{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:B4PSARZ7O6TU2CPCWQO5UL7XM3","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":"478542e221ba213a604f4191905d29900fe0e2de4ad3d0226c2513576eb78c36","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-28T04:14:01Z","title_canon_sha256":"9510160c214bac7e6c77238c3ab53e636cbed9a1e647063757db7f138dc18773"},"schema_version":"1.0","source":{"id":"2408.15521","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.15521","created_at":"2026-07-05T11:22:31Z"},{"alias_kind":"arxiv_version","alias_value":"2408.15521v3","created_at":"2026-07-05T11:22:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.15521","created_at":"2026-07-05T11:22:31Z"},{"alias_kind":"pith_short_12","alias_value":"B4PSARZ7O6TU","created_at":"2026-07-05T11:22:31Z"},{"alias_kind":"pith_short_16","alias_value":"B4PSARZ7O6TU2CPC","created_at":"2026-07-05T11:22:31Z"},{"alias_kind":"pith_short_8","alias_value":"B4PSARZ7","created_at":"2026-07-05T11:22:31Z"}],"graph_snapshots":[{"event_id":"sha256:653c6a013a3c39c740d1cc5d580f115835868f03ec8cd607f3b291420ec7371b","target":"graph","created_at":"2026-07-05T11:22:31Z","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/2408.15521/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Referring image segmentation (RIS) requires dense vision-language interactions between visual pixels and textual words to segment objects based on a given description. However, commonly adapted dual-encoders in RIS, e.g., Swin transformer and BERT (uni-modal encoders) or CLIP (a multi-modal dual-encoder), lack dense multi-modal interactions during pre-training, leading to a gap with a pixel-level RIS task. To bridge this gap, existing RIS methods often rely on multi-modal fusion modules that interact two encoders, but this approach leads to high computational costs. In this paper, we present a","authors_text":"Byeongju Han, Dongyoon Wee, Ilchae Jung, Jeany Son, Seonghoon Yu, Taeoh Kim, Yunho Kim","cross_cats":["cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-28T04:14:01Z","title":"A Simple Baseline with Single-encoder for Referring Image Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.15521","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":"sha256:3dcb2425c8d89fb7e360cc1293f049971dbc737f6c432fbf5a633802769901af","target":"record","created_at":"2026-07-05T11:22:31Z","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":"478542e221ba213a604f4191905d29900fe0e2de4ad3d0226c2513576eb78c36","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-28T04:14:01Z","title_canon_sha256":"9510160c214bac7e6c77238c3ab53e636cbed9a1e647063757db7f138dc18773"},"schema_version":"1.0","source":{"id":"2408.15521","kind":"arxiv","version":3}},"canonical_sha256":"0f1f20473f77a74d09e2b41dda2ff766c479678fcdf22df013471881ea68d2d3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0f1f20473f77a74d09e2b41dda2ff766c479678fcdf22df013471881ea68d2d3","first_computed_at":"2026-07-05T11:22:31.972678Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:22:31.972678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PTqz+pwCvxR+ob29f0sevHwkxsAN7yL5nO+UiWkKT+cPWScPZIIK6qZXDq1CvzQTDupSxwycRq/jVkfI3lj6BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:22:31.973142Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.15521","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3dcb2425c8d89fb7e360cc1293f049971dbc737f6c432fbf5a633802769901af","sha256:653c6a013a3c39c740d1cc5d580f115835868f03ec8cd607f3b291420ec7371b"],"state_sha256":"ad810e54cebdbb7b2f872f64ebaa977c754f2a579f5a4a043decbdd04446d43f"}