{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EPZCR54PW7HVTLM2K4PJZWSHGW","short_pith_number":"pith:EPZCR54P","schema_version":"1.0","canonical_sha256":"23f228f78fb7cf59ad9a571e9cda473583b6c66e1b8789d38c1f399255a2a1e8","source":{"kind":"arxiv","id":"2302.09561","version":1},"attestation_state":"computed","paper":{"title":"TAX: Tendency-and-Assignment Explainer for Semantic Segmentation with Multi-Annotators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Fu-En Yang, Yuan-Chia Cheng, Yu-Chiang Frank Wang, Zu-Yun Shiau","submitted_at":"2023-02-19T12:40:22Z","abstract_excerpt":"To understand how deep neural networks perform classification predictions, recent research attention has been focusing on developing techniques to offer desirable explanations. However, most existing methods cannot be easily applied for semantic segmentation; moreover, they are not designed to offer interpretability under the multi-annotator setting. Instead of viewing ground-truth pixel-level labels annotated by a single annotator with consistent labeling tendency, we aim at providing interpretable semantic segmentation and answer two critical yet practical questions: \"who\" contributes to 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":"2302.09561","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-19T12:40:22Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c430ecb9100a2b1122f1837b5c8af08906bf308810bab1f3530157771a92aa2e","abstract_canon_sha256":"64498223d709d8e990a333628abcb99e1cdfce2fa83c9745203ecce343221f34"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:43:27.378681Z","signature_b64":"tLHCrr3vGsNKjkgm7FTGKWra/DaEn782fNQym6wnVNdaLS0xTT0hu90lykSwjFTNFmVR2hTeLRXKEQhuDLzPBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23f228f78fb7cf59ad9a571e9cda473583b6c66e1b8789d38c1f399255a2a1e8","last_reissued_at":"2026-07-05T05:43:27.378209Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:43:27.378209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TAX: Tendency-and-Assignment Explainer for Semantic Segmentation with Multi-Annotators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Fu-En Yang, Yuan-Chia Cheng, Yu-Chiang Frank Wang, Zu-Yun Shiau","submitted_at":"2023-02-19T12:40:22Z","abstract_excerpt":"To understand how deep neural networks perform classification predictions, recent research attention has been focusing on developing techniques to offer desirable explanations. However, most existing methods cannot be easily applied for semantic segmentation; moreover, they are not designed to offer interpretability under the multi-annotator setting. Instead of viewing ground-truth pixel-level labels annotated by a single annotator with consistent labeling tendency, we aim at providing interpretable semantic segmentation and answer two critical yet practical questions: \"who\" contributes to the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.09561","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/2302.09561/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":"2302.09561","created_at":"2026-07-05T05:43:27.378278+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.09561v1","created_at":"2026-07-05T05:43:27.378278+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.09561","created_at":"2026-07-05T05:43:27.378278+00:00"},{"alias_kind":"pith_short_12","alias_value":"EPZCR54PW7HV","created_at":"2026-07-05T05:43:27.378278+00:00"},{"alias_kind":"pith_short_16","alias_value":"EPZCR54PW7HVTLM2","created_at":"2026-07-05T05:43:27.378278+00:00"},{"alias_kind":"pith_short_8","alias_value":"EPZCR54P","created_at":"2026-07-05T05:43:27.378278+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08210","citing_title":"Harmonized Feature Conditioning and Frequency-Prompt Personalization for Multi-Rater Medical Segmentation","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EPZCR54PW7HVTLM2K4PJZWSHGW","json":"https://pith.science/pith/EPZCR54PW7HVTLM2K4PJZWSHGW.json","graph_json":"https://pith.science/api/pith-number/EPZCR54PW7HVTLM2K4PJZWSHGW/graph.json","events_json":"https://pith.science/api/pith-number/EPZCR54PW7HVTLM2K4PJZWSHGW/events.json","paper":"https://pith.science/paper/EPZCR54P"},"agent_actions":{"view_html":"https://pith.science/pith/EPZCR54PW7HVTLM2K4PJZWSHGW","download_json":"https://pith.science/pith/EPZCR54PW7HVTLM2K4PJZWSHGW.json","view_paper":"https://pith.science/paper/EPZCR54P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.09561&json=true","fetch_graph":"https://pith.science/api/pith-number/EPZCR54PW7HVTLM2K4PJZWSHGW/graph.json","fetch_events":"https://pith.science/api/pith-number/EPZCR54PW7HVTLM2K4PJZWSHGW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EPZCR54PW7HVTLM2K4PJZWSHGW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EPZCR54PW7HVTLM2K4PJZWSHGW/action/storage_attestation","attest_author":"https://pith.science/pith/EPZCR54PW7HVTLM2K4PJZWSHGW/action/author_attestation","sign_citation":"https://pith.science/pith/EPZCR54PW7HVTLM2K4PJZWSHGW/action/citation_signature","submit_replication":"https://pith.science/pith/EPZCR54PW7HVTLM2K4PJZWSHGW/action/replication_record"}},"created_at":"2026-07-05T05:43:27.378278+00:00","updated_at":"2026-07-05T05:43:27.378278+00:00"}