{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LRQSKRK72USEY3NKAIAKY4O3BS","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":"853cce57460b07cf22538e8c81ae3b74376e6594f9fb670b2fa901e64438f63a","cross_cats_sorted":["cs.CL","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-12T19:00:04Z","title_canon_sha256":"89edd37a8a45c93e463ed4c0376a0ecd9fdaa0e7cf1acee28737940a4331a34f"},"schema_version":"1.0","source":{"id":"2312.07661","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.07661","created_at":"2026-07-05T08:16:24Z"},{"alias_kind":"arxiv_version","alias_value":"2312.07661v3","created_at":"2026-07-05T08:16:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.07661","created_at":"2026-07-05T08:16:24Z"},{"alias_kind":"pith_short_12","alias_value":"LRQSKRK72USE","created_at":"2026-07-05T08:16:24Z"},{"alias_kind":"pith_short_16","alias_value":"LRQSKRK72USEY3NK","created_at":"2026-07-05T08:16:24Z"},{"alias_kind":"pith_short_8","alias_value":"LRQSKRK7","created_at":"2026-07-05T08:16:24Z"}],"graph_snapshots":[{"event_id":"sha256:a314f7c5a1ecf8749a6c66641cddca2755efd1c0b0f850970439265f4078c5e7","target":"graph","created_at":"2026-07-05T08:16:24Z","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/2312.07661/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing open-vocabulary image segmentation methods require a fine-tuning step on mask labels and/or image-text datasets. Mask labels are labor-intensive, which limits the number of categories in segmentation datasets. Consequently, the vocabulary capacity of pre-trained VLMs is severely reduced after fine-tuning. However, without fine-tuning, VLMs trained under weak image-text supervision tend to make suboptimal mask predictions. To alleviate these issues, we introduce a novel recurrent framework that progressively filters out irrelevant texts and enhances mask quality without training effort","authors_text":"Philip Torr, Runjia Li, Shuyang Sun, Siyang Li, Xiuye Gu","cross_cats":["cs.CL","cs.LG","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-12T19:00:04Z","title":"CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.07661","kind":"arxiv","version":3},"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:c5db13eeb994aade26d2e3a404fba9931a2800908b633a9fbb2d57a56224fd28","target":"record","created_at":"2026-07-05T08:16:24Z","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":"853cce57460b07cf22538e8c81ae3b74376e6594f9fb670b2fa901e64438f63a","cross_cats_sorted":["cs.CL","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-12T19:00:04Z","title_canon_sha256":"89edd37a8a45c93e463ed4c0376a0ecd9fdaa0e7cf1acee28737940a4331a34f"},"schema_version":"1.0","source":{"id":"2312.07661","kind":"arxiv","version":3}},"canonical_sha256":"5c6125455fd5244c6daa0200ac71db0c8b05f5d6da08bf5b77155650472bd353","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c6125455fd5244c6daa0200ac71db0c8b05f5d6da08bf5b77155650472bd353","first_computed_at":"2026-07-05T08:16:24.208877Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:16:24.208877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Fkp8iguRTpqrDy5pDlzd8foKUizKxSBZfjo5Oi3OEc36ytss3SRgSYTXAxY8HscZJnEdHbsr8cFIXzz8f3erCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:16:24.209329Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.07661","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c5db13eeb994aade26d2e3a404fba9931a2800908b633a9fbb2d57a56224fd28","sha256:a314f7c5a1ecf8749a6c66641cddca2755efd1c0b0f850970439265f4078c5e7"],"state_sha256":"475886e27ac20d83dd7ecc692ccab726f8b8d15e7a4d3fd8d0da2d16ed8fc8cd"}