{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:E3WX3M4FZKYFLOPQ4EFRO6WWZP","short_pith_number":"pith:E3WX3M4F","schema_version":"1.0","canonical_sha256":"26ed7db385cab055b9f0e10b177ad6cbd1d2d0af9acc4683110da989469897c4","source":{"kind":"arxiv","id":"2607.01757","version":1},"attestation_state":"computed","paper":{"title":"DL-VINS-Factory: A Modular Framework for Learned Visual Front-Ends in Visual-Inertial SLAM","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Melissa Jia Ying Chong, Shoon Kit Lim, Ting Yang Ling","submitted_at":"2026-07-02T06:17:33Z","abstract_excerpt":"Deep-learning features excel in visual matching, yet their practical value in tightly coupled visual-inertial SLAM (VI-SLAM) remains insufficiently characterized. We present DL-VINS-Factory, a unified framework that integrates learned feature extractors (ALIKED, RaCo, SuperPoint, XFeat) with either Lucas--Kanade (LK) optical-flow tracking or LightGlue (LG) descriptor matching. All front-ends share a sliding-window Ceres back-end, with optional AnyLoc DINOv2-VLAD loop closure, and 4-DoF pose-graph optimization. We benchmark the system across the four datasets covering indoor, unstructured outdo"},"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":"2607.01757","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-02T06:17:33Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"b44521cd7260b76c8e26914dc406665b46a6e3f9f52e2d245797a1753d324504","abstract_canon_sha256":"30d51fe394f1ec3a4c0a25d2dc3de3ad0aab0d8445246159d1bc02f413ce1c7f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:28.657735Z","signature_b64":"3bS/kIkJMUKL7JdjVoEc7YKOFkzI8lPpqyySw9mKDv1xJEHvT8gIbINwgUdCmBzFgWrLHMv0IlQybxdGX9O8CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26ed7db385cab055b9f0e10b177ad6cbd1d2d0af9acc4683110da989469897c4","last_reissued_at":"2026-07-03T01:17:28.657327Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:28.657327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DL-VINS-Factory: A Modular Framework for Learned Visual Front-Ends in Visual-Inertial SLAM","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Melissa Jia Ying Chong, Shoon Kit Lim, Ting Yang Ling","submitted_at":"2026-07-02T06:17:33Z","abstract_excerpt":"Deep-learning features excel in visual matching, yet their practical value in tightly coupled visual-inertial SLAM (VI-SLAM) remains insufficiently characterized. We present DL-VINS-Factory, a unified framework that integrates learned feature extractors (ALIKED, RaCo, SuperPoint, XFeat) with either Lucas--Kanade (LK) optical-flow tracking or LightGlue (LG) descriptor matching. All front-ends share a sliding-window Ceres back-end, with optional AnyLoc DINOv2-VLAD loop closure, and 4-DoF pose-graph optimization. We benchmark the system across the four datasets covering indoor, unstructured outdo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01757","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/2607.01757/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":"2607.01757","created_at":"2026-07-03T01:17:28.657394+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.01757v1","created_at":"2026-07-03T01:17:28.657394+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01757","created_at":"2026-07-03T01:17:28.657394+00:00"},{"alias_kind":"pith_short_12","alias_value":"E3WX3M4FZKYF","created_at":"2026-07-03T01:17:28.657394+00:00"},{"alias_kind":"pith_short_16","alias_value":"E3WX3M4FZKYFLOPQ","created_at":"2026-07-03T01:17:28.657394+00:00"},{"alias_kind":"pith_short_8","alias_value":"E3WX3M4F","created_at":"2026-07-03T01:17:28.657394+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/E3WX3M4FZKYFLOPQ4EFRO6WWZP","json":"https://pith.science/pith/E3WX3M4FZKYFLOPQ4EFRO6WWZP.json","graph_json":"https://pith.science/api/pith-number/E3WX3M4FZKYFLOPQ4EFRO6WWZP/graph.json","events_json":"https://pith.science/api/pith-number/E3WX3M4FZKYFLOPQ4EFRO6WWZP/events.json","paper":"https://pith.science/paper/E3WX3M4F"},"agent_actions":{"view_html":"https://pith.science/pith/E3WX3M4FZKYFLOPQ4EFRO6WWZP","download_json":"https://pith.science/pith/E3WX3M4FZKYFLOPQ4EFRO6WWZP.json","view_paper":"https://pith.science/paper/E3WX3M4F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.01757&json=true","fetch_graph":"https://pith.science/api/pith-number/E3WX3M4FZKYFLOPQ4EFRO6WWZP/graph.json","fetch_events":"https://pith.science/api/pith-number/E3WX3M4FZKYFLOPQ4EFRO6WWZP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E3WX3M4FZKYFLOPQ4EFRO6WWZP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E3WX3M4FZKYFLOPQ4EFRO6WWZP/action/storage_attestation","attest_author":"https://pith.science/pith/E3WX3M4FZKYFLOPQ4EFRO6WWZP/action/author_attestation","sign_citation":"https://pith.science/pith/E3WX3M4FZKYFLOPQ4EFRO6WWZP/action/citation_signature","submit_replication":"https://pith.science/pith/E3WX3M4FZKYFLOPQ4EFRO6WWZP/action/replication_record"}},"created_at":"2026-07-03T01:17:28.657394+00:00","updated_at":"2026-07-03T01:17:28.657394+00:00"}