{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GV2OPBL6AO5K52FDF5GXYTGPVL","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":"0d0817441f385d6c9f389d2138d129fc22917a6ebed92f9ce203478d45986de5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-14T23:00:25Z","title_canon_sha256":"bbcf64b19a805687e91e818acac9fc2c2581f34276b5ef8b54966dfcd7a20ff8"},"schema_version":"1.0","source":{"id":"2302.07387","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.07387","created_at":"2026-07-05T05:55:19Z"},{"alias_kind":"arxiv_version","alias_value":"2302.07387v2","created_at":"2026-07-05T05:55:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.07387","created_at":"2026-07-05T05:55:19Z"},{"alias_kind":"pith_short_12","alias_value":"GV2OPBL6AO5K","created_at":"2026-07-05T05:55:19Z"},{"alias_kind":"pith_short_16","alias_value":"GV2OPBL6AO5K52FD","created_at":"2026-07-05T05:55:19Z"},{"alias_kind":"pith_short_8","alias_value":"GV2OPBL6","created_at":"2026-07-05T05:55:19Z"}],"graph_snapshots":[{"event_id":"sha256:66e18192697cd6d67b19f996be028370cc8625b485bd4862e42692ba405e1d13","target":"graph","created_at":"2026-07-05T05:55:19Z","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/2302.07387/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, instead of directly predicting the pixel-level segmentation masks, the problem of referring image segmentation is formulated as sequential polygon generation, and the predicted polygons can be later converted into segmentation masks. This is enabled by a new sequence-to-sequence framework, Polygon Transformer (PolyFormer), which takes a sequence of image patches and text query tokens as input, and outputs a sequence of polygon vertices autoregressively. For more accurate geometric localization, we propose a regression-based decoder, which predicts the precise floating-point coord","authors_text":"Hui Ding, Jiang Liu, Ravi Kumar Satzoda, R. Manmatha, Vijay Mahadevan, Yuting Zhang, Zhaowei Cai","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-14T23:00:25Z","title":"PolyFormer: Referring Image Segmentation as Sequential Polygon Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.07387","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:c8f621c4ae5a4c510929bb8dcd0a3f06ba21d6c8fa06da109b66a82126fcb962","target":"record","created_at":"2026-07-05T05:55:19Z","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":"0d0817441f385d6c9f389d2138d129fc22917a6ebed92f9ce203478d45986de5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-14T23:00:25Z","title_canon_sha256":"bbcf64b19a805687e91e818acac9fc2c2581f34276b5ef8b54966dfcd7a20ff8"},"schema_version":"1.0","source":{"id":"2302.07387","kind":"arxiv","version":2}},"canonical_sha256":"3574e7857e03baaee8a32f4d7c4ccfaae16946d81f809e7350b1023f976981c2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3574e7857e03baaee8a32f4d7c4ccfaae16946d81f809e7350b1023f976981c2","first_computed_at":"2026-07-05T05:55:19.185542Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:55:19.185542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3fBPDUIugN87Ax8eAeqkco5QgCWMss7SOu66+0drTESHg0LzdLskHw/8GCz0mKayYK2e2m240vZaBaOtxdItCw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:55:19.186040Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.07387","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c8f621c4ae5a4c510929bb8dcd0a3f06ba21d6c8fa06da109b66a82126fcb962","sha256:66e18192697cd6d67b19f996be028370cc8625b485bd4862e42692ba405e1d13"],"state_sha256":"f43f96ba7a6938d47a0394e07c182aab84c4690e48a61903eef3dcfa7090e9b7"}