{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BBPBQ3PC3PKM57HWTONU5XE6LV","short_pith_number":"pith:BBPBQ3PC","schema_version":"1.0","canonical_sha256":"085e186de2dbd4cefcf69b9b4edc9e5d4f33d56f427edfb9d988f86129fb8726","source":{"kind":"arxiv","id":"2605.20551","version":1},"attestation_state":"computed","paper":{"title":"Faster or Stronger: Towards Flexible Visual Place Recognition via Weighted Aggregation and Token Pruning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Jan Boehm, Jiaming Zhang, June Moh Goo, Junwei Zheng, Rainer Stiefelhagen, Weijia Fan, Zichao Zeng","submitted_at":"2026-05-19T23:01:57Z","abstract_excerpt":"Visual Place Recognition (VPR) aims to match a query image to reference images of the same place in a large-scale database. Recent state-of-the-art methods employ Vision Transformers (ViTs) as backbone foundation models to extract patch-level features that are robust to viewpoint, illumination, and seasonal variations, which are then aggregated into a compact global descriptor for retrieval. Most existing aggregation methods uniformly pool patch tokens into learned clusters, despite the fact that different clusters often encode distinct spatial or semantic patterns and contribute unequally to "},"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":"2605.20551","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-19T23:01:57Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"745ee879871ddb63b6bfe6fccfcd3e9296551c0c8e278db84656543b888f56ed","abstract_canon_sha256":"dd4a4b2deb21356156c810d89d7ecffcadc110bff96a41dd1dd6eb6416ea9bd7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:42.198490Z","signature_b64":"k2PfA16aq86IM1mfybv+coYeygkrbeOGrbtUgosFO2oWGJpvAPK3qoEGI3+yc0KePG8VjiEc5xVBaffJw5lHDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"085e186de2dbd4cefcf69b9b4edc9e5d4f33d56f427edfb9d988f86129fb8726","last_reissued_at":"2026-05-21T01:04:42.197780Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:42.197780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Faster or Stronger: Towards Flexible Visual Place Recognition via Weighted Aggregation and Token Pruning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Jan Boehm, Jiaming Zhang, June Moh Goo, Junwei Zheng, Rainer Stiefelhagen, Weijia Fan, Zichao Zeng","submitted_at":"2026-05-19T23:01:57Z","abstract_excerpt":"Visual Place Recognition (VPR) aims to match a query image to reference images of the same place in a large-scale database. Recent state-of-the-art methods employ Vision Transformers (ViTs) as backbone foundation models to extract patch-level features that are robust to viewpoint, illumination, and seasonal variations, which are then aggregated into a compact global descriptor for retrieval. Most existing aggregation methods uniformly pool patch tokens into learned clusters, despite the fact that different clusters often encode distinct spatial or semantic patterns and contribute unequally to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20551","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/2605.20551/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":"2605.20551","created_at":"2026-05-21T01:04:42.197885+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.20551v1","created_at":"2026-05-21T01:04:42.197885+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20551","created_at":"2026-05-21T01:04:42.197885+00:00"},{"alias_kind":"pith_short_12","alias_value":"BBPBQ3PC3PKM","created_at":"2026-05-21T01:04:42.197885+00:00"},{"alias_kind":"pith_short_16","alias_value":"BBPBQ3PC3PKM57HW","created_at":"2026-05-21T01:04:42.197885+00:00"},{"alias_kind":"pith_short_8","alias_value":"BBPBQ3PC","created_at":"2026-05-21T01:04:42.197885+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/BBPBQ3PC3PKM57HWTONU5XE6LV","json":"https://pith.science/pith/BBPBQ3PC3PKM57HWTONU5XE6LV.json","graph_json":"https://pith.science/api/pith-number/BBPBQ3PC3PKM57HWTONU5XE6LV/graph.json","events_json":"https://pith.science/api/pith-number/BBPBQ3PC3PKM57HWTONU5XE6LV/events.json","paper":"https://pith.science/paper/BBPBQ3PC"},"agent_actions":{"view_html":"https://pith.science/pith/BBPBQ3PC3PKM57HWTONU5XE6LV","download_json":"https://pith.science/pith/BBPBQ3PC3PKM57HWTONU5XE6LV.json","view_paper":"https://pith.science/paper/BBPBQ3PC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.20551&json=true","fetch_graph":"https://pith.science/api/pith-number/BBPBQ3PC3PKM57HWTONU5XE6LV/graph.json","fetch_events":"https://pith.science/api/pith-number/BBPBQ3PC3PKM57HWTONU5XE6LV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BBPBQ3PC3PKM57HWTONU5XE6LV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BBPBQ3PC3PKM57HWTONU5XE6LV/action/storage_attestation","attest_author":"https://pith.science/pith/BBPBQ3PC3PKM57HWTONU5XE6LV/action/author_attestation","sign_citation":"https://pith.science/pith/BBPBQ3PC3PKM57HWTONU5XE6LV/action/citation_signature","submit_replication":"https://pith.science/pith/BBPBQ3PC3PKM57HWTONU5XE6LV/action/replication_record"}},"created_at":"2026-05-21T01:04:42.197885+00:00","updated_at":"2026-05-21T01:04:42.197885+00:00"}