{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:WINLJYF5OGG7BKJRO7U6J4CSY7","short_pith_number":"pith:WINLJYF5","schema_version":"1.0","canonical_sha256":"b21ab4e0bd718df0a93177e9e4f052c7d5d9e8042b3f08c7317900ad0c1e7b3e","source":{"kind":"arxiv","id":"2106.09748","version":1},"attestation_state":"computed","paper":{"title":"DeepLab2: A TensorFlow Library for Deep Labeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan L. Yuille, Dahun Kim, Daniel Cremers, Florian Schroff, Hartwig Adam, Huiyu Wang, Jun Xie, Laura Leal-Taixe, Liang-Chieh Chen, Liangzhe Yuan, Mark Weber, Maxwell D. Collins, Qihang Yu, Siyuan Qiao, Yukun Zhu","submitted_at":"2021-06-17T18:04:53Z","abstract_excerpt":"DeepLab2 is a TensorFlow library for deep labeling, aiming to provide a state-of-the-art and easy-to-use TensorFlow codebase for general dense pixel prediction problems in computer vision. DeepLab2 includes all our recently developed DeepLab model variants with pretrained checkpoints as well as model training and evaluation code, allowing the community to reproduce and further improve upon the state-of-art systems. To showcase the effectiveness of DeepLab2, our Panoptic-DeepLab employing Axial-SWideRNet as network backbone achieves 68.0% PQ or 83.5% mIoU on Cityscaspes validation set, with onl"},"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":"2106.09748","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-17T18:04:53Z","cross_cats_sorted":[],"title_canon_sha256":"c4cbc5f6d840eccb7599700c6d261519483081636bfb6d43a5135506893f5e7e","abstract_canon_sha256":"47f08e414c2dd733c5c435d2f7559c31a35127f977943abd7fe347174448f379"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:50:20.301124Z","signature_b64":"27D5F4ulRK0viNoMzDOfJcQ4+w5DOxmw2uO0Ky/R29BpeLOJok6afN/hYrwURQLGyzunbfkGxe1UGCsBSM4rDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b21ab4e0bd718df0a93177e9e4f052c7d5d9e8042b3f08c7317900ad0c1e7b3e","last_reissued_at":"2026-07-05T02:50:20.300642Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:50:20.300642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeepLab2: A TensorFlow Library for Deep Labeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan L. Yuille, Dahun Kim, Daniel Cremers, Florian Schroff, Hartwig Adam, Huiyu Wang, Jun Xie, Laura Leal-Taixe, Liang-Chieh Chen, Liangzhe Yuan, Mark Weber, Maxwell D. Collins, Qihang Yu, Siyuan Qiao, Yukun Zhu","submitted_at":"2021-06-17T18:04:53Z","abstract_excerpt":"DeepLab2 is a TensorFlow library for deep labeling, aiming to provide a state-of-the-art and easy-to-use TensorFlow codebase for general dense pixel prediction problems in computer vision. DeepLab2 includes all our recently developed DeepLab model variants with pretrained checkpoints as well as model training and evaluation code, allowing the community to reproduce and further improve upon the state-of-art systems. To showcase the effectiveness of DeepLab2, our Panoptic-DeepLab employing Axial-SWideRNet as network backbone achieves 68.0% PQ or 83.5% mIoU on Cityscaspes validation set, with onl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.09748","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/2106.09748/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":"2106.09748","created_at":"2026-07-05T02:50:20.300703+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.09748v1","created_at":"2026-07-05T02:50:20.300703+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.09748","created_at":"2026-07-05T02:50:20.300703+00:00"},{"alias_kind":"pith_short_12","alias_value":"WINLJYF5OGG7","created_at":"2026-07-05T02:50:20.300703+00:00"},{"alias_kind":"pith_short_16","alias_value":"WINLJYF5OGG7BKJR","created_at":"2026-07-05T02:50:20.300703+00:00"},{"alias_kind":"pith_short_8","alias_value":"WINLJYF5","created_at":"2026-07-05T02:50:20.300703+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08824","citing_title":"HairGPT: Strand-as-Language Autoregressive Modeling for Realistic 3D Hairstyle Synthesis","ref_index":217,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WINLJYF5OGG7BKJRO7U6J4CSY7","json":"https://pith.science/pith/WINLJYF5OGG7BKJRO7U6J4CSY7.json","graph_json":"https://pith.science/api/pith-number/WINLJYF5OGG7BKJRO7U6J4CSY7/graph.json","events_json":"https://pith.science/api/pith-number/WINLJYF5OGG7BKJRO7U6J4CSY7/events.json","paper":"https://pith.science/paper/WINLJYF5"},"agent_actions":{"view_html":"https://pith.science/pith/WINLJYF5OGG7BKJRO7U6J4CSY7","download_json":"https://pith.science/pith/WINLJYF5OGG7BKJRO7U6J4CSY7.json","view_paper":"https://pith.science/paper/WINLJYF5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.09748&json=true","fetch_graph":"https://pith.science/api/pith-number/WINLJYF5OGG7BKJRO7U6J4CSY7/graph.json","fetch_events":"https://pith.science/api/pith-number/WINLJYF5OGG7BKJRO7U6J4CSY7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WINLJYF5OGG7BKJRO7U6J4CSY7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WINLJYF5OGG7BKJRO7U6J4CSY7/action/storage_attestation","attest_author":"https://pith.science/pith/WINLJYF5OGG7BKJRO7U6J4CSY7/action/author_attestation","sign_citation":"https://pith.science/pith/WINLJYF5OGG7BKJRO7U6J4CSY7/action/citation_signature","submit_replication":"https://pith.science/pith/WINLJYF5OGG7BKJRO7U6J4CSY7/action/replication_record"}},"created_at":"2026-07-05T02:50:20.300703+00:00","updated_at":"2026-07-05T02:50:20.300703+00:00"}