{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TV3YT2OCJMJISNASSMPQIOLPL4","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":"eed125ffaf1594f4418e4c6055d2928a50f3d443e1098112fc00c53792d31a27","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-10T15:18:19Z","title_canon_sha256":"4baebe68423d90ad7c4ff10ebbc4f1ebda445ed2d120579b990b15a00b82aa24"},"schema_version":"1.0","source":{"id":"2410.08021","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.08021","created_at":"2026-07-05T09:25:47Z"},{"alias_kind":"arxiv_version","alias_value":"2410.08021v2","created_at":"2026-07-05T09:25:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08021","created_at":"2026-07-05T09:25:47Z"},{"alias_kind":"pith_short_12","alias_value":"TV3YT2OCJMJI","created_at":"2026-07-05T09:25:47Z"},{"alias_kind":"pith_short_16","alias_value":"TV3YT2OCJMJISNAS","created_at":"2026-07-05T09:25:47Z"},{"alias_kind":"pith_short_8","alias_value":"TV3YT2OC","created_at":"2026-07-05T09:25:47Z"}],"graph_snapshots":[{"event_id":"sha256:3604bb65c40f4bf3e6fe716a02a0d9660a82edfa3502d29d7b83ac34a9fa220f","target":"graph","created_at":"2026-07-05T09:25:47Z","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/2410.08021/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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,","authors_text":"Changsheng Xu, Fang Peng, Linhui Xiao, Xiaoshan Yang, Yaowei Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-10T15:18:19Z","title":"OneRef: Unified One-tower Expression Grounding and Segmentation with Mask Referring Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08021","kind":"arxiv","version":2},"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":"sha256:90370f0b5035564f8581a0d1200af5d8a5bc685495dde0978fa3e13cdbbb5694","target":"record","created_at":"2026-07-05T09:25:47Z","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":"eed125ffaf1594f4418e4c6055d2928a50f3d443e1098112fc00c53792d31a27","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-10T15:18:19Z","title_canon_sha256":"4baebe68423d90ad7c4ff10ebbc4f1ebda445ed2d120579b990b15a00b82aa24"},"schema_version":"1.0","source":{"id":"2410.08021","kind":"arxiv","version":2}},"canonical_sha256":"9d7789e9c24b12893412931f04396f5f0e9020e25f7cb02e466639e4e3bddc18","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d7789e9c24b12893412931f04396f5f0e9020e25f7cb02e466639e4e3bddc18","first_computed_at":"2026-07-05T09:25:47.842361Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:25:47.842361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AW+gIIf5YUsKnVq8hw4BnM5jMHZqEkP3GYhZpw17VRZa5VbAiG4IERb63FQGKVrZhVcHhYBXqO8sKXpjOvhBCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:25:47.842898Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.08021","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:90370f0b5035564f8581a0d1200af5d8a5bc685495dde0978fa3e13cdbbb5694","sha256:3604bb65c40f4bf3e6fe716a02a0d9660a82edfa3502d29d7b83ac34a9fa220f"],"state_sha256":"97eda73ea946006ca1d0387be3f749e3614606bb16ebe8b6315112143ebdc28a"}