{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZXWJQJCP5UWGZKFCQKXRVFDNTQ","short_pith_number":"pith:ZXWJQJCP","schema_version":"1.0","canonical_sha256":"cdec98244fed2c6ca8a282af1a946d9c36640106ccd752ffed36524bc9d1360a","source":{"kind":"arxiv","id":"2505.11676","version":1},"attestation_state":"computed","paper":{"title":"DPSeg: Dual-Prompt Cost Volume Learning for Open-Vocabulary Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Linjia Shi, Nasrin Imanpour, Song Wang, Xiaoguang Li, Ziyu Zhao","submitted_at":"2025-05-16T20:25:42Z","abstract_excerpt":"Open-vocabulary semantic segmentation aims to segment images into distinct semantic regions for both seen and unseen categories at the pixel level. Current methods utilize text embeddings from pre-trained vision-language models like CLIP but struggle with the inherent domain gap between image and text embeddings, even after extensive alignment during training. Additionally, relying solely on deep text-aligned features limits shallow-level feature guidance, which is crucial for detecting small objects and fine details, ultimately reducing segmentation accuracy. To address these limitations, we "},"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":"2505.11676","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-16T20:25:42Z","cross_cats_sorted":[],"title_canon_sha256":"d91798f6e48aa0b6d573e5cd689a280e7f56ca2ba40033de0382f70b57c67c7f","abstract_canon_sha256":"f682ba4eafbff0b01b9e501d6f115f852e98900b39a96c1f5c89b9cdd2ce306f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:25.318603Z","signature_b64":"U4IVz+A+3k/1jB2w0qQfpCA53UxYYpHi5ySsM4pCml8AzuPhjUCoWX0NKVLTXhxOIdPXuDiwXs9vprq511lfBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cdec98244fed2c6ca8a282af1a946d9c36640106ccd752ffed36524bc9d1360a","last_reissued_at":"2026-07-05T11:04:25.318057Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:25.318057Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DPSeg: Dual-Prompt Cost Volume Learning for Open-Vocabulary Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Linjia Shi, Nasrin Imanpour, Song Wang, Xiaoguang Li, Ziyu Zhao","submitted_at":"2025-05-16T20:25:42Z","abstract_excerpt":"Open-vocabulary semantic segmentation aims to segment images into distinct semantic regions for both seen and unseen categories at the pixel level. Current methods utilize text embeddings from pre-trained vision-language models like CLIP but struggle with the inherent domain gap between image and text embeddings, even after extensive alignment during training. Additionally, relying solely on deep text-aligned features limits shallow-level feature guidance, which is crucial for detecting small objects and fine details, ultimately reducing segmentation accuracy. To address these limitations, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11676","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/2505.11676/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":"2505.11676","created_at":"2026-07-05T11:04:25.318117+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.11676v1","created_at":"2026-07-05T11:04:25.318117+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11676","created_at":"2026-07-05T11:04:25.318117+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZXWJQJCP5UWG","created_at":"2026-07-05T11:04:25.318117+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZXWJQJCP5UWGZKFC","created_at":"2026-07-05T11:04:25.318117+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZXWJQJCP","created_at":"2026-07-05T11:04:25.318117+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/ZXWJQJCP5UWGZKFCQKXRVFDNTQ","json":"https://pith.science/pith/ZXWJQJCP5UWGZKFCQKXRVFDNTQ.json","graph_json":"https://pith.science/api/pith-number/ZXWJQJCP5UWGZKFCQKXRVFDNTQ/graph.json","events_json":"https://pith.science/api/pith-number/ZXWJQJCP5UWGZKFCQKXRVFDNTQ/events.json","paper":"https://pith.science/paper/ZXWJQJCP"},"agent_actions":{"view_html":"https://pith.science/pith/ZXWJQJCP5UWGZKFCQKXRVFDNTQ","download_json":"https://pith.science/pith/ZXWJQJCP5UWGZKFCQKXRVFDNTQ.json","view_paper":"https://pith.science/paper/ZXWJQJCP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.11676&json=true","fetch_graph":"https://pith.science/api/pith-number/ZXWJQJCP5UWGZKFCQKXRVFDNTQ/graph.json","fetch_events":"https://pith.science/api/pith-number/ZXWJQJCP5UWGZKFCQKXRVFDNTQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZXWJQJCP5UWGZKFCQKXRVFDNTQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZXWJQJCP5UWGZKFCQKXRVFDNTQ/action/storage_attestation","attest_author":"https://pith.science/pith/ZXWJQJCP5UWGZKFCQKXRVFDNTQ/action/author_attestation","sign_citation":"https://pith.science/pith/ZXWJQJCP5UWGZKFCQKXRVFDNTQ/action/citation_signature","submit_replication":"https://pith.science/pith/ZXWJQJCP5UWGZKFCQKXRVFDNTQ/action/replication_record"}},"created_at":"2026-07-05T11:04:25.318117+00:00","updated_at":"2026-07-05T11:04:25.318117+00:00"}