{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NGXEHWTUVFJH6QRK4VZIZJOXZY","short_pith_number":"pith:NGXEHWTU","schema_version":"1.0","canonical_sha256":"69ae43da74a9527f422ae5728ca5d7ce3dbc9bab3bd386d8a72351128ceb78ad","source":{"kind":"arxiv","id":"2508.19593","version":1},"attestation_state":"computed","paper":{"title":"Generalizing Monocular 3D Object Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Kumar","submitted_at":"2025-08-27T06:06:18Z","abstract_excerpt":"Monocular 3D object detection (Mono3D) is a fundamental computer vision task that estimates an object's class, 3D position, dimensions, and orientation from a single image. Its applications, including autonomous driving, augmented reality, and robotics, critically rely on accurate 3D environmental understanding. This thesis addresses the challenge of generalizing Mono3D models to diverse scenarios, including occlusions, datasets, object sizes, and camera parameters. To enhance occlusion robustness, we propose a mathematically differentiable NMS (GrooMeD-NMS). To improve generalization to new d"},"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":"2508.19593","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-27T06:06:18Z","cross_cats_sorted":[],"title_canon_sha256":"2cee57befcf55cce31f5de33202a0944d6c9a60066bbb2dcde4b52db689b6e3b","abstract_canon_sha256":"b89860b5bb10d6a9517d7db8e8b1a4536993a4251b5d50517893d343923ec64b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:14.706126Z","signature_b64":"Az3JMX3W65s4+RjjYS3niudZdakb0plUfNOc6R6bz+ucnLAQDSrwFIE/eIFJn24ZHea3MqWAPvc3LvvE0SsbCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69ae43da74a9527f422ae5728ca5d7ce3dbc9bab3bd386d8a72351128ceb78ad","last_reissued_at":"2026-07-05T12:00:14.705613Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:14.705613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalizing Monocular 3D Object Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Kumar","submitted_at":"2025-08-27T06:06:18Z","abstract_excerpt":"Monocular 3D object detection (Mono3D) is a fundamental computer vision task that estimates an object's class, 3D position, dimensions, and orientation from a single image. Its applications, including autonomous driving, augmented reality, and robotics, critically rely on accurate 3D environmental understanding. This thesis addresses the challenge of generalizing Mono3D models to diverse scenarios, including occlusions, datasets, object sizes, and camera parameters. To enhance occlusion robustness, we propose a mathematically differentiable NMS (GrooMeD-NMS). To improve generalization to new d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.19593","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/2508.19593/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":"2508.19593","created_at":"2026-07-05T12:00:14.705673+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.19593v1","created_at":"2026-07-05T12:00:14.705673+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.19593","created_at":"2026-07-05T12:00:14.705673+00:00"},{"alias_kind":"pith_short_12","alias_value":"NGXEHWTUVFJH","created_at":"2026-07-05T12:00:14.705673+00:00"},{"alias_kind":"pith_short_16","alias_value":"NGXEHWTUVFJH6QRK","created_at":"2026-07-05T12:00:14.705673+00:00"},{"alias_kind":"pith_short_8","alias_value":"NGXEHWTU","created_at":"2026-07-05T12:00:14.705673+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/NGXEHWTUVFJH6QRK4VZIZJOXZY","json":"https://pith.science/pith/NGXEHWTUVFJH6QRK4VZIZJOXZY.json","graph_json":"https://pith.science/api/pith-number/NGXEHWTUVFJH6QRK4VZIZJOXZY/graph.json","events_json":"https://pith.science/api/pith-number/NGXEHWTUVFJH6QRK4VZIZJOXZY/events.json","paper":"https://pith.science/paper/NGXEHWTU"},"agent_actions":{"view_html":"https://pith.science/pith/NGXEHWTUVFJH6QRK4VZIZJOXZY","download_json":"https://pith.science/pith/NGXEHWTUVFJH6QRK4VZIZJOXZY.json","view_paper":"https://pith.science/paper/NGXEHWTU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.19593&json=true","fetch_graph":"https://pith.science/api/pith-number/NGXEHWTUVFJH6QRK4VZIZJOXZY/graph.json","fetch_events":"https://pith.science/api/pith-number/NGXEHWTUVFJH6QRK4VZIZJOXZY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NGXEHWTUVFJH6QRK4VZIZJOXZY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NGXEHWTUVFJH6QRK4VZIZJOXZY/action/storage_attestation","attest_author":"https://pith.science/pith/NGXEHWTUVFJH6QRK4VZIZJOXZY/action/author_attestation","sign_citation":"https://pith.science/pith/NGXEHWTUVFJH6QRK4VZIZJOXZY/action/citation_signature","submit_replication":"https://pith.science/pith/NGXEHWTUVFJH6QRK4VZIZJOXZY/action/replication_record"}},"created_at":"2026-07-05T12:00:14.705673+00:00","updated_at":"2026-07-05T12:00:14.705673+00:00"}