{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:2PUUUTMQVDATH7D4ZBMDYR4MGK","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":"ff6352ec2c2caa97a07a391987a26a3e9b728d9dd8c07885eed961aca00891c8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-30T07:29:08Z","title_canon_sha256":"486737294a6d9c5c233527c5c81978de6d68065d876e246159980711e9deffeb"},"schema_version":"1.0","source":{"id":"2111.15174","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.15174","created_at":"2026-07-05T04:05:03Z"},{"alias_kind":"arxiv_version","alias_value":"2111.15174v2","created_at":"2026-07-05T04:05:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.15174","created_at":"2026-07-05T04:05:03Z"},{"alias_kind":"pith_short_12","alias_value":"2PUUUTMQVDAT","created_at":"2026-07-05T04:05:03Z"},{"alias_kind":"pith_short_16","alias_value":"2PUUUTMQVDATH7D4","created_at":"2026-07-05T04:05:03Z"},{"alias_kind":"pith_short_8","alias_value":"2PUUUTMQ","created_at":"2026-07-05T04:05:03Z"}],"graph_snapshots":[{"event_id":"sha256:bb32d4d2dfa4056e45148368057a13b022a6c68bfe053215ebd275e5a57bd63d","target":"graph","created_at":"2026-07-05T04:05:03Z","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/2111.15174/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Referring image segmentation aims to segment a referent via a natural linguistic expression.Due to the distinct data properties between text and image, it is challenging for a network to well align text and pixel-level features. Existing approaches use pretrained models to facilitate learning, yet separately transfer the language/vision knowledge from pretrained models, ignoring the multi-modal corresponding information. Inspired by the recent advance in Contrastive Language-Image Pretraining (CLIP), in this paper, we propose an end-to-end CLIP-Driven Referring Image Segmentation framework (CR","authors_text":"Mingming Gong, Qiang Li, Tongliang Liu, Xunqiang Tao, Yandong Guo, Yu Lu, Zhaoqing Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-30T07:29:08Z","title":"CRIS: CLIP-Driven Referring Image Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.15174","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":"sha256:567d85b19639272f34f1b6abee646c807e112fdc62274f24c61902945a3c7720","target":"record","created_at":"2026-07-05T04:05:03Z","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":"ff6352ec2c2caa97a07a391987a26a3e9b728d9dd8c07885eed961aca00891c8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-30T07:29:08Z","title_canon_sha256":"486737294a6d9c5c233527c5c81978de6d68065d876e246159980711e9deffeb"},"schema_version":"1.0","source":{"id":"2111.15174","kind":"arxiv","version":2}},"canonical_sha256":"d3e94a4d90a8c133fc7cc8583c478c328053864c5348dac659e78fd32dd17dda","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d3e94a4d90a8c133fc7cc8583c478c328053864c5348dac659e78fd32dd17dda","first_computed_at":"2026-07-05T04:05:03.813101Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:05:03.813101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K4vQncSwMbQJhZQIpHiuybj7uIFbMUaMNiLC+sYMTwp2u0CNLuLnAAkiCmMt3VczEvs3F4/RO6GDoUe6TcoOBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:05:03.813580Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.15174","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:567d85b19639272f34f1b6abee646c807e112fdc62274f24c61902945a3c7720","sha256:bb32d4d2dfa4056e45148368057a13b022a6c68bfe053215ebd275e5a57bd63d"],"state_sha256":"74e40a3af6f699ccd750f682724059b72079ce2ddfead2a7cd09c568fd39d526"}