{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NDBAIY32BSKCXDW5VFKLPMACV2","short_pith_number":"pith:NDBAIY32","schema_version":"1.0","canonical_sha256":"68c204637a0c942b8edda954b7b002ae949319f9a776635a18f9161ba4a8114a","source":{"kind":"arxiv","id":"2406.19638","version":1},"attestation_state":"computed","paper":{"title":"Precision matters: Precision-aware ensemble for weakly supervised semantic segmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hyunjung Shim, Junsung Park","submitted_at":"2024-06-28T03:58:02Z","abstract_excerpt":"Weakly Supervised Semantic Segmentation (WSSS) employs weak supervision, such as image-level labels, to train the segmentation model. Despite the impressive achievement in recent WSSS methods, we identify that introducing weak labels with high mean Intersection of Union (mIoU) does not guarantee high segmentation performance. Existing studies have emphasized the importance of prioritizing precision and reducing noise to improve overall performance. In the same vein, we propose ORANDNet, an advanced ensemble approach tailored for WSSS. ORANDNet combines Class Activation Maps (CAMs) from two dif"},"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":"2406.19638","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-28T03:58:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c6537e00e57501afd8b53ef1d8f6ab565a90370c760131c34c228c3b4b689fe1","abstract_canon_sha256":"72d6982d28b5c358911d2f214aebb6918cc4d5c7fc17c63aa2eb4d2d7dbd0149"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:37:42.933668Z","signature_b64":"8bNPv8VfwhQv1DZHk9Vq2zUTCF+vzJXEcddE0TW2NRLmlfNgmba3wOR8/g+yUT5SkSAByiq38uzUZPBiyCnKBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68c204637a0c942b8edda954b7b002ae949319f9a776635a18f9161ba4a8114a","last_reissued_at":"2026-07-05T08:37:42.933245Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:37:42.933245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Precision matters: Precision-aware ensemble for weakly supervised semantic segmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hyunjung Shim, Junsung Park","submitted_at":"2024-06-28T03:58:02Z","abstract_excerpt":"Weakly Supervised Semantic Segmentation (WSSS) employs weak supervision, such as image-level labels, to train the segmentation model. Despite the impressive achievement in recent WSSS methods, we identify that introducing weak labels with high mean Intersection of Union (mIoU) does not guarantee high segmentation performance. Existing studies have emphasized the importance of prioritizing precision and reducing noise to improve overall performance. In the same vein, we propose ORANDNet, an advanced ensemble approach tailored for WSSS. ORANDNet combines Class Activation Maps (CAMs) from two dif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.19638","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/2406.19638/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":"2406.19638","created_at":"2026-07-05T08:37:42.933294+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.19638v1","created_at":"2026-07-05T08:37:42.933294+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.19638","created_at":"2026-07-05T08:37:42.933294+00:00"},{"alias_kind":"pith_short_12","alias_value":"NDBAIY32BSKC","created_at":"2026-07-05T08:37:42.933294+00:00"},{"alias_kind":"pith_short_16","alias_value":"NDBAIY32BSKCXDW5","created_at":"2026-07-05T08:37:42.933294+00:00"},{"alias_kind":"pith_short_8","alias_value":"NDBAIY32","created_at":"2026-07-05T08:37:42.933294+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.21959","citing_title":"Mitigating Spurious Correlations in Weakly Supervised Semantic Segmentation via Cross-architecture Consistency Regularization","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NDBAIY32BSKCXDW5VFKLPMACV2","json":"https://pith.science/pith/NDBAIY32BSKCXDW5VFKLPMACV2.json","graph_json":"https://pith.science/api/pith-number/NDBAIY32BSKCXDW5VFKLPMACV2/graph.json","events_json":"https://pith.science/api/pith-number/NDBAIY32BSKCXDW5VFKLPMACV2/events.json","paper":"https://pith.science/paper/NDBAIY32"},"agent_actions":{"view_html":"https://pith.science/pith/NDBAIY32BSKCXDW5VFKLPMACV2","download_json":"https://pith.science/pith/NDBAIY32BSKCXDW5VFKLPMACV2.json","view_paper":"https://pith.science/paper/NDBAIY32","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.19638&json=true","fetch_graph":"https://pith.science/api/pith-number/NDBAIY32BSKCXDW5VFKLPMACV2/graph.json","fetch_events":"https://pith.science/api/pith-number/NDBAIY32BSKCXDW5VFKLPMACV2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NDBAIY32BSKCXDW5VFKLPMACV2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NDBAIY32BSKCXDW5VFKLPMACV2/action/storage_attestation","attest_author":"https://pith.science/pith/NDBAIY32BSKCXDW5VFKLPMACV2/action/author_attestation","sign_citation":"https://pith.science/pith/NDBAIY32BSKCXDW5VFKLPMACV2/action/citation_signature","submit_replication":"https://pith.science/pith/NDBAIY32BSKCXDW5VFKLPMACV2/action/replication_record"}},"created_at":"2026-07-05T08:37:42.933294+00:00","updated_at":"2026-07-05T08:37:42.933294+00:00"}