{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6KEJIQATKVA5IPV4OLSAP34TAM","short_pith_number":"pith:6KEJIQAT","schema_version":"1.0","canonical_sha256":"f2889440135541d43ebc72e407ef93032e6f7146ddedf8a7b11a79ba2d0c4159","source":{"kind":"arxiv","id":"2410.01261","version":1},"attestation_state":"computed","paper":{"title":"OCC-MLLM:Empowering Multimodal Large Language Model For the Understanding of Occluded Objects","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Wenmo Qiu, Xinhan Di","submitted_at":"2024-10-02T06:14:49Z","abstract_excerpt":"There is a gap in the understanding of occluded objects in existing large-scale visual language multi-modal models. Current state-of-the-art multimodal models fail to provide satisfactory results in describing occluded objects for visual-language multimodal models through universal visual encoders. Another challenge is the limited number of datasets containing image-text pairs with a large number of occluded objects. Therefore, we introduce a novel multimodal model that applies a newly designed visual encoder to understand occluded objects in RGB images. We also introduce a large-scale visual-"},"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":"2410.01261","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-02T06:14:49Z","cross_cats_sorted":[],"title_canon_sha256":"e268f962fb6779083cc281592b68d0938220f1f8547211187f0d5e0ec9df05d4","abstract_canon_sha256":"ba07411a806647fdd3240adea1def2dcd3f206415c9ebf21ac19ef3a2909e603"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:45.525204Z","signature_b64":"BTolNInz/hJhcZux8FKZ89LZXOmPVHv0ziYdVf0P4LpP9aU7LC8GfCsZ+TQAt+D6DaZaTKuq//Hsocy610zaDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2889440135541d43ebc72e407ef93032e6f7146ddedf8a7b11a79ba2d0c4159","last_reissued_at":"2026-07-05T09:14:45.524731Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:45.524731Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OCC-MLLM:Empowering Multimodal Large Language Model For the Understanding of Occluded Objects","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Wenmo Qiu, Xinhan Di","submitted_at":"2024-10-02T06:14:49Z","abstract_excerpt":"There is a gap in the understanding of occluded objects in existing large-scale visual language multi-modal models. Current state-of-the-art multimodal models fail to provide satisfactory results in describing occluded objects for visual-language multimodal models through universal visual encoders. Another challenge is the limited number of datasets containing image-text pairs with a large number of occluded objects. Therefore, we introduce a novel multimodal model that applies a newly designed visual encoder to understand occluded objects in RGB images. We also introduce a large-scale visual-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01261","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/2410.01261/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":"2410.01261","created_at":"2026-07-05T09:14:45.524795+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.01261v1","created_at":"2026-07-05T09:14:45.524795+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01261","created_at":"2026-07-05T09:14:45.524795+00:00"},{"alias_kind":"pith_short_12","alias_value":"6KEJIQATKVA5","created_at":"2026-07-05T09:14:45.524795+00:00"},{"alias_kind":"pith_short_16","alias_value":"6KEJIQATKVA5IPV4","created_at":"2026-07-05T09:14:45.524795+00:00"},{"alias_kind":"pith_short_8","alias_value":"6KEJIQAT","created_at":"2026-07-05T09:14:45.524795+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.15485","citing_title":"CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6KEJIQATKVA5IPV4OLSAP34TAM","json":"https://pith.science/pith/6KEJIQATKVA5IPV4OLSAP34TAM.json","graph_json":"https://pith.science/api/pith-number/6KEJIQATKVA5IPV4OLSAP34TAM/graph.json","events_json":"https://pith.science/api/pith-number/6KEJIQATKVA5IPV4OLSAP34TAM/events.json","paper":"https://pith.science/paper/6KEJIQAT"},"agent_actions":{"view_html":"https://pith.science/pith/6KEJIQATKVA5IPV4OLSAP34TAM","download_json":"https://pith.science/pith/6KEJIQATKVA5IPV4OLSAP34TAM.json","view_paper":"https://pith.science/paper/6KEJIQAT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.01261&json=true","fetch_graph":"https://pith.science/api/pith-number/6KEJIQATKVA5IPV4OLSAP34TAM/graph.json","fetch_events":"https://pith.science/api/pith-number/6KEJIQATKVA5IPV4OLSAP34TAM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6KEJIQATKVA5IPV4OLSAP34TAM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6KEJIQATKVA5IPV4OLSAP34TAM/action/storage_attestation","attest_author":"https://pith.science/pith/6KEJIQATKVA5IPV4OLSAP34TAM/action/author_attestation","sign_citation":"https://pith.science/pith/6KEJIQATKVA5IPV4OLSAP34TAM/action/citation_signature","submit_replication":"https://pith.science/pith/6KEJIQATKVA5IPV4OLSAP34TAM/action/replication_record"}},"created_at":"2026-07-05T09:14:45.524795+00:00","updated_at":"2026-07-05T09:14:45.524795+00:00"}