{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4JVPWF62UNRDMPMLSJBX6A736Q","short_pith_number":"pith:4JVPWF62","schema_version":"1.0","canonical_sha256":"e26afb17daa362363d8b92437f03fbf41917fc9f6465f9a404ebdfdbfcc7c8e6","source":{"kind":"arxiv","id":"2603.29236","version":2},"attestation_state":"computed","paper":{"title":"M2H-MX: Multi-Task Semantic and Geometric Perception for Real-Time Monocular 3D Scene Graph Construction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Francesco Nex, George Vosselman, U.V.B.L. Udugama","submitted_at":"2026-03-31T04:07:42Z","abstract_excerpt":"Monocular cameras are attractive for robotic perception due to their low cost and ease of deployment, yet achieving reliable real-time spatial understanding from a single image stream remains challenging. While recent multi-task dense prediction models have improved per-pixel depth and semantic estimation, translating these advances into stable monocular mapping systems is still non-trivial.\n  This paper presents M2H-MX, a real-time multi-task perception model for monocular spatial understanding. The model preserves multi-scale feature representations while introducing register-gated global co"},"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":"2603.29236","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-31T04:07:42Z","cross_cats_sorted":[],"title_canon_sha256":"da24dba46288e57cdc705456128e9b97fbdf800493f09a8ec83d01211a9342a6","abstract_canon_sha256":"6d1e3607949c7e1b655cd325631e9b0371942c27bbb7d0fbe0aeedd0be8a5aba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:29.028019Z","signature_b64":"5BBo8IKZKiZ/W0y7fV8ym6KRYOHaHIMot5c1KluxCx9ONbqGQsV8QOUCww/RgZKhlK8wTIFK7QhT45ygRhfiDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e26afb17daa362363d8b92437f03fbf41917fc9f6465f9a404ebdfdbfcc7c8e6","last_reissued_at":"2026-05-26T01:03:29.027223Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:29.027223Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"M2H-MX: Multi-Task Semantic and Geometric Perception for Real-Time Monocular 3D Scene Graph Construction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Francesco Nex, George Vosselman, U.V.B.L. Udugama","submitted_at":"2026-03-31T04:07:42Z","abstract_excerpt":"Monocular cameras are attractive for robotic perception due to their low cost and ease of deployment, yet achieving reliable real-time spatial understanding from a single image stream remains challenging. While recent multi-task dense prediction models have improved per-pixel depth and semantic estimation, translating these advances into stable monocular mapping systems is still non-trivial.\n  This paper presents M2H-MX, a real-time multi-task perception model for monocular spatial understanding. The model preserves multi-scale feature representations while introducing register-gated global co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.29236","kind":"arxiv","version":2},"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/2603.29236/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":"2603.29236","created_at":"2026-05-26T01:03:29.027358+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.29236v2","created_at":"2026-05-26T01:03:29.027358+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.29236","created_at":"2026-05-26T01:03:29.027358+00:00"},{"alias_kind":"pith_short_12","alias_value":"4JVPWF62UNRD","created_at":"2026-05-26T01:03:29.027358+00:00"},{"alias_kind":"pith_short_16","alias_value":"4JVPWF62UNRDMPML","created_at":"2026-05-26T01:03:29.027358+00:00"},{"alias_kind":"pith_short_8","alias_value":"4JVPWF62","created_at":"2026-05-26T01:03:29.027358+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.17661","citing_title":"Mono-Hydra++: Real-Time Monocular Scene Graph Construction with Multi-Task Learning for 3D Indoor Mapping","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4JVPWF62UNRDMPMLSJBX6A736Q","json":"https://pith.science/pith/4JVPWF62UNRDMPMLSJBX6A736Q.json","graph_json":"https://pith.science/api/pith-number/4JVPWF62UNRDMPMLSJBX6A736Q/graph.json","events_json":"https://pith.science/api/pith-number/4JVPWF62UNRDMPMLSJBX6A736Q/events.json","paper":"https://pith.science/paper/4JVPWF62"},"agent_actions":{"view_html":"https://pith.science/pith/4JVPWF62UNRDMPMLSJBX6A736Q","download_json":"https://pith.science/pith/4JVPWF62UNRDMPMLSJBX6A736Q.json","view_paper":"https://pith.science/paper/4JVPWF62","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.29236&json=true","fetch_graph":"https://pith.science/api/pith-number/4JVPWF62UNRDMPMLSJBX6A736Q/graph.json","fetch_events":"https://pith.science/api/pith-number/4JVPWF62UNRDMPMLSJBX6A736Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4JVPWF62UNRDMPMLSJBX6A736Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4JVPWF62UNRDMPMLSJBX6A736Q/action/storage_attestation","attest_author":"https://pith.science/pith/4JVPWF62UNRDMPMLSJBX6A736Q/action/author_attestation","sign_citation":"https://pith.science/pith/4JVPWF62UNRDMPMLSJBX6A736Q/action/citation_signature","submit_replication":"https://pith.science/pith/4JVPWF62UNRDMPMLSJBX6A736Q/action/replication_record"}},"created_at":"2026-05-26T01:03:29.027358+00:00","updated_at":"2026-05-26T01:03:29.027358+00:00"}