{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:N6BQEGEBRY76ECFZMFMW6ACT4L","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":"61aa96df243ab1dfa327f09a525430978b6ce1a7c54bbce94ee3464805499422","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-09T02:57:32Z","title_canon_sha256":"ab5e61143bfc259f5649667d38bdc36db4845ebc76d4f28f7a57fd47ae138a0d"},"schema_version":"1.0","source":{"id":"2210.04150","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.04150","created_at":"2026-07-05T05:56:54Z"},{"alias_kind":"arxiv_version","alias_value":"2210.04150v3","created_at":"2026-07-05T05:56:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.04150","created_at":"2026-07-05T05:56:54Z"},{"alias_kind":"pith_short_12","alias_value":"N6BQEGEBRY76","created_at":"2026-07-05T05:56:54Z"},{"alias_kind":"pith_short_16","alias_value":"N6BQEGEBRY76ECFZ","created_at":"2026-07-05T05:56:54Z"},{"alias_kind":"pith_short_8","alias_value":"N6BQEGEB","created_at":"2026-07-05T05:56:54Z"}],"graph_snapshots":[{"event_id":"sha256:390b2caa4dc89771ae95ac99d91e21cd6c67d9ecd62988b91306eb715540fad6","target":"graph","created_at":"2026-07-05T05:56:54Z","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/2210.04150/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Open-vocabulary semantic segmentation aims to segment an image into semantic regions according to text descriptions, which may not have been seen during training. Recent two-stage methods first generate class-agnostic mask proposals and then leverage pre-trained vision-language models, e.g., CLIP, to classify masked regions. We identify the performance bottleneck of this paradigm to be the pre-trained CLIP model, since it does not perform well on masked images. To address this, we propose to finetune CLIP on a collection of masked image regions and their corresponding text descriptions. We col","authors_text":"Bichen Wu, Diana Marculescu, Feng Liang, Hang Zhang, Kunpeng Li, Peizhao Zhang, Peter Vajda, Xiaoliang Dai, Yinan Zhao","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-09T02:57:32Z","title":"Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.04150","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":"sha256:7efca2c9cc24573574ff80864b5524a2868aa817f7a73169fff3aa4668bba163","target":"record","created_at":"2026-07-05T05:56:54Z","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":"61aa96df243ab1dfa327f09a525430978b6ce1a7c54bbce94ee3464805499422","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-09T02:57:32Z","title_canon_sha256":"ab5e61143bfc259f5649667d38bdc36db4845ebc76d4f28f7a57fd47ae138a0d"},"schema_version":"1.0","source":{"id":"2210.04150","kind":"arxiv","version":3}},"canonical_sha256":"6f830218818e3fe208b961596f0053e2f87fa7e98a10268ee4f301534de1d88f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6f830218818e3fe208b961596f0053e2f87fa7e98a10268ee4f301534de1d88f","first_computed_at":"2026-07-05T05:56:54.844558Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:56:54.844558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U1WZduw0Aba2f1/CI8gN2o9HnD8/WnsCrkLVsEJYRQPXcTPAqQ1qgGkdV8TNy7Fd0qhNsypXmdIyk0ORs15/DA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:56:54.845042Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.04150","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7efca2c9cc24573574ff80864b5524a2868aa817f7a73169fff3aa4668bba163","sha256:390b2caa4dc89771ae95ac99d91e21cd6c67d9ecd62988b91306eb715540fad6"],"state_sha256":"a80cb9f97175a0c2619e50cebd31767a1f8e4a5d0e0fb61240376c317240048a"}