{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2AUEHVP6ZJRMMCIBSTKOKMMIGJ","short_pith_number":"pith:2AUEHVP6","schema_version":"1.0","canonical_sha256":"d02843d5feca62c6090194d4e531883257e99aaadb674d2266d4cdd29a2872e8","source":{"kind":"arxiv","id":"2305.06121","version":3},"attestation_state":"computed","paper":{"title":"Transformer-Based Model for Monocular Visual Odometry: A Video Understanding Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Andr\\'e O. Fran\\c{c}ani, Marcos R. O. A. Maximo","submitted_at":"2023-05-10T13:11:23Z","abstract_excerpt":"Estimating the camera's pose given images from a single camera is a traditional task in mobile robots and autonomous vehicles. This problem is called monocular visual odometry and often relies on geometric approaches that require considerable engineering effort for a specific scenario. Deep learning methods have been shown to be generalizable after proper training and with a large amount of available data. Transformer-based architectures have dominated the state-of-the-art in natural language processing and computer vision tasks, such as image and video understanding. In this work, we deal wit"},"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":"2305.06121","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-10T13:11:23Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"a9e3cdc3efeddc2d951884582efef5248ee926eff21cb146705bf3f9df9d7471","abstract_canon_sha256":"80a4c44f7a35459c304ddebc01b31dab35100d335bebd2dd8db1945fbe067f20"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:40.411325Z","signature_b64":"a82hjhk/jVdU/0zkfOqgdUHi+g5imgI6W+nUG9U7W+1i1xHKzGp6YySbwsX8cnCeoxt++Cd3WUSLYhDZXFuXBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d02843d5feca62c6090194d4e531883257e99aaadb674d2266d4cdd29a2872e8","last_reissued_at":"2026-07-05T10:02:40.410805Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:40.410805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transformer-Based Model for Monocular Visual Odometry: A Video Understanding Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Andr\\'e O. Fran\\c{c}ani, Marcos R. O. A. Maximo","submitted_at":"2023-05-10T13:11:23Z","abstract_excerpt":"Estimating the camera's pose given images from a single camera is a traditional task in mobile robots and autonomous vehicles. This problem is called monocular visual odometry and often relies on geometric approaches that require considerable engineering effort for a specific scenario. Deep learning methods have been shown to be generalizable after proper training and with a large amount of available data. Transformer-based architectures have dominated the state-of-the-art in natural language processing and computer vision tasks, such as image and video understanding. In this work, we deal wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.06121","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/2305.06121/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":"2305.06121","created_at":"2026-07-05T10:02:40.410867+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.06121v3","created_at":"2026-07-05T10:02:40.410867+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.06121","created_at":"2026-07-05T10:02:40.410867+00:00"},{"alias_kind":"pith_short_12","alias_value":"2AUEHVP6ZJRM","created_at":"2026-07-05T10:02:40.410867+00:00"},{"alias_kind":"pith_short_16","alias_value":"2AUEHVP6ZJRMMCIB","created_at":"2026-07-05T10:02:40.410867+00:00"},{"alias_kind":"pith_short_8","alias_value":"2AUEHVP6","created_at":"2026-07-05T10:02:40.410867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.18994","citing_title":"VKFPos: A Learning-Based Monocular Positioning with Variational Bayesian Extended Kalman Filter Integration","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2AUEHVP6ZJRMMCIBSTKOKMMIGJ","json":"https://pith.science/pith/2AUEHVP6ZJRMMCIBSTKOKMMIGJ.json","graph_json":"https://pith.science/api/pith-number/2AUEHVP6ZJRMMCIBSTKOKMMIGJ/graph.json","events_json":"https://pith.science/api/pith-number/2AUEHVP6ZJRMMCIBSTKOKMMIGJ/events.json","paper":"https://pith.science/paper/2AUEHVP6"},"agent_actions":{"view_html":"https://pith.science/pith/2AUEHVP6ZJRMMCIBSTKOKMMIGJ","download_json":"https://pith.science/pith/2AUEHVP6ZJRMMCIBSTKOKMMIGJ.json","view_paper":"https://pith.science/paper/2AUEHVP6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.06121&json=true","fetch_graph":"https://pith.science/api/pith-number/2AUEHVP6ZJRMMCIBSTKOKMMIGJ/graph.json","fetch_events":"https://pith.science/api/pith-number/2AUEHVP6ZJRMMCIBSTKOKMMIGJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2AUEHVP6ZJRMMCIBSTKOKMMIGJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2AUEHVP6ZJRMMCIBSTKOKMMIGJ/action/storage_attestation","attest_author":"https://pith.science/pith/2AUEHVP6ZJRMMCIBSTKOKMMIGJ/action/author_attestation","sign_citation":"https://pith.science/pith/2AUEHVP6ZJRMMCIBSTKOKMMIGJ/action/citation_signature","submit_replication":"https://pith.science/pith/2AUEHVP6ZJRMMCIBSTKOKMMIGJ/action/replication_record"}},"created_at":"2026-07-05T10:02:40.410867+00:00","updated_at":"2026-07-05T10:02:40.410867+00:00"}