{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FYPQPSWQZKZ4PLM62SFTHEF6JX","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":"4664d38d7aa9f27510549031efb0f3d0e1483f6e30982b43ed82bdb9e637ff5a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-18T07:21:12Z","title_canon_sha256":"9e9c0bc5896ddea88d88803d8a65fed466afd747fd22c0a72dc17af14dbc1516"},"schema_version":"1.0","source":{"id":"2405.11205","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.11205","created_at":"2026-07-05T08:20:34Z"},{"alias_kind":"arxiv_version","alias_value":"2405.11205v1","created_at":"2026-07-05T08:20:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.11205","created_at":"2026-07-05T08:20:34Z"},{"alias_kind":"pith_short_12","alias_value":"FYPQPSWQZKZ4","created_at":"2026-07-05T08:20:34Z"},{"alias_kind":"pith_short_16","alias_value":"FYPQPSWQZKZ4PLM6","created_at":"2026-07-05T08:20:34Z"},{"alias_kind":"pith_short_8","alias_value":"FYPQPSWQ","created_at":"2026-07-05T08:20:34Z"}],"graph_snapshots":[{"event_id":"sha256:7b46c3988c862ff103c2a57c4985cafa31146e7cd47a5727f248e4734a2a54c5","target":"graph","created_at":"2026-07-05T08:20:34Z","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/2405.11205/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Referring Image Segmentation (RIS) aims to segment an object described in natural language from an image, with the main challenge being a text-to-pixel correlation. Previous methods typically rely on single-modality features, such as vision or language features, to guide the multi-modal fusion process. However, this approach limits the interaction between vision and language, leading to a lack of fine-grained correlation between the language description and pixel-level details during the decoding process. In this paper, we introduce FCNet, a framework that employs a bi-directional guided fusio","authors_text":"Jing Liu, Shichen Lu, Sihan Chen, Xingjian He, Yichen Yan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-18T07:21:12Z","title":"Fuse & Calibrate: A bi-directional Vision-Language Guided Framework for Referring Image Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.11205","kind":"arxiv","version":1},"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":"sha256:66fde959952ee71226fbb390aa4e6973aede9d217e1645eccb2fd5ce87fb79d0","target":"record","created_at":"2026-07-05T08:20:34Z","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":"4664d38d7aa9f27510549031efb0f3d0e1483f6e30982b43ed82bdb9e637ff5a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-18T07:21:12Z","title_canon_sha256":"9e9c0bc5896ddea88d88803d8a65fed466afd747fd22c0a72dc17af14dbc1516"},"schema_version":"1.0","source":{"id":"2405.11205","kind":"arxiv","version":1}},"canonical_sha256":"2e1f07cad0cab3c7ad9ed48b3390be4ddfd5899d3a8dfecc78bb7b6da51e807b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e1f07cad0cab3c7ad9ed48b3390be4ddfd5899d3a8dfecc78bb7b6da51e807b","first_computed_at":"2026-07-05T08:20:34.882540Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:20:34.882540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jIG8rAaRArUt9ve9FB7n4TKKyIfV2I5MM1k69Mm3ypoVVgot0/TzkjV1rB3BctLDOX7LfZOtYjmoxwYrnpKSDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:20:34.883027Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.11205","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:66fde959952ee71226fbb390aa4e6973aede9d217e1645eccb2fd5ce87fb79d0","sha256:7b46c3988c862ff103c2a57c4985cafa31146e7cd47a5727f248e4734a2a54c5"],"state_sha256":"3581e9f7d3ebaeda30f347dc19ef123378857fc265de138eacd3eebf526b7c22"}