{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FYPQPSWQZKZ4PLM62SFTHEF6JX","short_pith_number":"pith:FYPQPSWQ","canonical_record":{"source":{"id":"2405.11205","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-18T07:21:12Z","cross_cats_sorted":[],"title_canon_sha256":"9e9c0bc5896ddea88d88803d8a65fed466afd747fd22c0a72dc17af14dbc1516","abstract_canon_sha256":"4664d38d7aa9f27510549031efb0f3d0e1483f6e30982b43ed82bdb9e637ff5a"},"schema_version":"1.0"},"canonical_sha256":"2e1f07cad0cab3c7ad9ed48b3390be4ddfd5899d3a8dfecc78bb7b6da51e807b","source":{"kind":"arxiv","id":"2405.11205","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FYPQPSWQZKZ4PLM62SFTHEF6JX","target":"record","payload":{"canonical_record":{"source":{"id":"2405.11205","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-18T07:21:12Z","cross_cats_sorted":[],"title_canon_sha256":"9e9c0bc5896ddea88d88803d8a65fed466afd747fd22c0a72dc17af14dbc1516","abstract_canon_sha256":"4664d38d7aa9f27510549031efb0f3d0e1483f6e30982b43ed82bdb9e637ff5a"},"schema_version":"1.0"},"canonical_sha256":"2e1f07cad0cab3c7ad9ed48b3390be4ddfd5899d3a8dfecc78bb7b6da51e807b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:20:34.883027Z","signature_b64":"jIG8rAaRArUt9ve9FB7n4TKKyIfV2I5MM1k69Mm3ypoVVgot0/TzkjV1rB3BctLDOX7LfZOtYjmoxwYrnpKSDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e1f07cad0cab3c7ad9ed48b3390be4ddfd5899d3a8dfecc78bb7b6da51e807b","last_reissued_at":"2026-07-05T08:20:34.882540Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:20:34.882540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.11205","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:20:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gE9scLd1dbClgTGdiAg21N4flAD71BAcxitEQ/iU6HhhuKFvtOm/5VI2trIEZN+dnXV+xhERCwiHijWQa4e+BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:49:58.374322Z"},"content_sha256":"66fde959952ee71226fbb390aa4e6973aede9d217e1645eccb2fd5ce87fb79d0","schema_version":"1.0","event_id":"sha256:66fde959952ee71226fbb390aa4e6973aede9d217e1645eccb2fd5ce87fb79d0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FYPQPSWQZKZ4PLM62SFTHEF6JX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fuse & Calibrate: A bi-directional Vision-Language Guided Framework for Referring Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing Liu, Shichen Lu, Sihan Chen, Xingjian He, Yichen Yan","submitted_at":"2024-05-18T07:21:12Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.11205","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/2405.11205/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:20:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ES3SPIDjdPFV8mT7M1UQsBp6dU02BZu/JHCb3U621QmO2iQJt1N+BHmkv8N/gtfikO5mkG9ICsjgwcoVWvz2Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:49:58.374829Z"},"content_sha256":"7b46c3988c862ff103c2a57c4985cafa31146e7cd47a5727f248e4734a2a54c5","schema_version":"1.0","event_id":"sha256:7b46c3988c862ff103c2a57c4985cafa31146e7cd47a5727f248e4734a2a54c5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FYPQPSWQZKZ4PLM62SFTHEF6JX/bundle.json","state_url":"https://pith.science/pith/FYPQPSWQZKZ4PLM62SFTHEF6JX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FYPQPSWQZKZ4PLM62SFTHEF6JX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T11:49:58Z","links":{"resolver":"https://pith.science/pith/FYPQPSWQZKZ4PLM62SFTHEF6JX","bundle":"https://pith.science/pith/FYPQPSWQZKZ4PLM62SFTHEF6JX/bundle.json","state":"https://pith.science/pith/FYPQPSWQZKZ4PLM62SFTHEF6JX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FYPQPSWQZKZ4PLM62SFTHEF6JX/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PAHVp3mzyt+7XHyVFuc8T8Q8sBTesIRDSAjC2OrLc5H64Uhl01gZqGpM/MyDZ9VBb8QvWWloKSggaThfaHdWBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:49:58.379510Z","bundle_sha256":"60ec0d7caa6219d90948b5fabaa986b58f1c0dc2d3fabf8d90ba19b0a2aea739"}}