{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:LUFFF46JVGUWLFV5D64WP6EFVK","short_pith_number":"pith:LUFFF46J","schema_version":"1.0","canonical_sha256":"5d0a52f3c9a9a96596bd1fb967f885aa8abaea89d13fdecefffe817322825e7d","source":{"kind":"arxiv","id":"2103.13253","version":2},"attestation_state":"computed","paper":{"title":"Learning Versatile Neural Architectures by Propagating Network Codes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoyu Lu, Jingdong Wang, Linjie Yang, Mingyu Ding, Ping Luo, Yuqi Huo, Zhe Wang, Zhiwu Lu","submitted_at":"2021-03-24T15:20:38Z","abstract_excerpt":"This work explores how to design a single neural network capable of adapting to multiple heterogeneous vision tasks, such as image segmentation, 3D detection, and video recognition. This goal is challenging because both network architecture search (NAS) spaces and methods in different tasks are inconsistent. We solve this challenge from both sides. We first introduce a unified design space for multiple tasks and build a multitask NAS benchmark (NAS-Bench-MR) on many widely used datasets, including ImageNet, Cityscapes, KITTI, and HMDB51. We further propose Network Coding Propagation (NCP), whi"},"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":"2103.13253","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-24T15:20:38Z","cross_cats_sorted":[],"title_canon_sha256":"41a7cf38f418b7b3296f0d076947ba1364ddbeb3f737059e2444a38b2f674025","abstract_canon_sha256":"d38afbf67fa20bd528c9b5a71529f6d6122ca400895f31c01841e8eca8f6d28b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:57:53.843238Z","signature_b64":"e5PIUXTwf3N3lbKRRHJf0EdYXAOGkvS8WdTmCH2cAa4B+lKhs1NUx3cZvJNHoXCncJCaBR7Q8LzRJ0WV+e1JCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d0a52f3c9a9a96596bd1fb967f885aa8abaea89d13fdecefffe817322825e7d","last_reissued_at":"2026-07-05T03:57:53.842789Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:57:53.842789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Versatile Neural Architectures by Propagating Network Codes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoyu Lu, Jingdong Wang, Linjie Yang, Mingyu Ding, Ping Luo, Yuqi Huo, Zhe Wang, Zhiwu Lu","submitted_at":"2021-03-24T15:20:38Z","abstract_excerpt":"This work explores how to design a single neural network capable of adapting to multiple heterogeneous vision tasks, such as image segmentation, 3D detection, and video recognition. This goal is challenging because both network architecture search (NAS) spaces and methods in different tasks are inconsistent. We solve this challenge from both sides. We first introduce a unified design space for multiple tasks and build a multitask NAS benchmark (NAS-Bench-MR) on many widely used datasets, including ImageNet, Cityscapes, KITTI, and HMDB51. We further propose Network Coding Propagation (NCP), whi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.13253","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/2103.13253/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":"2103.13253","created_at":"2026-07-05T03:57:53.842845+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.13253v2","created_at":"2026-07-05T03:57:53.842845+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.13253","created_at":"2026-07-05T03:57:53.842845+00:00"},{"alias_kind":"pith_short_12","alias_value":"LUFFF46JVGUW","created_at":"2026-07-05T03:57:53.842845+00:00"},{"alias_kind":"pith_short_16","alias_value":"LUFFF46JVGUWLFV5","created_at":"2026-07-05T03:57:53.842845+00:00"},{"alias_kind":"pith_short_8","alias_value":"LUFFF46J","created_at":"2026-07-05T03:57:53.842845+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2402.13228","citing_title":"Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive","ref_index":256,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LUFFF46JVGUWLFV5D64WP6EFVK","json":"https://pith.science/pith/LUFFF46JVGUWLFV5D64WP6EFVK.json","graph_json":"https://pith.science/api/pith-number/LUFFF46JVGUWLFV5D64WP6EFVK/graph.json","events_json":"https://pith.science/api/pith-number/LUFFF46JVGUWLFV5D64WP6EFVK/events.json","paper":"https://pith.science/paper/LUFFF46J"},"agent_actions":{"view_html":"https://pith.science/pith/LUFFF46JVGUWLFV5D64WP6EFVK","download_json":"https://pith.science/pith/LUFFF46JVGUWLFV5D64WP6EFVK.json","view_paper":"https://pith.science/paper/LUFFF46J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.13253&json=true","fetch_graph":"https://pith.science/api/pith-number/LUFFF46JVGUWLFV5D64WP6EFVK/graph.json","fetch_events":"https://pith.science/api/pith-number/LUFFF46JVGUWLFV5D64WP6EFVK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LUFFF46JVGUWLFV5D64WP6EFVK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LUFFF46JVGUWLFV5D64WP6EFVK/action/storage_attestation","attest_author":"https://pith.science/pith/LUFFF46JVGUWLFV5D64WP6EFVK/action/author_attestation","sign_citation":"https://pith.science/pith/LUFFF46JVGUWLFV5D64WP6EFVK/action/citation_signature","submit_replication":"https://pith.science/pith/LUFFF46JVGUWLFV5D64WP6EFVK/action/replication_record"}},"created_at":"2026-07-05T03:57:53.842845+00:00","updated_at":"2026-07-05T03:57:53.842845+00:00"}