{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YZPFHZFWAACF6RZIPCSFJ5XRLR","short_pith_number":"pith:YZPFHZFW","schema_version":"1.0","canonical_sha256":"c65e53e4b600045f472878a454f6f15c4669d2f0e147596f7bb36fd26064fd29","source":{"kind":"arxiv","id":"2504.01954","version":1},"attestation_state":"computed","paper":{"title":"Towards Unified Referring Expression Segmentation Across Omni-Level Visual Target Granularities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing Liu, Longteng Guo, Tongtian Yue, Wenxuan Wang, Xingjian He, Xinlong Wang, Yepeng Tang, Yisi Zhang","submitted_at":"2025-04-02T17:58:05Z","abstract_excerpt":"Referring expression segmentation (RES) aims at segmenting the entities' masks that match the descriptive language expression. While traditional RES methods primarily address object-level grounding, real-world scenarios demand a more versatile framework that can handle multiple levels of target granularity, such as multi-object, single object or part-level references. This introduces great challenges due to the diverse and nuanced ways users describe targets. However, existing datasets and models mainly focus on designing grounding specialists for object-level target localization, lacking the "},"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":"2504.01954","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-02T17:58:05Z","cross_cats_sorted":[],"title_canon_sha256":"32ba2e2fbbf71824004cab9002b23aa900a3488fcb69ee5414f4937f625fb68c","abstract_canon_sha256":"130f1b8185b81e313bf422ef1861762df9e6363d8c73914af5728a0077333235"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:32.262998Z","signature_b64":"B4Xtc+rCQOGRtmDX2xk1vEsr9MYyiUeh9W4Qbfv5ANu7EEXW/qn9Oh7Fbx5X1Yt7R7uqpll6OV37KbpTxhr1BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c65e53e4b600045f472878a454f6f15c4669d2f0e147596f7bb36fd26064fd29","last_reissued_at":"2026-07-05T10:43:32.262542Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:32.262542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Unified Referring Expression Segmentation Across Omni-Level Visual Target Granularities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing Liu, Longteng Guo, Tongtian Yue, Wenxuan Wang, Xingjian He, Xinlong Wang, Yepeng Tang, Yisi Zhang","submitted_at":"2025-04-02T17:58:05Z","abstract_excerpt":"Referring expression segmentation (RES) aims at segmenting the entities' masks that match the descriptive language expression. While traditional RES methods primarily address object-level grounding, real-world scenarios demand a more versatile framework that can handle multiple levels of target granularity, such as multi-object, single object or part-level references. This introduces great challenges due to the diverse and nuanced ways users describe targets. However, existing datasets and models mainly focus on designing grounding specialists for object-level target localization, lacking the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.01954","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/2504.01954/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":"2504.01954","created_at":"2026-07-05T10:43:32.262597+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.01954v1","created_at":"2026-07-05T10:43:32.262597+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.01954","created_at":"2026-07-05T10:43:32.262597+00:00"},{"alias_kind":"pith_short_12","alias_value":"YZPFHZFWAACF","created_at":"2026-07-05T10:43:32.262597+00:00"},{"alias_kind":"pith_short_16","alias_value":"YZPFHZFWAACF6RZI","created_at":"2026-07-05T10:43:32.262597+00:00"},{"alias_kind":"pith_short_8","alias_value":"YZPFHZFW","created_at":"2026-07-05T10:43:32.262597+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26196","citing_title":"From Structure to Synergy: A Survey of Vision-Language Perception Paradigm Evolution in Multimodal Large Language Models","ref_index":94,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YZPFHZFWAACF6RZIPCSFJ5XRLR","json":"https://pith.science/pith/YZPFHZFWAACF6RZIPCSFJ5XRLR.json","graph_json":"https://pith.science/api/pith-number/YZPFHZFWAACF6RZIPCSFJ5XRLR/graph.json","events_json":"https://pith.science/api/pith-number/YZPFHZFWAACF6RZIPCSFJ5XRLR/events.json","paper":"https://pith.science/paper/YZPFHZFW"},"agent_actions":{"view_html":"https://pith.science/pith/YZPFHZFWAACF6RZIPCSFJ5XRLR","download_json":"https://pith.science/pith/YZPFHZFWAACF6RZIPCSFJ5XRLR.json","view_paper":"https://pith.science/paper/YZPFHZFW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.01954&json=true","fetch_graph":"https://pith.science/api/pith-number/YZPFHZFWAACF6RZIPCSFJ5XRLR/graph.json","fetch_events":"https://pith.science/api/pith-number/YZPFHZFWAACF6RZIPCSFJ5XRLR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YZPFHZFWAACF6RZIPCSFJ5XRLR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YZPFHZFWAACF6RZIPCSFJ5XRLR/action/storage_attestation","attest_author":"https://pith.science/pith/YZPFHZFWAACF6RZIPCSFJ5XRLR/action/author_attestation","sign_citation":"https://pith.science/pith/YZPFHZFWAACF6RZIPCSFJ5XRLR/action/citation_signature","submit_replication":"https://pith.science/pith/YZPFHZFWAACF6RZIPCSFJ5XRLR/action/replication_record"}},"created_at":"2026-07-05T10:43:32.262597+00:00","updated_at":"2026-07-05T10:43:32.262597+00:00"}