{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YHXX3LCNZJOXX6XRVTPPTS75DM","short_pith_number":"pith:YHXX3LCN","schema_version":"1.0","canonical_sha256":"c1ef7dac4dca5d7bfaf1acdef9cbfd1b27757dbec4cf3591d9349889a735eff7","source":{"kind":"arxiv","id":"2503.19240","version":1},"attestation_state":"computed","paper":{"title":"Beyond Object Categories: Multi-Attribute Reference Understanding for Visual Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CV","authors_text":"Chunzhi Yi, Feng Jiang, Hao Guo, Jianfei Zhu, Wei Fan","submitted_at":"2025-03-25T00:59:58Z","abstract_excerpt":"Referring expression comprehension (REC) aims at achieving object localization based on natural language descriptions. However, existing REC approaches are constrained by object category descriptions and single-attribute intention descriptions, hindering their application in real-world scenarios. In natural human-robot interactions, users often express their desires through individual states and intentions, accompanied by guiding gestures, rather than detailed object descriptions. To address this challenge, we propose Multi-ref EC, a novel task framework that integrates state descriptions, der"},"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":"2503.19240","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T00:59:58Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"01087eaf75f6094d70422887cc7b7c446b1f9276a1963694ef5d2f4ea4a68560","abstract_canon_sha256":"f3be3be8d9ef4373556d3be7fa40b028a8be7ea3ef7f575c403557b0a6ea79cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:51.637997Z","signature_b64":"4yNzcfoAirfzz+gUEMZvDZhvUzpNCqFlUFr7I0v03rfNRuf4I9w+MnAUllLUKhS9HYuPrpNVSfmoVIZkNm2iDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1ef7dac4dca5d7bfaf1acdef9cbfd1b27757dbec4cf3591d9349889a735eff7","last_reissued_at":"2026-07-05T10:38:51.637364Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:51.637364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Object Categories: Multi-Attribute Reference Understanding for Visual Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CV","authors_text":"Chunzhi Yi, Feng Jiang, Hao Guo, Jianfei Zhu, Wei Fan","submitted_at":"2025-03-25T00:59:58Z","abstract_excerpt":"Referring expression comprehension (REC) aims at achieving object localization based on natural language descriptions. However, existing REC approaches are constrained by object category descriptions and single-attribute intention descriptions, hindering their application in real-world scenarios. In natural human-robot interactions, users often express their desires through individual states and intentions, accompanied by guiding gestures, rather than detailed object descriptions. To address this challenge, we propose Multi-ref EC, a novel task framework that integrates state descriptions, der"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.19240","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/2503.19240/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":"2503.19240","created_at":"2026-07-05T10:38:51.637453+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.19240v1","created_at":"2026-07-05T10:38:51.637453+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.19240","created_at":"2026-07-05T10:38:51.637453+00:00"},{"alias_kind":"pith_short_12","alias_value":"YHXX3LCNZJOX","created_at":"2026-07-05T10:38:51.637453+00:00"},{"alias_kind":"pith_short_16","alias_value":"YHXX3LCNZJOXX6XR","created_at":"2026-07-05T10:38:51.637453+00:00"},{"alias_kind":"pith_short_8","alias_value":"YHXX3LCN","created_at":"2026-07-05T10:38:51.637453+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24539","citing_title":"PointVG-R: Internalizing Geometric Reasoning in MLLMs for Precise Pointing Localization via Visual Chain of Thought","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24498","citing_title":"VistaRef: Boosting Visual Spatial Orientation Awareness for Pointing-to-Object Detection","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YHXX3LCNZJOXX6XRVTPPTS75DM","json":"https://pith.science/pith/YHXX3LCNZJOXX6XRVTPPTS75DM.json","graph_json":"https://pith.science/api/pith-number/YHXX3LCNZJOXX6XRVTPPTS75DM/graph.json","events_json":"https://pith.science/api/pith-number/YHXX3LCNZJOXX6XRVTPPTS75DM/events.json","paper":"https://pith.science/paper/YHXX3LCN"},"agent_actions":{"view_html":"https://pith.science/pith/YHXX3LCNZJOXX6XRVTPPTS75DM","download_json":"https://pith.science/pith/YHXX3LCNZJOXX6XRVTPPTS75DM.json","view_paper":"https://pith.science/paper/YHXX3LCN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.19240&json=true","fetch_graph":"https://pith.science/api/pith-number/YHXX3LCNZJOXX6XRVTPPTS75DM/graph.json","fetch_events":"https://pith.science/api/pith-number/YHXX3LCNZJOXX6XRVTPPTS75DM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YHXX3LCNZJOXX6XRVTPPTS75DM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YHXX3LCNZJOXX6XRVTPPTS75DM/action/storage_attestation","attest_author":"https://pith.science/pith/YHXX3LCNZJOXX6XRVTPPTS75DM/action/author_attestation","sign_citation":"https://pith.science/pith/YHXX3LCNZJOXX6XRVTPPTS75DM/action/citation_signature","submit_replication":"https://pith.science/pith/YHXX3LCNZJOXX6XRVTPPTS75DM/action/replication_record"}},"created_at":"2026-07-05T10:38:51.637453+00:00","updated_at":"2026-07-05T10:38:51.637453+00:00"}