{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:K5ZOU2TZPC43GTEDDF3BGK4KYX","short_pith_number":"pith:K5ZOU2TZ","schema_version":"1.0","canonical_sha256":"5772ea6a7978b9b34c831976132b8ac5f4e39f57d192d5146c5f50c53ef734ba","source":{"kind":"arxiv","id":"2311.05770","version":1},"attestation_state":"computed","paper":{"title":"PolyMaX: General Dense Prediction with Mask Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Astuti Sharma, Hartwig Adam, Huisheng Wang, Kimberly Wilber, Liang-Chieh Chen, Liangzhe Yuan, Mikhail Sirotenko, Siyuan Qiao, Stephanie Debats, Xiuye Gu, Xuan Yang","submitted_at":"2023-11-09T22:29:21Z","abstract_excerpt":"Dense prediction tasks, such as semantic segmentation, depth estimation, and surface normal prediction, can be easily formulated as per-pixel classification (discrete outputs) or regression (continuous outputs). This per-pixel prediction paradigm has remained popular due to the prevalence of fully convolutional networks. However, on the recent frontier of segmentation task, the community has been witnessing a shift of paradigm from per-pixel prediction to cluster-prediction with the emergence of transformer architectures, particularly the mask transformers, which directly predicts a label for "},"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":"2311.05770","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-09T22:29:21Z","cross_cats_sorted":[],"title_canon_sha256":"8d835dd593fca8080329f30897ef7182fa215d6c961f825b8e14b16248a97cba","abstract_canon_sha256":"91af0cf5373d1ff48fe79a678a86f3662d3fa64b86ad58f3aeebce1d55592cdc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:11:22.577002Z","signature_b64":"5CVP+z3cr7Wox/nU53WYCMszgsE/T8nkDUVI1q/UD3yGUjJ9HaXZfgxD/CXEta87Qe5aJvOOxM1ug5k6dqs6Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5772ea6a7978b9b34c831976132b8ac5f4e39f57d192d5146c5f50c53ef734ba","last_reissued_at":"2026-07-05T07:11:22.576528Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:11:22.576528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PolyMaX: General Dense Prediction with Mask Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Astuti Sharma, Hartwig Adam, Huisheng Wang, Kimberly Wilber, Liang-Chieh Chen, Liangzhe Yuan, Mikhail Sirotenko, Siyuan Qiao, Stephanie Debats, Xiuye Gu, Xuan Yang","submitted_at":"2023-11-09T22:29:21Z","abstract_excerpt":"Dense prediction tasks, such as semantic segmentation, depth estimation, and surface normal prediction, can be easily formulated as per-pixel classification (discrete outputs) or regression (continuous outputs). This per-pixel prediction paradigm has remained popular due to the prevalence of fully convolutional networks. However, on the recent frontier of segmentation task, the community has been witnessing a shift of paradigm from per-pixel prediction to cluster-prediction with the emergence of transformer architectures, particularly the mask transformers, which directly predicts a label for "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.05770","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/2311.05770/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":"2311.05770","created_at":"2026-07-05T07:11:22.576587+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.05770v1","created_at":"2026-07-05T07:11:22.576587+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.05770","created_at":"2026-07-05T07:11:22.576587+00:00"},{"alias_kind":"pith_short_12","alias_value":"K5ZOU2TZPC43","created_at":"2026-07-05T07:11:22.576587+00:00"},{"alias_kind":"pith_short_16","alias_value":"K5ZOU2TZPC43GTED","created_at":"2026-07-05T07:11:22.576587+00:00"},{"alias_kind":"pith_short_8","alias_value":"K5ZOU2TZ","created_at":"2026-07-05T07:11:22.576587+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/K5ZOU2TZPC43GTEDDF3BGK4KYX","json":"https://pith.science/pith/K5ZOU2TZPC43GTEDDF3BGK4KYX.json","graph_json":"https://pith.science/api/pith-number/K5ZOU2TZPC43GTEDDF3BGK4KYX/graph.json","events_json":"https://pith.science/api/pith-number/K5ZOU2TZPC43GTEDDF3BGK4KYX/events.json","paper":"https://pith.science/paper/K5ZOU2TZ"},"agent_actions":{"view_html":"https://pith.science/pith/K5ZOU2TZPC43GTEDDF3BGK4KYX","download_json":"https://pith.science/pith/K5ZOU2TZPC43GTEDDF3BGK4KYX.json","view_paper":"https://pith.science/paper/K5ZOU2TZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.05770&json=true","fetch_graph":"https://pith.science/api/pith-number/K5ZOU2TZPC43GTEDDF3BGK4KYX/graph.json","fetch_events":"https://pith.science/api/pith-number/K5ZOU2TZPC43GTEDDF3BGK4KYX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K5ZOU2TZPC43GTEDDF3BGK4KYX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K5ZOU2TZPC43GTEDDF3BGK4KYX/action/storage_attestation","attest_author":"https://pith.science/pith/K5ZOU2TZPC43GTEDDF3BGK4KYX/action/author_attestation","sign_citation":"https://pith.science/pith/K5ZOU2TZPC43GTEDDF3BGK4KYX/action/citation_signature","submit_replication":"https://pith.science/pith/K5ZOU2TZPC43GTEDDF3BGK4KYX/action/replication_record"}},"created_at":"2026-07-05T07:11:22.576587+00:00","updated_at":"2026-07-05T07:11:22.576587+00:00"}