{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BDUACW7TE57PWZNNVKLT3EMQOF","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":"4205b342b16ed0265f8bb5396b29f3eb8092b4366bd88ea1a86cf46e4b37a34a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-29T07:33:38Z","title_canon_sha256":"2ff914dcf165b0f3e6ceec0cbac0c88204a848e46b360903c79aba29e41ca6ed"},"schema_version":"1.0","source":{"id":"2311.17952","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.17952","created_at":"2026-07-05T07:18:34Z"},{"alias_kind":"arxiv_version","alias_value":"2311.17952v1","created_at":"2026-07-05T07:18:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.17952","created_at":"2026-07-05T07:18:34Z"},{"alias_kind":"pith_short_12","alias_value":"BDUACW7TE57P","created_at":"2026-07-05T07:18:34Z"},{"alias_kind":"pith_short_16","alias_value":"BDUACW7TE57PWZNN","created_at":"2026-07-05T07:18:34Z"},{"alias_kind":"pith_short_8","alias_value":"BDUACW7T","created_at":"2026-07-05T07:18:34Z"}],"graph_snapshots":[{"event_id":"sha256:9c4300b56611f50a7c2d58e391581bcb71dbccba16a9d0d33743e95dde280db3","target":"graph","created_at":"2026-07-05T07:18:34Z","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/2311.17952/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 target objects expressed in natural language within a scene at the pixel level. Various recent RIS models have achieved state-of-the-art performance by generating contextual tokens to model multimodal features from pretrained encoders and effectively fusing them using transformer-based cross-modal attention. While these methods match language features with image features to effectively identify likely target objects, they often struggle to correctly understand contextual information in complex and ambiguous sentences and scenes. To address thi","authors_text":"Dogyoon Lee, Heeseung Choi, Ig-jae Kim, Jungho Lee, Minhyeok Lee, Sangyoun Lee, Suhwan Cho","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-29T07:33:38Z","title":"Synchronizing Vision and Language: Bidirectional Token-Masking AutoEncoder for Referring Image Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.17952","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":"sha256:9b239a76a6c541a2c1787783c598ef9d23d22f6cd36664ab57ea480533f42774","target":"record","created_at":"2026-07-05T07:18:34Z","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":"4205b342b16ed0265f8bb5396b29f3eb8092b4366bd88ea1a86cf46e4b37a34a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-29T07:33:38Z","title_canon_sha256":"2ff914dcf165b0f3e6ceec0cbac0c88204a848e46b360903c79aba29e41ca6ed"},"schema_version":"1.0","source":{"id":"2311.17952","kind":"arxiv","version":1}},"canonical_sha256":"08e8015bf3277efb65adaa973d9190717ac5ec478321f1fe7f5b2d6ded5735bf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"08e8015bf3277efb65adaa973d9190717ac5ec478321f1fe7f5b2d6ded5735bf","first_computed_at":"2026-07-05T07:18:34.072307Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:18:34.072307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C8RqUim9DDVrVtkeLwcfhwMmMdhpQbuXlvv2x3S41mX3ypXyZeWiGQ3udrzDX2dZXIy6YDs/K4PrPsNjcpFwAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:18:34.072806Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.17952","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9b239a76a6c541a2c1787783c598ef9d23d22f6cd36664ab57ea480533f42774","sha256:9c4300b56611f50a7c2d58e391581bcb71dbccba16a9d0d33743e95dde280db3"],"state_sha256":"88e306afd35518bc912d3f53568d79a8348061f15258925056e646fa90082bc6"}