{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HSFINWXTTCL2B4MDF7XCKMKS6H","short_pith_number":"pith:HSFINWXT","schema_version":"1.0","canonical_sha256":"3c8a86daf39897a0f1832fee253152f1e41564d8778273fedcf7fab98317c3da","source":{"kind":"arxiv","id":"2308.09228","version":2},"attestation_state":"computed","paper":{"title":"Generalized Sum Pooling for Metric Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"A. Ayd{\\i}n Alatan, Ozan Sener, Yeti Z. Gurbuz","submitted_at":"2023-08-18T01:20:25Z","abstract_excerpt":"A common architectural choice for deep metric learning is a convolutional neural network followed by global average pooling (GAP). Albeit simple, GAP is a highly effective way to aggregate information. One possible explanation for the effectiveness of GAP is considering each feature vector as representing a different semantic entity and GAP as a convex combination of them. Following this perspective, we generalize GAP and propose a learnable generalized sum pooling method (GSP). GSP improves GAP with two distinct abilities: i) the ability to choose a subset of semantic entities, effectively le"},"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":"2308.09228","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-18T01:20:25Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"52c2fa3de8f565c115ca26d6297c2521f27f71fbbac1d8b9949636ab0079911e","abstract_canon_sha256":"441575a8311a9902dfff5277cc8b7e1c9b54434bd504cdd88ad6a22377e35514"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:43:25.682293Z","signature_b64":"gd/3o7TF9xkDHX8fgyq+pVAtBfXfPiMaO0S7I1eiCw4v5F0SIzWMlfdt/bdkFodKZxUGxrN2zNDkcLELYaNwBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c8a86daf39897a0f1832fee253152f1e41564d8778273fedcf7fab98317c3da","last_reissued_at":"2026-07-05T06:43:25.681779Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:43:25.681779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalized Sum Pooling for Metric Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"A. Ayd{\\i}n Alatan, Ozan Sener, Yeti Z. Gurbuz","submitted_at":"2023-08-18T01:20:25Z","abstract_excerpt":"A common architectural choice for deep metric learning is a convolutional neural network followed by global average pooling (GAP). Albeit simple, GAP is a highly effective way to aggregate information. One possible explanation for the effectiveness of GAP is considering each feature vector as representing a different semantic entity and GAP as a convex combination of them. Following this perspective, we generalize GAP and propose a learnable generalized sum pooling method (GSP). GSP improves GAP with two distinct abilities: i) the ability to choose a subset of semantic entities, effectively le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.09228","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/2308.09228/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":"2308.09228","created_at":"2026-07-05T06:43:25.681843+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.09228v2","created_at":"2026-07-05T06:43:25.681843+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.09228","created_at":"2026-07-05T06:43:25.681843+00:00"},{"alias_kind":"pith_short_12","alias_value":"HSFINWXTTCL2","created_at":"2026-07-05T06:43:25.681843+00:00"},{"alias_kind":"pith_short_16","alias_value":"HSFINWXTTCL2B4MD","created_at":"2026-07-05T06:43:25.681843+00:00"},{"alias_kind":"pith_short_8","alias_value":"HSFINWXT","created_at":"2026-07-05T06:43:25.681843+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/HSFINWXTTCL2B4MDF7XCKMKS6H","json":"https://pith.science/pith/HSFINWXTTCL2B4MDF7XCKMKS6H.json","graph_json":"https://pith.science/api/pith-number/HSFINWXTTCL2B4MDF7XCKMKS6H/graph.json","events_json":"https://pith.science/api/pith-number/HSFINWXTTCL2B4MDF7XCKMKS6H/events.json","paper":"https://pith.science/paper/HSFINWXT"},"agent_actions":{"view_html":"https://pith.science/pith/HSFINWXTTCL2B4MDF7XCKMKS6H","download_json":"https://pith.science/pith/HSFINWXTTCL2B4MDF7XCKMKS6H.json","view_paper":"https://pith.science/paper/HSFINWXT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.09228&json=true","fetch_graph":"https://pith.science/api/pith-number/HSFINWXTTCL2B4MDF7XCKMKS6H/graph.json","fetch_events":"https://pith.science/api/pith-number/HSFINWXTTCL2B4MDF7XCKMKS6H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HSFINWXTTCL2B4MDF7XCKMKS6H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HSFINWXTTCL2B4MDF7XCKMKS6H/action/storage_attestation","attest_author":"https://pith.science/pith/HSFINWXTTCL2B4MDF7XCKMKS6H/action/author_attestation","sign_citation":"https://pith.science/pith/HSFINWXTTCL2B4MDF7XCKMKS6H/action/citation_signature","submit_replication":"https://pith.science/pith/HSFINWXTTCL2B4MDF7XCKMKS6H/action/replication_record"}},"created_at":"2026-07-05T06:43:25.681843+00:00","updated_at":"2026-07-05T06:43:25.681843+00:00"}