{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:WC6O7FEXY4EC3SURIRNML75JON","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":"b99a83b561d0698af4e41c992b63370790f06e95ce801f24094ed0a47f10c44b","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-04T04:53:35Z","title_canon_sha256":"e9b675e8fa127f3a1ff1adc2568ea58de7cc43abe3da094c003dfe0c4c8fa0bc"},"schema_version":"1.0","source":{"id":"2112.02244","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.02244","created_at":"2026-07-05T04:12:05Z"},{"alias_kind":"arxiv_version","alias_value":"2112.02244v2","created_at":"2026-07-05T04:12:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.02244","created_at":"2026-07-05T04:12:05Z"},{"alias_kind":"pith_short_12","alias_value":"WC6O7FEXY4EC","created_at":"2026-07-05T04:12:05Z"},{"alias_kind":"pith_short_16","alias_value":"WC6O7FEXY4EC3SUR","created_at":"2026-07-05T04:12:05Z"},{"alias_kind":"pith_short_8","alias_value":"WC6O7FEX","created_at":"2026-07-05T04:12:05Z"}],"graph_snapshots":[{"event_id":"sha256:2f4267aa0377304aafce81d022869c0e2e9f294bdfa31306d18fb21ded20a3a1","target":"graph","created_at":"2026-07-05T04:12:05Z","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/2112.02244/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Referring image segmentation is a fundamental vision-language task that aims to segment out an object referred to by a natural language expression from an image. One of the key challenges behind this task is leveraging the referring expression for highlighting relevant positions in the image. A paradigm for tackling this problem is to leverage a powerful vision-language (\"cross-modal\") decoder to fuse features independently extracted from a vision encoder and a language encoder. Recent methods have made remarkable advancements in this paradigm by exploiting Transformers as cross-modal decoders","authors_text":"Hengshuang Zhao, Jiaqi Wang, Kai Chen, Philip H.S. Torr, Yansong Tang, Zhao Yang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-04T04:53:35Z","title":"LAVT: Language-Aware Vision Transformer for Referring Image Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.02244","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:c38af8790a04d5873560e05437cba9573587b7117ee0c25cc9f3730e1e670c6d","target":"record","created_at":"2026-07-05T04:12:05Z","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":"b99a83b561d0698af4e41c992b63370790f06e95ce801f24094ed0a47f10c44b","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-04T04:53:35Z","title_canon_sha256":"e9b675e8fa127f3a1ff1adc2568ea58de7cc43abe3da094c003dfe0c4c8fa0bc"},"schema_version":"1.0","source":{"id":"2112.02244","kind":"arxiv","version":2}},"canonical_sha256":"b0bcef9497c7082dca91445ac5ffa973609b48c041c57fba31d0bb3ac3d0cbc7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b0bcef9497c7082dca91445ac5ffa973609b48c041c57fba31d0bb3ac3d0cbc7","first_computed_at":"2026-07-05T04:12:05.249451Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:12:05.249451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b6n4CNr8FxxHM156927PZ7bcp5GFlqhYwhJt2k7FrhWaeG6toXK6sZj+c3uQVTM9cGpuEuRhbu2po6srvwi/Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T04:12:05.249946Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.02244","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c38af8790a04d5873560e05437cba9573587b7117ee0c25cc9f3730e1e670c6d","sha256:2f4267aa0377304aafce81d022869c0e2e9f294bdfa31306d18fb21ded20a3a1"],"state_sha256":"5c329ee3af2108d80143ebf505bbff6a1bc195ef58a0f0fe40214ad3e311decd"}