{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LPIVVIMLRD6OQ7E26W6ONKCCNH","short_pith_number":"pith:LPIVVIML","schema_version":"1.0","canonical_sha256":"5bd15aa18b88fce87c9af5bce6a84269cc0b2189b54e41787ccd203eb59dce25","source":{"kind":"arxiv","id":"2502.17237","version":3},"attestation_state":"computed","paper":{"title":"MegaLoc: One Retrieval to Place Them All","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Carlo Masone, Gabriele Berton","submitted_at":"2025-02-24T15:14:55Z","abstract_excerpt":"Retrieving images from the same location as a given query is an important component of multiple computer vision tasks, like Visual Place Recognition, Landmark Retrieval, Visual Localization, 3D reconstruction, and SLAM. However, existing solutions are built to specifically work for one of these tasks, and are known to fail when the requirements slightly change or when they meet out-of-distribution data. In this paper we combine a variety of existing methods, training techniques, and datasets to train a retrieval model, called MegaLoc, that is performant on multiple tasks. We find that MegaLoc "},"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":"2502.17237","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-24T15:14:55Z","cross_cats_sorted":[],"title_canon_sha256":"151608cd33724549dcf18a84092026a53f10dac8ca157ce3e204e8abeee1f30c","abstract_canon_sha256":"caa4fa0d0897443b6e425a6a17dd4e32a1df5f56432f81672bff61acc237954b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:41.701692Z","signature_b64":"bd+uu9n2UxxrlclUU6bF/drMZKuv6mvjMNGxoww2r3g1UwoaqLFv7LqUC0nKEySuFg7YxC1AR6G3pwPcBW2iDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5bd15aa18b88fce87c9af5bce6a84269cc0b2189b54e41787ccd203eb59dce25","last_reissued_at":"2026-07-05T11:18:41.701264Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:41.701264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MegaLoc: One Retrieval to Place Them All","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Carlo Masone, Gabriele Berton","submitted_at":"2025-02-24T15:14:55Z","abstract_excerpt":"Retrieving images from the same location as a given query is an important component of multiple computer vision tasks, like Visual Place Recognition, Landmark Retrieval, Visual Localization, 3D reconstruction, and SLAM. However, existing solutions are built to specifically work for one of these tasks, and are known to fail when the requirements slightly change or when they meet out-of-distribution data. In this paper we combine a variety of existing methods, training techniques, and datasets to train a retrieval model, called MegaLoc, that is performant on multiple tasks. We find that MegaLoc "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.17237","kind":"arxiv","version":3},"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/2502.17237/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":"2502.17237","created_at":"2026-07-05T11:18:41.701328+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.17237v3","created_at":"2026-07-05T11:18:41.701328+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.17237","created_at":"2026-07-05T11:18:41.701328+00:00"},{"alias_kind":"pith_short_12","alias_value":"LPIVVIMLRD6O","created_at":"2026-07-05T11:18:41.701328+00:00"},{"alias_kind":"pith_short_16","alias_value":"LPIVVIMLRD6OQ7E2","created_at":"2026-07-05T11:18:41.701328+00:00"},{"alias_kind":"pith_short_8","alias_value":"LPIVVIML","created_at":"2026-07-05T11:18:41.701328+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.15683","citing_title":"Hi^2-GSLoc: Dual-Hierarchical Gaussian-Specific Visual Relocalization for Remote Sensing","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LPIVVIMLRD6OQ7E26W6ONKCCNH","json":"https://pith.science/pith/LPIVVIMLRD6OQ7E26W6ONKCCNH.json","graph_json":"https://pith.science/api/pith-number/LPIVVIMLRD6OQ7E26W6ONKCCNH/graph.json","events_json":"https://pith.science/api/pith-number/LPIVVIMLRD6OQ7E26W6ONKCCNH/events.json","paper":"https://pith.science/paper/LPIVVIML"},"agent_actions":{"view_html":"https://pith.science/pith/LPIVVIMLRD6OQ7E26W6ONKCCNH","download_json":"https://pith.science/pith/LPIVVIMLRD6OQ7E26W6ONKCCNH.json","view_paper":"https://pith.science/paper/LPIVVIML","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.17237&json=true","fetch_graph":"https://pith.science/api/pith-number/LPIVVIMLRD6OQ7E26W6ONKCCNH/graph.json","fetch_events":"https://pith.science/api/pith-number/LPIVVIMLRD6OQ7E26W6ONKCCNH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LPIVVIMLRD6OQ7E26W6ONKCCNH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LPIVVIMLRD6OQ7E26W6ONKCCNH/action/storage_attestation","attest_author":"https://pith.science/pith/LPIVVIMLRD6OQ7E26W6ONKCCNH/action/author_attestation","sign_citation":"https://pith.science/pith/LPIVVIMLRD6OQ7E26W6ONKCCNH/action/citation_signature","submit_replication":"https://pith.science/pith/LPIVVIMLRD6OQ7E26W6ONKCCNH/action/replication_record"}},"created_at":"2026-07-05T11:18:41.701328+00:00","updated_at":"2026-07-05T11:18:41.701328+00:00"}