{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FBQSQI357KLTYDZCHVNXZM2VG2","short_pith_number":"pith:FBQSQI35","schema_version":"1.0","canonical_sha256":"286128237dfa973c0f223d5b7cb3553695a8d3c6fa6f223b3bdc4d332b067b4a","source":{"kind":"arxiv","id":"2402.08960","version":2},"attestation_state":"computed","paper":{"title":"Open-Vocabulary Segmentation with Unpaired Mask-Text Supervision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Mingming Gong, Tongliang Liu, Xiaobo Xia, Xiao He, Yandong Guo, Zhaoqing Wang, Ziye Chen","submitted_at":"2024-02-14T06:01:44Z","abstract_excerpt":"Current state-of-the-art open-vocabulary segmentation methods typically rely on image-mask-text triplet annotations for supervision. However, acquiring such detailed annotations is labour-intensive and poses scalability challenges in complex real-world scenarios. While existing weakly-supervised approaches leverage image-text pairs to reduce the expansive annotation cost, the lack of mask supervision makes it difficult for the model to locate multiple instances and accurately group pixels with similar semantics, significantly hampering versatility and performance. In this paper, we introduce U"},"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":"2402.08960","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-14T06:01:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"747f113430005fc31997aaa286635ed22e434533ec1abeab7fb0400b63d92ac6","abstract_canon_sha256":"bf7ca711f8c4744fa220e00e39864be494590d6ddb4827d898bc540a0c987b6b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:30:08.691150Z","signature_b64":"2JJ5djPPwHoIqg1vHX7lGyn0yVugzhVkLWLMqC6bi2DpvGoYPYNE5L6rAUvfoPVYV0U1Gso9h7DeyFNa70CqAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"286128237dfa973c0f223d5b7cb3553695a8d3c6fa6f223b3bdc4d332b067b4a","last_reissued_at":"2026-07-05T08:30:08.690583Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:30:08.690583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Open-Vocabulary Segmentation with Unpaired Mask-Text Supervision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Mingming Gong, Tongliang Liu, Xiaobo Xia, Xiao He, Yandong Guo, Zhaoqing Wang, Ziye Chen","submitted_at":"2024-02-14T06:01:44Z","abstract_excerpt":"Current state-of-the-art open-vocabulary segmentation methods typically rely on image-mask-text triplet annotations for supervision. However, acquiring such detailed annotations is labour-intensive and poses scalability challenges in complex real-world scenarios. While existing weakly-supervised approaches leverage image-text pairs to reduce the expansive annotation cost, the lack of mask supervision makes it difficult for the model to locate multiple instances and accurately group pixels with similar semantics, significantly hampering versatility and performance. In this paper, we introduce U"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.08960","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/2402.08960/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":"2402.08960","created_at":"2026-07-05T08:30:08.690641+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.08960v2","created_at":"2026-07-05T08:30:08.690641+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.08960","created_at":"2026-07-05T08:30:08.690641+00:00"},{"alias_kind":"pith_short_12","alias_value":"FBQSQI357KLT","created_at":"2026-07-05T08:30:08.690641+00:00"},{"alias_kind":"pith_short_16","alias_value":"FBQSQI357KLTYDZC","created_at":"2026-07-05T08:30:08.690641+00:00"},{"alias_kind":"pith_short_8","alias_value":"FBQSQI35","created_at":"2026-07-05T08:30:08.690641+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.07763","citing_title":"Beyond Surface Artifacts: Capturing Shared Latent Forgery Knowledge Across Modalities","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18562","citing_title":"AnchorSeg: Language Grounded Query Banks for Reasoning Segmentation","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FBQSQI357KLTYDZCHVNXZM2VG2","json":"https://pith.science/pith/FBQSQI357KLTYDZCHVNXZM2VG2.json","graph_json":"https://pith.science/api/pith-number/FBQSQI357KLTYDZCHVNXZM2VG2/graph.json","events_json":"https://pith.science/api/pith-number/FBQSQI357KLTYDZCHVNXZM2VG2/events.json","paper":"https://pith.science/paper/FBQSQI35"},"agent_actions":{"view_html":"https://pith.science/pith/FBQSQI357KLTYDZCHVNXZM2VG2","download_json":"https://pith.science/pith/FBQSQI357KLTYDZCHVNXZM2VG2.json","view_paper":"https://pith.science/paper/FBQSQI35","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.08960&json=true","fetch_graph":"https://pith.science/api/pith-number/FBQSQI357KLTYDZCHVNXZM2VG2/graph.json","fetch_events":"https://pith.science/api/pith-number/FBQSQI357KLTYDZCHVNXZM2VG2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FBQSQI357KLTYDZCHVNXZM2VG2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FBQSQI357KLTYDZCHVNXZM2VG2/action/storage_attestation","attest_author":"https://pith.science/pith/FBQSQI357KLTYDZCHVNXZM2VG2/action/author_attestation","sign_citation":"https://pith.science/pith/FBQSQI357KLTYDZCHVNXZM2VG2/action/citation_signature","submit_replication":"https://pith.science/pith/FBQSQI357KLTYDZCHVNXZM2VG2/action/replication_record"}},"created_at":"2026-07-05T08:30:08.690641+00:00","updated_at":"2026-07-05T08:30:08.690641+00:00"}