{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:NKREYGT76FHNX57EGLEOHJVIZB","short_pith_number":"pith:NKREYGT7","canonical_record":{"source":{"id":"1903.08923","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-21T11:10:05Z","cross_cats_sorted":[],"title_canon_sha256":"7645ab477967351add605a5a6faa967a52bd6209f699a27a30f16f7d1e031590","abstract_canon_sha256":"1cca9323bdd1d5007faa5914e5137f74eefa8778f4d9d40375174b6f88055b6d"},"schema_version":"1.0"},"canonical_sha256":"6aa24c1a7ff14edbf7e432c8e3a6a8c85295e9ba3e81b2e5a8be55b6db6faa4e","source":{"kind":"arxiv","id":"1903.08923","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.08923","created_at":"2026-05-17T23:50:43Z"},{"alias_kind":"arxiv_version","alias_value":"1903.08923v1","created_at":"2026-05-17T23:50:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.08923","created_at":"2026-05-17T23:50:43Z"},{"alias_kind":"pith_short_12","alias_value":"NKREYGT76FHN","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"NKREYGT76FHNX57E","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"NKREYGT7","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:NKREYGT76FHNX57EGLEOHJVIZB","target":"record","payload":{"canonical_record":{"source":{"id":"1903.08923","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-21T11:10:05Z","cross_cats_sorted":[],"title_canon_sha256":"7645ab477967351add605a5a6faa967a52bd6209f699a27a30f16f7d1e031590","abstract_canon_sha256":"1cca9323bdd1d5007faa5914e5137f74eefa8778f4d9d40375174b6f88055b6d"},"schema_version":"1.0"},"canonical_sha256":"6aa24c1a7ff14edbf7e432c8e3a6a8c85295e9ba3e81b2e5a8be55b6db6faa4e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:43.564538Z","signature_b64":"I8BDRratlBhFbjsyO4mnzQNus6GDzQqQu/pqVh0l0fJc4Tsc94G/jwoSrNQAZixv35eZyKT3C1Rx2MlYEn8dAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6aa24c1a7ff14edbf7e432c8e3a6a8c85295e9ba3e81b2e5a8be55b6db6faa4e","last_reissued_at":"2026-05-17T23:50:43.564135Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:43.564135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.08923","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":"2026-05-17T23:50:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MaP0zvlIm4eYo6BoDiRBM4TdgLvWIJQy4+mySH5QO4DX0sBBPTpizMWLFtQ6FvgGRVF+pv0h+XdQ4kUyJNErBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T01:52:30.760167Z"},"content_sha256":"019cec0ca0be1c168f75e529cbdffc83cc4b2d42db1ed010f7a4976736399362","schema_version":"1.0","event_id":"sha256:019cec0ca0be1c168f75e529cbdffc83cc4b2d42db1ed010f7a4976736399362"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:NKREYGT76FHNX57EGLEOHJVIZB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning with Batch-wise Optimal Transport Loss for 3D Shape Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Han Sun, Lin Xu, Yuai Liu","submitted_at":"2019-03-21T11:10:05Z","abstract_excerpt":"Deep metric learning is essential for visual recognition. The widely used pair-wise (or triplet) based loss objectives cannot make full use of semantical information in training samples or give enough attention to those hard samples during optimization. Thus, they often suffer from a slow convergence rate and inferior performance. In this paper, we show how to learn an importance-driven distance metric via optimal transport programming from batches of samples. It can automatically emphasize hard examples and lead to significant improvements in convergence. We propose a new batch-wise optimal t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.08923","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":"2026-05-17T23:50:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5lycTLG1EvxUfyJ+QQUaMfYlj1J+EGb3RNeYd/5Znr1v+nSBJFkLgR+Xg2ka3yDOqa+hGmP0D5rKv8pUOTHYCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T01:52:30.760597Z"},"content_sha256":"8a7728cc72150644918894cabd1ad1f6c28354a7993fe5c5728e8a67885efc71","schema_version":"1.0","event_id":"sha256:8a7728cc72150644918894cabd1ad1f6c28354a7993fe5c5728e8a67885efc71"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NKREYGT76FHNX57EGLEOHJVIZB/bundle.json","state_url":"https://pith.science/pith/NKREYGT76FHNX57EGLEOHJVIZB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NKREYGT76FHNX57EGLEOHJVIZB/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":"2026-06-01T01:52:30Z","links":{"resolver":"https://pith.science/pith/NKREYGT76FHNX57EGLEOHJVIZB","bundle":"https://pith.science/pith/NKREYGT76FHNX57EGLEOHJVIZB/bundle.json","state":"https://pith.science/pith/NKREYGT76FHNX57EGLEOHJVIZB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NKREYGT76FHNX57EGLEOHJVIZB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:NKREYGT76FHNX57EGLEOHJVIZB","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":"1cca9323bdd1d5007faa5914e5137f74eefa8778f4d9d40375174b6f88055b6d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-21T11:10:05Z","title_canon_sha256":"7645ab477967351add605a5a6faa967a52bd6209f699a27a30f16f7d1e031590"},"schema_version":"1.0","source":{"id":"1903.08923","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.08923","created_at":"2026-05-17T23:50:43Z"},{"alias_kind":"arxiv_version","alias_value":"1903.08923v1","created_at":"2026-05-17T23:50:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.08923","created_at":"2026-05-17T23:50:43Z"},{"alias_kind":"pith_short_12","alias_value":"NKREYGT76FHN","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"NKREYGT76FHNX57E","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"NKREYGT7","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:8a7728cc72150644918894cabd1ad1f6c28354a7993fe5c5728e8a67885efc71","target":"graph","created_at":"2026-05-17T23:50:43Z","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":"Deep metric learning is essential for visual recognition. The widely used pair-wise (or triplet) based loss objectives cannot make full use of semantical information in training samples or give enough attention to those hard samples during optimization. Thus, they often suffer from a slow convergence rate and inferior performance. In this paper, we show how to learn an importance-driven distance metric via optimal transport programming from batches of samples. It can automatically emphasize hard examples and lead to significant improvements in convergence. We propose a new batch-wise optimal t","authors_text":"Han Sun, Lin Xu, Yuai Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-21T11:10:05Z","title":"Learning with Batch-wise Optimal Transport Loss for 3D Shape Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.08923","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":"sha256:019cec0ca0be1c168f75e529cbdffc83cc4b2d42db1ed010f7a4976736399362","target":"record","created_at":"2026-05-17T23:50:43Z","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":"1cca9323bdd1d5007faa5914e5137f74eefa8778f4d9d40375174b6f88055b6d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-21T11:10:05Z","title_canon_sha256":"7645ab477967351add605a5a6faa967a52bd6209f699a27a30f16f7d1e031590"},"schema_version":"1.0","source":{"id":"1903.08923","kind":"arxiv","version":1}},"canonical_sha256":"6aa24c1a7ff14edbf7e432c8e3a6a8c85295e9ba3e81b2e5a8be55b6db6faa4e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6aa24c1a7ff14edbf7e432c8e3a6a8c85295e9ba3e81b2e5a8be55b6db6faa4e","first_computed_at":"2026-05-17T23:50:43.564135Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:50:43.564135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I8BDRratlBhFbjsyO4mnzQNus6GDzQqQu/pqVh0l0fJc4Tsc94G/jwoSrNQAZixv35eZyKT3C1Rx2MlYEn8dAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:50:43.564538Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.08923","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:019cec0ca0be1c168f75e529cbdffc83cc4b2d42db1ed010f7a4976736399362","sha256:8a7728cc72150644918894cabd1ad1f6c28354a7993fe5c5728e8a67885efc71"],"state_sha256":"dade0104b740dc5c69aa1fb0934e2c909ffff141f37e778950fed0938507b665"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x6Xq/Fwg6yVE7IZTAY7uX+z96RdtyQRxblQAadsBprzcvHYzEg5PZTclNNsP6MSUFxzoKuiRM4hOXLNSyYmOAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T01:52:30.762834Z","bundle_sha256":"96d6bfb8d40014e75356f8841697743c97577b707c9ff3319e4fef07722223e2"}}