6797154e129edad49d9c8d6380e2cb4e391"},"schema_version":"1.0"},"canonical_sha256":"cc1f264713ffb397c902ab326c76cbc5fedefba20409a4371b085a0d236f6627","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:04:37.323942Z","signature_b64":"KtCcMuMt4yJ+YbLKLEn8D6qojYikHdk3lU0w3JGZmxL+noDJa3EDI2gh/+VuLRDQENs/+cY6dNTk10gEI+bDBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc1f264713ffb397c902ab326c76cbc5fedefba20409a4371b085a0d236f6627","last_reissued_at":"2026-07-05T05:04:37.323475Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:04:37.323475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.04180","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":"2026-07-05T05:04:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/dmTf6V05zgr2IF//TM/5ZgyfmEnL/2AAS0i+keaybxb3XxuPgSIKb+ZJVO5a3ATHh0/K3g5hej21eZcdvcCDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T19:12:37.518483Z"},"content_sha256":"0e085393493bb3a4cebd5c3b8222f120b281aadca7661effc2452cf1b68f3f84","schema_version":"1.0","event_id":"sha256:0e085393493bb3a4cebd5c3b8222f120b281aadca7661effc2452cf1b68f3f84"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:ZQPSMRYT76ZZPSICVMZGY5WLYX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Coded Residual Transform for Generalizable Deep Metric Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianxin Wang, Min Li, Shichao Kan, Yigang Cen, Yixiong Liang, Zhihai He","submitted_at":"2022-10-09T06:17:31Z","abstract_excerpt":"A fundamental challenge in deep metric learning is the generalization capability of the feature embedding network model since the embedding network learned on training classes need to be evaluated on new test classes. To address this challenge, in this paper, we introduce a new method called coded residual transform (CRT) for deep metric learning to significantly improve its generalization capability. Specifically, we learn a set of diversified prototype features, project the feature map onto each prototype, and then encode its features using their projection residuals weighted by their correl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.04180","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2210.04180/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":"2026-07-05T05:04:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pNGsBizyeEp6ryYOvM/c4i5L8XssWqnk1AziCDgjUn2ToQCtarzKqFgxzPpuQTqy0XcjC64MOe6Ce6F9TsapCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T19:12:37.518861Z"},"content_sha256":"64560a3843b60f248ad6a1a1b490a5a8a5ddd998706f6696e954d1feb466b20c","schema_version":"1.0","event_id":"sha256:64560a3843b60f248ad6a1a1b490a5a8a5ddd998706f6696e954d1feb466b20c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZQPSMRYT76ZZPSICVMZGY5WLYX/bundle.json","state_url":"https://pith.science/pith/ZQPSMRYT76ZZPSICVMZGY5WLYX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZQPSMRYT76ZZPSICVMZGY5WLYX/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":"2026-08-17T19:12:37Z","links":{"resolver":"https://pith.science/pith/ZQPSMRYT76ZZPSICVMZGY5WLYX","bundle":"https://pith.science/pith/ZQPSMRYT76ZZPSICVMZGY5WLYX/bundle.json","state":"https://pith.science/pith/ZQPSMRYT76ZZPSICVMZGY5WLYX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZQPSMRYT76ZZPSICVMZGY5WLYX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ZQPSMRYT76ZZPSICVMZGY5WLYX","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":"a65539024ace35715dbf1edbe870b6797154e129edad49d9c8d6380e2cb4e391","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-09T06:17:31Z","title_canon_sha256":"cdf9155ff8a5018e55b1d46fc43dcf53f458e1ce5799498481332b1ecef83aef"},"schema_version":"1.0","source":{"id":"2210.04180","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.04180","created_at":"2026-07-05T05:04:37Z"},{"alias_kind":"arxiv_version","alias_value":"2210.04180v1","created_at":"2026-07-05T05:04:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.04180","created_at":"2026-07-05T05:04:37Z"},{"alias_kind":"pith_short_12","alias_value":"ZQPSMRYT76ZZ","created_at":"2026-07-05T05:04:37Z"},{"alias_kind":"pith_short_16","alias_value":"ZQPSMRYT76ZZPSIC","created_at":"2026-07-05T05:04:37Z"},{"alias_kind":"pith_short_8","alias_value":"ZQPSMRYT","created_at":"2026-07-05T05:04:37Z"}],"graph_snapshots":[{"event_id":"sha256:64560a3843b60f248ad6a1a1b490a5a8a5ddd998706f6696e954d1feb466b20c","target":"graph","created_at":"2026-07-05T05:04:37Z","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/2210.04180/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A fundamental challenge in deep metric learning is the generalization capability of the feature embedding network model since the embedding network learned on training classes need to be evaluated on new test classes. To address this challenge, in this paper, we introduce a new method called coded residual transform (CRT) for deep metric learning to significantly improve its generalization capability. Specifically, we learn a set of diversified prototype features, project the feature map onto each prototype, and then encode its features using their projection residuals weighted by their correl","authors_text":"Jianxin Wang, Min Li, Shichao Kan, Yigang Cen, Yixiong Liang, Zhihai He","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-09T06:17:31Z","title":"Coded Residual Transform for Generalizable Deep Metric Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.04180","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":"sha256:0e085393493bb3a4cebd5c3b8222f120b281aadca7661effc2452cf1b68f3f84","target":"record","created_at":"2026-07-05T05:04:37Z","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":"a65539024ace35715dbf1edbe870b6797154e129edad49d9c8d6380e2cb4e391","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-09T06:17:31Z","title_canon_sha256":"cdf9155ff8a5018e55b1d46fc43dcf53f458e1ce5799498481332b1ecef83aef"},"schema_version":"1.0","source":{"id":"2210.04180","kind":"arxiv","version":1}},"canonical_sha256":"cc1f264713ffb397c902ab326c76cbc5fedefba20409a4371b085a0d236f6627","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc1f264713ffb397c902ab326c76cbc5fedefba20409a4371b085a0d236f6627","first_computed_at":"2026-07-05T05:04:37.323475Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:04:37.323475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KtCcMuMt4yJ+YbLKLEn8D6qojYikHdk3lU0w3JGZmxL+noDJa3EDI2gh/+VuLRDQENs/+cY6dNTk10gEI+bDBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:04:37.323942Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.04180","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e085393493bb3a4cebd5c3b8222f120b281aadca7661effc2452cf1b68f3f84","sha256:64560a3843b60f248ad6a1a1b490a5a8a5ddd998706f6696e954d1feb466b20c"],"state_sha256":"7ace207701f332c5993775b8c7f444730c19b336ab0fad3b83e4d1ffd45b64f2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lHEy0Jn+t4q4BEPkZDYxetZWKGlkNug0PqHEf7Mr/q9BP1nTLsHu3CLiKIgsuG6BAQm5kHSsni3DAS5dis+AAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T19:12:37.521217Z","bundle_sha256":"211c8da0de3276d516b801d4d46affe5bc172b5c0f07144de8cceb4b15b47aa7"}}