{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TV3YT2OCJMJISNASSMPQIOLPL4","short_pith_number":"pith:TV3YT2OC","schema_version":"1.0","canonical_sha256":"9d7789e9c24b12893412931f04396f5f0e9020e25f7cb02e466639e4e3bddc18","source":{"kind":"arxiv","id":"2410.08021","version":2},"attestation_state":"computed","paper":{"title":"OneRef: Unified One-tower Expression Grounding and Segmentation with Mask Referring Modeling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changsheng Xu, Fang Peng, Linhui Xiao, Xiaoshan Yang, Yaowei Wang","submitted_at":"2024-10-10T15:18:19Z","abstract_excerpt":"Constrained by the separate encoding of vision and language, existing grounding and referring segmentation works heavily rely on bulky Transformer-based fusion en-/decoders and a variety of early-stage interaction technologies. Simultaneously, the current mask visual language modeling (MVLM) fails to capture the nuanced referential relationship between image-text in referring tasks. In this paper, we propose OneRef, a minimalist referring framework built on the modality-shared one-tower transformer that unifies the visual and linguistic feature spaces. To modeling the referential relationship,"},"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":"2410.08021","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-10T15:18:19Z","cross_cats_sorted":[],"title_canon_sha256":"4baebe68423d90ad7c4ff10ebbc4f1ebda445ed2d120579b990b15a00b82aa24","abstract_canon_sha256":"eed125ffaf1594f4418e4c6055d2928a50f3d443e1098112fc00c53792d31a27"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:47.842898Z","signature_b64":"AW+gIIf5YUsKnVq8hw4BnM5jMHZqEkP3GYhZpw17VRZa5VbAiG4IERb63FQGKVrZhVcHhYBXqO8sKXpjOvhBCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d7789e9c24b12893412931f04396f5f0e9020e25f7cb02e466639e4e3bddc18","last_reissued_at":"2026-07-05T09:25:47.842361Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:47.842361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OneRef: Unified One-tower Expression Grounding and Segmentation with Mask Referring Modeling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changsheng Xu, Fang Peng, Linhui Xiao, Xiaoshan Yang, Yaowei Wang","submitted_at":"2024-10-10T15:18:19Z","abstract_excerpt":"Constrained by the separate encoding of vision and language, existing grounding and referring segmentation works heavily rely on bulky Transformer-based fusion en-/decoders and a variety of early-stage interaction technologies. Simultaneously, the current mask visual language modeling (MVLM) fails to capture the nuanced referential relationship between image-text in referring tasks. In this paper, we propose OneRef, a minimalist referring framework built on the modality-shared one-tower transformer that unifies the visual and linguistic feature spaces. To modeling the referential relationship,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08021","kind":"arxiv","version":2},"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/2410.08021/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":"2410.08021","created_at":"2026-07-05T09:25:47.842427+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.08021v2","created_at":"2026-07-05T09:25:47.842427+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08021","created_at":"2026-07-05T09:25:47.842427+00:00"},{"alias_kind":"pith_short_12","alias_value":"TV3YT2OCJMJI","created_at":"2026-07-05T09:25:47.842427+00:00"},{"alias_kind":"pith_short_16","alias_value":"TV3YT2OCJMJISNAS","created_at":"2026-07-05T09:25:47.842427+00:00"},{"alias_kind":"pith_short_8","alias_value":"TV3YT2OC","created_at":"2026-07-05T09:25:47.842427+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/TV3YT2OCJMJISNASSMPQIOLPL4","json":"https://pith.science/pith/TV3YT2OCJMJISNASSMPQIOLPL4.json","graph_json":"https://pith.science/api/pith-number/TV3YT2OCJMJISNASSMPQIOLPL4/graph.json","events_json":"https://pith.science/api/pith-number/TV3YT2OCJMJISNASSMPQIOLPL4/events.json","paper":"https://pith.science/paper/TV3YT2OC"},"agent_actions":{"view_html":"https://pith.science/pith/TV3YT2OCJMJISNASSMPQIOLPL4","download_json":"https://pith.science/pith/TV3YT2OCJMJISNASSMPQIOLPL4.json","view_paper":"https://pith.science/paper/TV3YT2OC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.08021&json=true","fetch_graph":"https://pith.science/api/pith-number/TV3YT2OCJMJISNASSMPQIOLPL4/graph.json","fetch_events":"https://pith.science/api/pith-number/TV3YT2OCJMJISNASSMPQIOLPL4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TV3YT2OCJMJISNASSMPQIOLPL4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TV3YT2OCJMJISNASSMPQIOLPL4/action/storage_attestation","attest_author":"https://pith.science/pith/TV3YT2OCJMJISNASSMPQIOLPL4/action/author_attestation","sign_citation":"https://pith.science/pith/TV3YT2OCJMJISNASSMPQIOLPL4/action/citation_signature","submit_replication":"https://pith.science/pith/TV3YT2OCJMJISNASSMPQIOLPL4/action/replication_record"}},"created_at":"2026-07-05T09:25:47.842427+00:00","updated_at":"2026-07-05T09:25:47.842427+00:00"}