{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NFLX4AUZ6NY2QL6IFEQZ4RQFLW","short_pith_number":"pith:NFLX4AUZ","schema_version":"1.0","canonical_sha256":"69577e0299f371a82fc829219e46055da96d9b379ef8140064093ece3c84bd79","source":{"kind":"arxiv","id":"2501.00877","version":2},"attestation_state":"computed","paper":{"title":"FGAseg: Fine-Grained Pixel-Text Alignment for Open-Vocabulary Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingyu Li, Da Zhang, Junyu Gao, Xuelong Li, Zhiyuan Zhao","submitted_at":"2025-01-01T15:47:04Z","abstract_excerpt":"Open-vocabulary segmentation aims to identify and segment specific regions and objects based on text-based descriptions. A common solution is to leverage powerful vision-language models (VLMs), such as CLIP, to bridge the gap between vision and text information. However, VLMs are typically pretrained for image-level vision-text alignment, focusing on global semantic features. In contrast, segmentation tasks require fine-grained pixel-level alignment and detailed category boundary information, which VLMs alone cannot provide. As a result, information extracted directly from VLMs can't meet the "},"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":"2501.00877","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-01T15:47:04Z","cross_cats_sorted":[],"title_canon_sha256":"8f2c4815fdc9ef1ac8f2930c6d28541802e08a37a767f0f2ba695da14e7fd37f","abstract_canon_sha256":"8a70ac85eb94ef19727ac30b21911faa48474a5f6d5087cb6121d98d7e6c6cde"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:38.975897Z","signature_b64":"C3Zw55EQ61rPyyphogu8M6Uz8jXO24hxNtnVEdc7IhebPzEUiefIAu1mhE8XuhFEun0FBUsdTb5CEDhnJ73mBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69577e0299f371a82fc829219e46055da96d9b379ef8140064093ece3c84bd79","last_reissued_at":"2026-07-05T09:56:38.975451Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:38.975451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FGAseg: Fine-Grained Pixel-Text Alignment for Open-Vocabulary Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingyu Li, Da Zhang, Junyu Gao, Xuelong Li, Zhiyuan Zhao","submitted_at":"2025-01-01T15:47:04Z","abstract_excerpt":"Open-vocabulary segmentation aims to identify and segment specific regions and objects based on text-based descriptions. A common solution is to leverage powerful vision-language models (VLMs), such as CLIP, to bridge the gap between vision and text information. However, VLMs are typically pretrained for image-level vision-text alignment, focusing on global semantic features. In contrast, segmentation tasks require fine-grained pixel-level alignment and detailed category boundary information, which VLMs alone cannot provide. As a result, information extracted directly from VLMs can't meet the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00877","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/2501.00877/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":"2501.00877","created_at":"2026-07-05T09:56:38.975514+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.00877v2","created_at":"2026-07-05T09:56:38.975514+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00877","created_at":"2026-07-05T09:56:38.975514+00:00"},{"alias_kind":"pith_short_12","alias_value":"NFLX4AUZ6NY2","created_at":"2026-07-05T09:56:38.975514+00:00"},{"alias_kind":"pith_short_16","alias_value":"NFLX4AUZ6NY2QL6I","created_at":"2026-07-05T09:56:38.975514+00:00"},{"alias_kind":"pith_short_8","alias_value":"NFLX4AUZ","created_at":"2026-07-05T09:56:38.975514+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.14176","citing_title":"The Devil Is in Gradient Entanglement: Energy-Aware Gradient Coordinator for Robust Generalized Category Discovery","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NFLX4AUZ6NY2QL6IFEQZ4RQFLW","json":"https://pith.science/pith/NFLX4AUZ6NY2QL6IFEQZ4RQFLW.json","graph_json":"https://pith.science/api/pith-number/NFLX4AUZ6NY2QL6IFEQZ4RQFLW/graph.json","events_json":"https://pith.science/api/pith-number/NFLX4AUZ6NY2QL6IFEQZ4RQFLW/events.json","paper":"https://pith.science/paper/NFLX4AUZ"},"agent_actions":{"view_html":"https://pith.science/pith/NFLX4AUZ6NY2QL6IFEQZ4RQFLW","download_json":"https://pith.science/pith/NFLX4AUZ6NY2QL6IFEQZ4RQFLW.json","view_paper":"https://pith.science/paper/NFLX4AUZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.00877&json=true","fetch_graph":"https://pith.science/api/pith-number/NFLX4AUZ6NY2QL6IFEQZ4RQFLW/graph.json","fetch_events":"https://pith.science/api/pith-number/NFLX4AUZ6NY2QL6IFEQZ4RQFLW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NFLX4AUZ6NY2QL6IFEQZ4RQFLW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NFLX4AUZ6NY2QL6IFEQZ4RQFLW/action/storage_attestation","attest_author":"https://pith.science/pith/NFLX4AUZ6NY2QL6IFEQZ4RQFLW/action/author_attestation","sign_citation":"https://pith.science/pith/NFLX4AUZ6NY2QL6IFEQZ4RQFLW/action/citation_signature","submit_replication":"https://pith.science/pith/NFLX4AUZ6NY2QL6IFEQZ4RQFLW/action/replication_record"}},"created_at":"2026-07-05T09:56:38.975514+00:00","updated_at":"2026-07-05T09:56:38.975514+00:00"}