{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ZBWA776AAAIQ7L7ARTBVBCRZJG","short_pith_number":"pith:ZBWA776A","schema_version":"1.0","canonical_sha256":"c86c0fffc000110fafe08cc3508a3949a7fe84334c8be1e6d18dd1bc266e3311","source":{"kind":"arxiv","id":"2212.00785","version":2},"attestation_state":"computed","paper":{"title":"Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Byungseok Roh, Jonghwan Mun, Junbum Cha","submitted_at":"2022-12-01T18:59:03Z","abstract_excerpt":"We tackle open-world semantic segmentation, which aims at learning to segment arbitrary visual concepts in images, by using only image-text pairs without dense annotations. Existing open-world segmentation methods have shown impressive advances by employing contrastive learning (CL) to learn diverse visual concepts and transferring the learned image-level understanding to the segmentation task. However, these CL-based methods suffer from a train-test discrepancy, since it only considers image-text alignment during training, whereas segmentation requires region-text alignment during testing. In"},"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":"2212.00785","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-01T18:59:03Z","cross_cats_sorted":[],"title_canon_sha256":"6d5eef570a4ff54ca631ff2a26e2278f10b20668757f713bc9acd4b11a6af42c","abstract_canon_sha256":"755239e1f3db743bd28c59e1f91aec431e67f7b0bd63c5dd1970192b5fd919f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:34.013477Z","signature_b64":"nEZ5EJa7hoNEPbQrwYQg4cvofTF4WCXNFQn+e8wl5J2Q3yrSNtvBRQc27UIIKNdlZHAVCGyYPwdR5DyjlS0YCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c86c0fffc000110fafe08cc3508a3949a7fe84334c8be1e6d18dd1bc266e3311","last_reissued_at":"2026-07-05T05:54:34.012980Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:34.012980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Byungseok Roh, Jonghwan Mun, Junbum Cha","submitted_at":"2022-12-01T18:59:03Z","abstract_excerpt":"We tackle open-world semantic segmentation, which aims at learning to segment arbitrary visual concepts in images, by using only image-text pairs without dense annotations. Existing open-world segmentation methods have shown impressive advances by employing contrastive learning (CL) to learn diverse visual concepts and transferring the learned image-level understanding to the segmentation task. However, these CL-based methods suffer from a train-test discrepancy, since it only considers image-text alignment during training, whereas segmentation requires region-text alignment during testing. In"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.00785","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/2212.00785/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":"2212.00785","created_at":"2026-07-05T05:54:34.013052+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.00785v2","created_at":"2026-07-05T05:54:34.013052+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.00785","created_at":"2026-07-05T05:54:34.013052+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZBWA776AAAIQ","created_at":"2026-07-05T05:54:34.013052+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZBWA776AAAIQ7L7A","created_at":"2026-07-05T05:54:34.013052+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZBWA776A","created_at":"2026-07-05T05:54:34.013052+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZBWA776AAAIQ7L7ARTBVBCRZJG","json":"https://pith.science/pith/ZBWA776AAAIQ7L7ARTBVBCRZJG.json","graph_json":"https://pith.science/api/pith-number/ZBWA776AAAIQ7L7ARTBVBCRZJG/graph.json","events_json":"https://pith.science/api/pith-number/ZBWA776AAAIQ7L7ARTBVBCRZJG/events.json","paper":"https://pith.science/paper/ZBWA776A"},"agent_actions":{"view_html":"https://pith.science/pith/ZBWA776AAAIQ7L7ARTBVBCRZJG","download_json":"https://pith.science/pith/ZBWA776AAAIQ7L7ARTBVBCRZJG.json","view_paper":"https://pith.science/paper/ZBWA776A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.00785&json=true","fetch_graph":"https://pith.science/api/pith-number/ZBWA776AAAIQ7L7ARTBVBCRZJG/graph.json","fetch_events":"https://pith.science/api/pith-number/ZBWA776AAAIQ7L7ARTBVBCRZJG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZBWA776AAAIQ7L7ARTBVBCRZJG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZBWA776AAAIQ7L7ARTBVBCRZJG/action/storage_attestation","attest_author":"https://pith.science/pith/ZBWA776AAAIQ7L7ARTBVBCRZJG/action/author_attestation","sign_citation":"https://pith.science/pith/ZBWA776AAAIQ7L7ARTBVBCRZJG/action/citation_signature","submit_replication":"https://pith.science/pith/ZBWA776AAAIQ7L7ARTBVBCRZJG/action/replication_record"}},"created_at":"2026-07-05T05:54:34.013052+00:00","updated_at":"2026-07-05T05:54:34.013052+00:00"}