{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:GLTEEGT5IO64GKW4QITSI6JRZ7","short_pith_number":"pith:GLTEEGT5","schema_version":"1.0","canonical_sha256":"32e6421a7d43bdc32adc8227247931cfd16d623f1631110628db63d3793718c3","source":{"kind":"arxiv","id":"1911.12110","version":1},"attestation_state":"computed","paper":{"title":"AdaSample: Adaptive Sampling of Hard Positives for Descriptor Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jia-Wang Bian, Le Zhang, Ming-Ming Cheng, Xin-Yu Zhang, Yun Liu, Zao-Yi Zheng","submitted_at":"2019-11-27T12:38:08Z","abstract_excerpt":"Triplet loss has been widely employed in a wide range of computer vision tasks, including local descriptor learning. The effectiveness of the triplet loss heavily relies on the triplet selection, in which a common practice is to first sample intra-class patches (positives) from the dataset for batch construction and then mine in-batch negatives to form triplets. For high-informativeness triplet collection, researchers mostly focus on mining hard negatives in the second stage, while paying relatively less attention to constructing informative batches. To alleviate this issue, we propose AdaSamp"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1911.12110","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-11-27T12:38:08Z","cross_cats_sorted":[],"title_canon_sha256":"99fad714f68902b046e6c967d599147729ddabd689f6d026798f855627804ef1","abstract_canon_sha256":"8dbb70981856e68cc24c2497aa5e0c939fefd104884a1bff33a0470cbca6e55f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:22:30.574508Z","signature_b64":"NSEGpyffCz+oTBdXthV9gf5rNmuG7fYQLdJb5I1ueRBU6xOg8O+E94P7AGIC7WhB5QJrYjAMVo+c0skWjLj7Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32e6421a7d43bdc32adc8227247931cfd16d623f1631110628db63d3793718c3","last_reissued_at":"2026-07-05T00:22:30.573958Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:22:30.573958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AdaSample: Adaptive Sampling of Hard Positives for Descriptor Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jia-Wang Bian, Le Zhang, Ming-Ming Cheng, Xin-Yu Zhang, Yun Liu, Zao-Yi Zheng","submitted_at":"2019-11-27T12:38:08Z","abstract_excerpt":"Triplet loss has been widely employed in a wide range of computer vision tasks, including local descriptor learning. The effectiveness of the triplet loss heavily relies on the triplet selection, in which a common practice is to first sample intra-class patches (positives) from the dataset for batch construction and then mine in-batch negatives to form triplets. For high-informativeness triplet collection, researchers mostly focus on mining hard negatives in the second stage, while paying relatively less attention to constructing informative batches. To alleviate this issue, we propose AdaSamp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.12110","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/1911.12110/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1911.12110","created_at":"2026-07-05T00:22:30.574014+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.12110v1","created_at":"2026-07-05T00:22:30.574014+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.12110","created_at":"2026-07-05T00:22:30.574014+00:00"},{"alias_kind":"pith_short_12","alias_value":"GLTEEGT5IO64","created_at":"2026-07-05T00:22:30.574014+00:00"},{"alias_kind":"pith_short_16","alias_value":"GLTEEGT5IO64GKW4","created_at":"2026-07-05T00:22:30.574014+00:00"},{"alias_kind":"pith_short_8","alias_value":"GLTEEGT5","created_at":"2026-07-05T00:22:30.574014+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GLTEEGT5IO64GKW4QITSI6JRZ7","json":"https://pith.science/pith/GLTEEGT5IO64GKW4QITSI6JRZ7.json","graph_json":"https://pith.science/api/pith-number/GLTEEGT5IO64GKW4QITSI6JRZ7/graph.json","events_json":"https://pith.science/api/pith-number/GLTEEGT5IO64GKW4QITSI6JRZ7/events.json","paper":"https://pith.science/paper/GLTEEGT5"},"agent_actions":{"view_html":"https://pith.science/pith/GLTEEGT5IO64GKW4QITSI6JRZ7","download_json":"https://pith.science/pith/GLTEEGT5IO64GKW4QITSI6JRZ7.json","view_paper":"https://pith.science/paper/GLTEEGT5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.12110&json=true","fetch_graph":"https://pith.science/api/pith-number/GLTEEGT5IO64GKW4QITSI6JRZ7/graph.json","fetch_events":"https://pith.science/api/pith-number/GLTEEGT5IO64GKW4QITSI6JRZ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GLTEEGT5IO64GKW4QITSI6JRZ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GLTEEGT5IO64GKW4QITSI6JRZ7/action/storage_attestation","attest_author":"https://pith.science/pith/GLTEEGT5IO64GKW4QITSI6JRZ7/action/author_attestation","sign_citation":"https://pith.science/pith/GLTEEGT5IO64GKW4QITSI6JRZ7/action/citation_signature","submit_replication":"https://pith.science/pith/GLTEEGT5IO64GKW4QITSI6JRZ7/action/replication_record"}},"created_at":"2026-07-05T00:22:30.574014+00:00","updated_at":"2026-07-05T00:22:30.574014+00:00"}