{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:F5JETIBQJFLZ5G5MDMH4IAJSZO","short_pith_number":"pith:F5JETIBQ","schema_version":"1.0","canonical_sha256":"2f5249a03049579e9bac1b0fc40132cba932b017123de08a2abd9e649fc98f06","source":{"kind":"arxiv","id":"2602.01753","version":3},"attestation_state":"computed","paper":{"title":"ObjEmbed: Towards Universal Multimodal Object Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fengyun Rao, Jing Lyu, Shenghao Fu, Wei-Shi Zheng, Xiaohua Xie, Yukun Su","submitted_at":"2026-02-02T07:38:45Z","abstract_excerpt":"Aligning objects with corresponding textual descriptions is a fundamental challenge and a realistic requirement in vision-language understanding. While recent multimodal embedding models excel at global image-text alignment, they often struggle with fine-grained alignment between image regions and specific phrases. In this work, we present ObjEmbed, a novel MLLM embedding model that decomposes the input image into multiple regional embeddings, each corresponding to an individual object, along with global embeddings. It supports a wide range of visual understanding tasks like visual grounding, "},"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":"2602.01753","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-02T07:38:45Z","cross_cats_sorted":[],"title_canon_sha256":"c1809426fe90e5b5d0fea253496aabda3ac72aa21351584760f6c555f830cc0f","abstract_canon_sha256":"f7b8892156d6819190db7329e045ff1f73bc8d009b68ef5f13380643383a6207"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:50.589839Z","signature_b64":"EsNeWr0nxv7FaVNej3UsukSYW4oHfM+Ms7n+tOjR/KLTJxweLtk19KlLQPn6SOgoQ3EjG7+7MsBLAjt6F3KsCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f5249a03049579e9bac1b0fc40132cba932b017123de08a2abd9e649fc98f06","last_reissued_at":"2026-06-02T02:04:50.589401Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:50.589401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ObjEmbed: Towards Universal Multimodal Object Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fengyun Rao, Jing Lyu, Shenghao Fu, Wei-Shi Zheng, Xiaohua Xie, Yukun Su","submitted_at":"2026-02-02T07:38:45Z","abstract_excerpt":"Aligning objects with corresponding textual descriptions is a fundamental challenge and a realistic requirement in vision-language understanding. While recent multimodal embedding models excel at global image-text alignment, they often struggle with fine-grained alignment between image regions and specific phrases. In this work, we present ObjEmbed, a novel MLLM embedding model that decomposes the input image into multiple regional embeddings, each corresponding to an individual object, along with global embeddings. It supports a wide range of visual understanding tasks like visual grounding, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.01753","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/2602.01753/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":"2602.01753","created_at":"2026-06-02T02:04:50.589466+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.01753v3","created_at":"2026-06-02T02:04:50.589466+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.01753","created_at":"2026-06-02T02:04:50.589466+00:00"},{"alias_kind":"pith_short_12","alias_value":"F5JETIBQJFLZ","created_at":"2026-06-02T02:04:50.589466+00:00"},{"alias_kind":"pith_short_16","alias_value":"F5JETIBQJFLZ5G5M","created_at":"2026-06-02T02:04:50.589466+00:00"},{"alias_kind":"pith_short_8","alias_value":"F5JETIBQ","created_at":"2026-06-02T02:04:50.589466+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/F5JETIBQJFLZ5G5MDMH4IAJSZO","json":"https://pith.science/pith/F5JETIBQJFLZ5G5MDMH4IAJSZO.json","graph_json":"https://pith.science/api/pith-number/F5JETIBQJFLZ5G5MDMH4IAJSZO/graph.json","events_json":"https://pith.science/api/pith-number/F5JETIBQJFLZ5G5MDMH4IAJSZO/events.json","paper":"https://pith.science/paper/F5JETIBQ"},"agent_actions":{"view_html":"https://pith.science/pith/F5JETIBQJFLZ5G5MDMH4IAJSZO","download_json":"https://pith.science/pith/F5JETIBQJFLZ5G5MDMH4IAJSZO.json","view_paper":"https://pith.science/paper/F5JETIBQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.01753&json=true","fetch_graph":"https://pith.science/api/pith-number/F5JETIBQJFLZ5G5MDMH4IAJSZO/graph.json","fetch_events":"https://pith.science/api/pith-number/F5JETIBQJFLZ5G5MDMH4IAJSZO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F5JETIBQJFLZ5G5MDMH4IAJSZO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F5JETIBQJFLZ5G5MDMH4IAJSZO/action/storage_attestation","attest_author":"https://pith.science/pith/F5JETIBQJFLZ5G5MDMH4IAJSZO/action/author_attestation","sign_citation":"https://pith.science/pith/F5JETIBQJFLZ5G5MDMH4IAJSZO/action/citation_signature","submit_replication":"https://pith.science/pith/F5JETIBQJFLZ5G5MDMH4IAJSZO/action/replication_record"}},"created_at":"2026-06-02T02:04:50.589466+00:00","updated_at":"2026-06-02T02:04:50.589466+00:00"}