{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2A55KLWGZR2S65AT7H6ZWZG6L2","short_pith_number":"pith:2A55KLWG","schema_version":"1.0","canonical_sha256":"d03bd52ec6cc752f7413f9fd9b64de5e806d5e95bb12155c6d9df15854fca8f1","source":{"kind":"arxiv","id":"2411.14723","version":2},"attestation_state":"computed","paper":{"title":"Effective SAM Combination for Open-Vocabulary Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Heeseung Choi, Ig-jae Kim, Jungho Lee, Minhyeok Lee, Sangyoun Lee, Suhwan Cho, Sunghun Yang","submitted_at":"2024-11-22T04:36:12Z","abstract_excerpt":"Open-vocabulary semantic segmentation aims to assign pixel-level labels to images across an unlimited range of classes. Traditional methods address this by sequentially connecting a powerful mask proposal generator, such as the Segment Anything Model (SAM), with a pre-trained vision-language model like CLIP. But these two-stage approaches often suffer from high computational costs, memory inefficiencies. In this paper, we propose ESC-Net, a novel one-stage open-vocabulary segmentation model that leverages the SAM decoder blocks for class-agnostic segmentation within an efficient inference fram"},"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":"2411.14723","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-22T04:36:12Z","cross_cats_sorted":[],"title_canon_sha256":"e870de36705cdd24af5ba40a256df8b6714c89f2f28b9aa5f7243e2835d0ebbb","abstract_canon_sha256":"3dd77a61ef948a2739dc0a60a7b9017dc0e7338fe1e33d8eb86a7c581827325e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:17.410487Z","signature_b64":"90/whKYritKVQ4cEcQtdzmqk4SHUHzPLaV1e5i5KhfZlP5H2LKgUaKLMiDJg/RwDrPaSAdYZ0F4UEug6LiVMCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d03bd52ec6cc752f7413f9fd9b64de5e806d5e95bb12155c6d9df15854fca8f1","last_reissued_at":"2026-07-05T10:41:17.409980Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:17.409980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Effective SAM Combination for Open-Vocabulary Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Heeseung Choi, Ig-jae Kim, Jungho Lee, Minhyeok Lee, Sangyoun Lee, Suhwan Cho, Sunghun Yang","submitted_at":"2024-11-22T04:36:12Z","abstract_excerpt":"Open-vocabulary semantic segmentation aims to assign pixel-level labels to images across an unlimited range of classes. Traditional methods address this by sequentially connecting a powerful mask proposal generator, such as the Segment Anything Model (SAM), with a pre-trained vision-language model like CLIP. But these two-stage approaches often suffer from high computational costs, memory inefficiencies. In this paper, we propose ESC-Net, a novel one-stage open-vocabulary segmentation model that leverages the SAM decoder blocks for class-agnostic segmentation within an efficient inference fram"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14723","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/2411.14723/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":"2411.14723","created_at":"2026-07-05T10:41:17.410038+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.14723v2","created_at":"2026-07-05T10:41:17.410038+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14723","created_at":"2026-07-05T10:41:17.410038+00:00"},{"alias_kind":"pith_short_12","alias_value":"2A55KLWGZR2S","created_at":"2026-07-05T10:41:17.410038+00:00"},{"alias_kind":"pith_short_16","alias_value":"2A55KLWGZR2S65AT","created_at":"2026-07-05T10:41:17.410038+00:00"},{"alias_kind":"pith_short_8","alias_value":"2A55KLWG","created_at":"2026-07-05T10:41:17.410038+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/2A55KLWGZR2S65AT7H6ZWZG6L2","json":"https://pith.science/pith/2A55KLWGZR2S65AT7H6ZWZG6L2.json","graph_json":"https://pith.science/api/pith-number/2A55KLWGZR2S65AT7H6ZWZG6L2/graph.json","events_json":"https://pith.science/api/pith-number/2A55KLWGZR2S65AT7H6ZWZG6L2/events.json","paper":"https://pith.science/paper/2A55KLWG"},"agent_actions":{"view_html":"https://pith.science/pith/2A55KLWGZR2S65AT7H6ZWZG6L2","download_json":"https://pith.science/pith/2A55KLWGZR2S65AT7H6ZWZG6L2.json","view_paper":"https://pith.science/paper/2A55KLWG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.14723&json=true","fetch_graph":"https://pith.science/api/pith-number/2A55KLWGZR2S65AT7H6ZWZG6L2/graph.json","fetch_events":"https://pith.science/api/pith-number/2A55KLWGZR2S65AT7H6ZWZG6L2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2A55KLWGZR2S65AT7H6ZWZG6L2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2A55KLWGZR2S65AT7H6ZWZG6L2/action/storage_attestation","attest_author":"https://pith.science/pith/2A55KLWGZR2S65AT7H6ZWZG6L2/action/author_attestation","sign_citation":"https://pith.science/pith/2A55KLWGZR2S65AT7H6ZWZG6L2/action/citation_signature","submit_replication":"https://pith.science/pith/2A55KLWGZR2S65AT7H6ZWZG6L2/action/replication_record"}},"created_at":"2026-07-05T10:41:17.410038+00:00","updated_at":"2026-07-05T10:41:17.410038+00:00"}