{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6CXJ54KSQWV73YZLFVDLIFYF2R","short_pith_number":"pith:6CXJ54KS","schema_version":"1.0","canonical_sha256":"f0ae9ef15285abfde32b2d46b41705d460a7a933cf35f4ea25eb5d14d4d0121a","source":{"kind":"arxiv","id":"2308.02487","version":2},"attestation_state":"computed","paper":{"title":"Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ju He, Liang-Chieh Chen, Qihang Yu, Xiaohui Shen, Xueqing Deng","submitted_at":"2023-08-04T17:59:01Z","abstract_excerpt":"Open-vocabulary segmentation is a challenging task requiring segmenting and recognizing objects from an open set of categories. One way to address this challenge is to leverage multi-modal models, such as CLIP, to provide image and text features in a shared embedding space, which bridges the gap between closed-vocabulary and open-vocabulary recognition. Hence, existing methods often adopt a two-stage framework to tackle the problem, where the inputs first go through a mask generator and then through the CLIP model along with the predicted masks. This process involves extracting features from i"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2308.02487","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-04T17:59:01Z","cross_cats_sorted":[],"title_canon_sha256":"921fefb5e935912377ba3671b98fcae8b236dbd9d5511f36c7f7c4bb46624525","abstract_canon_sha256":"ec97af8c6a7e3b3775043eb78af5d446ad7f2980ee114ffc947d72087ad178f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:12:52.086957Z","signature_b64":"YG/mlDv1fISJ86IYQ1qt7A/09Lf0wACJT9n2BFbAC2HWrq71G1QlS91c5DiOPH9KaPSJvxhZdZ8Fe3TEa69dCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0ae9ef15285abfde32b2d46b41705d460a7a933cf35f4ea25eb5d14d4d0121a","last_reissued_at":"2026-07-05T07:12:52.086466Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:12:52.086466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ju He, Liang-Chieh Chen, Qihang Yu, Xiaohui Shen, Xueqing Deng","submitted_at":"2023-08-04T17:59:01Z","abstract_excerpt":"Open-vocabulary segmentation is a challenging task requiring segmenting and recognizing objects from an open set of categories. One way to address this challenge is to leverage multi-modal models, such as CLIP, to provide image and text features in a shared embedding space, which bridges the gap between closed-vocabulary and open-vocabulary recognition. Hence, existing methods often adopt a two-stage framework to tackle the problem, where the inputs first go through a mask generator and then through the CLIP model along with the predicted masks. This process involves extracting features from i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.02487","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2308.02487/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2308.02487","created_at":"2026-07-05T07:12:52.086524+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.02487v2","created_at":"2026-07-05T07:12:52.086524+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.02487","created_at":"2026-07-05T07:12:52.086524+00:00"},{"alias_kind":"pith_short_12","alias_value":"6CXJ54KSQWV7","created_at":"2026-07-05T07:12:52.086524+00:00"},{"alias_kind":"pith_short_16","alias_value":"6CXJ54KSQWV73YZL","created_at":"2026-07-05T07:12:52.086524+00:00"},{"alias_kind":"pith_short_8","alias_value":"6CXJ54KS","created_at":"2026-07-05T07:12:52.086524+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17630","citing_title":"SegRAG: Training-Free Retrieval-Augmented Semantic Segmentation","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17630","citing_title":"SegRAG: Training-Free Retrieval-Augmented Semantic Segmentation","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2403.14608","citing_title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","ref_index":204,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6CXJ54KSQWV73YZLFVDLIFYF2R","json":"https://pith.science/pith/6CXJ54KSQWV73YZLFVDLIFYF2R.json","graph_json":"https://pith.science/api/pith-number/6CXJ54KSQWV73YZLFVDLIFYF2R/graph.json","events_json":"https://pith.science/api/pith-number/6CXJ54KSQWV73YZLFVDLIFYF2R/events.json","paper":"https://pith.science/paper/6CXJ54KS"},"agent_actions":{"view_html":"https://pith.science/pith/6CXJ54KSQWV73YZLFVDLIFYF2R","download_json":"https://pith.science/pith/6CXJ54KSQWV73YZLFVDLIFYF2R.json","view_paper":"https://pith.science/paper/6CXJ54KS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.02487&json=true","fetch_graph":"https://pith.science/api/pith-number/6CXJ54KSQWV73YZLFVDLIFYF2R/graph.json","fetch_events":"https://pith.science/api/pith-number/6CXJ54KSQWV73YZLFVDLIFYF2R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6CXJ54KSQWV73YZLFVDLIFYF2R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6CXJ54KSQWV73YZLFVDLIFYF2R/action/storage_attestation","attest_author":"https://pith.science/pith/6CXJ54KSQWV73YZLFVDLIFYF2R/action/author_attestation","sign_citation":"https://pith.science/pith/6CXJ54KSQWV73YZLFVDLIFYF2R/action/citation_signature","submit_replication":"https://pith.science/pith/6CXJ54KSQWV73YZLFVDLIFYF2R/action/replication_record"}},"created_at":"2026-07-05T07:12:52.086524+00:00","updated_at":"2026-07-05T07:12:52.086524+00:00"}