{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:F5JETIBQJFLZ5G5MDMH4IAJSZO","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f7b8892156d6819190db7329e045ff1f73bc8d009b68ef5f13380643383a6207","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-02T07:38:45Z","title_canon_sha256":"c1809426fe90e5b5d0fea253496aabda3ac72aa21351584760f6c555f830cc0f"},"schema_version":"1.0","source":{"id":"2602.01753","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.01753","created_at":"2026-06-02T02:04:50Z"},{"alias_kind":"arxiv_version","alias_value":"2602.01753v3","created_at":"2026-06-02T02:04:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.01753","created_at":"2026-06-02T02:04:50Z"},{"alias_kind":"pith_short_12","alias_value":"F5JETIBQJFLZ","created_at":"2026-06-02T02:04:50Z"},{"alias_kind":"pith_short_16","alias_value":"F5JETIBQJFLZ5G5M","created_at":"2026-06-02T02:04:50Z"},{"alias_kind":"pith_short_8","alias_value":"F5JETIBQ","created_at":"2026-06-02T02:04:50Z"}],"graph_snapshots":[{"event_id":"sha256:7fd58337f4dac885d91211ffce7c02580838b32cfc073a7c343c78c4c03f9ada","target":"graph","created_at":"2026-06-02T02:04:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2602.01753/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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, ","authors_text":"Fengyun Rao, Jing Lyu, Shenghao Fu, Wei-Shi Zheng, Xiaohua Xie, Yukun Su","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-02T07:38:45Z","title":"ObjEmbed: Towards Universal Multimodal Object Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.01753","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b387cb8235a1ea9a5cd215ffc8225fb7cadeb824163053ebb8e84d81583557fb","target":"record","created_at":"2026-06-02T02:04:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f7b8892156d6819190db7329e045ff1f73bc8d009b68ef5f13380643383a6207","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-02T07:38:45Z","title_canon_sha256":"c1809426fe90e5b5d0fea253496aabda3ac72aa21351584760f6c555f830cc0f"},"schema_version":"1.0","source":{"id":"2602.01753","kind":"arxiv","version":3}},"canonical_sha256":"2f5249a03049579e9bac1b0fc40132cba932b017123de08a2abd9e649fc98f06","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f5249a03049579e9bac1b0fc40132cba932b017123de08a2abd9e649fc98f06","first_computed_at":"2026-06-02T02:04:50.589401Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:50.589401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EsNeWr0nxv7FaVNej3UsukSYW4oHfM+Ms7n+tOjR/KLTJxweLtk19KlLQPn6SOgoQ3EjG7+7MsBLAjt6F3KsCw==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:50.589839Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.01753","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b387cb8235a1ea9a5cd215ffc8225fb7cadeb824163053ebb8e84d81583557fb","sha256:7fd58337f4dac885d91211ffce7c02580838b32cfc073a7c343c78c4c03f9ada"],"state_sha256":"648cdb56c68d9cc7a120cdd9aee254f8dda163c4e9fd17976870009c95a65d50"}