{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:733PCQSKJSQTRHVXMX3IMZSVS4","short_pith_number":"pith:733PCQSK","schema_version":"1.0","canonical_sha256":"fef6f1424a4ca1389eb765f686665597301b58f498d72edc5dc333be2a4626ee","source":{"kind":"arxiv","id":"2608.11681","version":1},"attestation_state":"computed","paper":{"title":"Learning from Multimodal Pseudo-Labels for Robust Open-Vocabulary Instance and Panoptic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Byeongkeun Kang, Duy Tran Thanh, Yeejin Lee","submitted_at":"2026-08-12T05:39:57Z","abstract_excerpt":"This work addresses the challenge of open-vocabulary instance segmentation (OVIS) and open-set panoptic segmentation (OSPS), which aim to recognize both predefined and unseen object categories without exhaustive human annotations. Existing methods often suffer from noisy pseudo-masks, limited visual-textual grounding, and difficulty handling synonyms or out-of-vocabulary (OOV) words. To overcome these challenges, we propose a multimodal framework that leverages pre-trained vision-language models for automatic pseudo-label generation, CLIP-guided synonym filtering, and GPT-based caption reconst"},"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":"2608.11681","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-12T05:39:57Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"869a3fb38265bb7b4279f148821c4a6a07bc06b60c4c34483fad716c1730b38d","abstract_canon_sha256":"a146c7a35dd15091eeeb9cec3796113f812bbd4304411f9836b79bcba0e95f19"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-13T01:27:49.365960Z","signature_b64":"goJNT19VDZbYN5z6mBQTyItDzIqFoqgGAmlyHHU5r35pEA76aEX5/+XnqawJ5gCRKv2w/k8lfvIQqZgOJI8+Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fef6f1424a4ca1389eb765f686665597301b58f498d72edc5dc333be2a4626ee","last_reissued_at":"2026-08-13T01:27:49.363825Z","signature_status":"signed_v1","first_computed_at":"2026-08-13T01:27:49.363825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning from Multimodal Pseudo-Labels for Robust Open-Vocabulary Instance and Panoptic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Byeongkeun Kang, Duy Tran Thanh, Yeejin Lee","submitted_at":"2026-08-12T05:39:57Z","abstract_excerpt":"This work addresses the challenge of open-vocabulary instance segmentation (OVIS) and open-set panoptic segmentation (OSPS), which aim to recognize both predefined and unseen object categories without exhaustive human annotations. Existing methods often suffer from noisy pseudo-masks, limited visual-textual grounding, and difficulty handling synonyms or out-of-vocabulary (OOV) words. To overcome these challenges, we propose a multimodal framework that leverages pre-trained vision-language models for automatic pseudo-label generation, CLIP-guided synonym filtering, and GPT-based caption reconst"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.11681","kind":"arxiv","version":1},"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/2608.11681/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":"2608.11681","created_at":"2026-08-13T01:27:49.364970+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.11681v1","created_at":"2026-08-13T01:27:49.364970+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.11681","created_at":"2026-08-13T01:27:49.364970+00:00"},{"alias_kind":"pith_short_12","alias_value":"733PCQSKJSQT","created_at":"2026-08-13T01:27:49.364970+00:00"},{"alias_kind":"pith_short_16","alias_value":"733PCQSKJSQTRHVX","created_at":"2026-08-13T01:27:49.364970+00:00"},{"alias_kind":"pith_short_8","alias_value":"733PCQSK","created_at":"2026-08-13T01:27:49.364970+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/733PCQSKJSQTRHVXMX3IMZSVS4","json":"https://pith.science/pith/733PCQSKJSQTRHVXMX3IMZSVS4.json","graph_json":"https://pith.science/api/pith-number/733PCQSKJSQTRHVXMX3IMZSVS4/graph.json","events_json":"https://pith.science/api/pith-number/733PCQSKJSQTRHVXMX3IMZSVS4/events.json","paper":"https://pith.science/paper/733PCQSK"},"agent_actions":{"view_html":"https://pith.science/pith/733PCQSKJSQTRHVXMX3IMZSVS4","download_json":"https://pith.science/pith/733PCQSKJSQTRHVXMX3IMZSVS4.json","view_paper":"https://pith.science/paper/733PCQSK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.11681&json=true","fetch_graph":"https://pith.science/api/pith-number/733PCQSKJSQTRHVXMX3IMZSVS4/graph.json","fetch_events":"https://pith.science/api/pith-number/733PCQSKJSQTRHVXMX3IMZSVS4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/733PCQSKJSQTRHVXMX3IMZSVS4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/733PCQSKJSQTRHVXMX3IMZSVS4/action/storage_attestation","attest_author":"https://pith.science/pith/733PCQSKJSQTRHVXMX3IMZSVS4/action/author_attestation","sign_citation":"https://pith.science/pith/733PCQSKJSQTRHVXMX3IMZSVS4/action/citation_signature","submit_replication":"https://pith.science/pith/733PCQSKJSQTRHVXMX3IMZSVS4/action/replication_record"}},"created_at":"2026-08-13T01:27:49.364970+00:00","updated_at":"2026-08-13T01:27:49.364970+00:00"}