{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JMCHHK3JCXFQ6UONAIWY3HML6D","short_pith_number":"pith:JMCHHK3J","schema_version":"1.0","canonical_sha256":"4b0473ab6915cb0f51cd022d8d9d8bf0feb0a1e35ddb5483315a46284b6db863","source":{"kind":"arxiv","id":"2502.18202","version":1},"attestation_state":"computed","paper":{"title":"DenoMAE2.0: Improving Denoising Masked Autoencoders by Classifying Local Patches","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Atik Faysal, Huaxia Wang, Mohammad Rostami, Nikhil Muralidhar, Reihaneh Gh. Roshan, Taha Boushine","submitted_at":"2025-02-25T13:41:56Z","abstract_excerpt":"We introduce DenoMAE2.0, an enhanced denoising masked autoencoder that integrates a local patch classification objective alongside traditional reconstruction loss to improve representation learning and robustness. Unlike conventional Masked Autoencoders (MAE), which focus solely on reconstructing missing inputs, DenoMAE2.0 introduces position-aware classification of unmasked patches, enabling the model to capture fine-grained local features while maintaining global coherence. This dual-objective approach is particularly beneficial in semi-supervised learning for wireless communication, where h"},"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":"2502.18202","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-25T13:41:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"13c083a7c0334034b5b5a86fbb0a5a70e9b77ca2a07422247f545b376c020f2a","abstract_canon_sha256":"96505d160984db0d8ca6957c346e13b82291a4132d320ee5e3fe7ccf07a396fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:19:50.496278Z","signature_b64":"HXcmIpXdmYwZXdTZcDiu3Y/BlHTxAYMaZgtpY5rEwWhiw8xVwjuwV6L4RZckJBnl5wBE/ok2uO3/wAxW/VeZDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b0473ab6915cb0f51cd022d8d9d8bf0feb0a1e35ddb5483315a46284b6db863","last_reissued_at":"2026-07-05T10:19:50.495857Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:19:50.495857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DenoMAE2.0: Improving Denoising Masked Autoencoders by Classifying Local Patches","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Atik Faysal, Huaxia Wang, Mohammad Rostami, Nikhil Muralidhar, Reihaneh Gh. Roshan, Taha Boushine","submitted_at":"2025-02-25T13:41:56Z","abstract_excerpt":"We introduce DenoMAE2.0, an enhanced denoising masked autoencoder that integrates a local patch classification objective alongside traditional reconstruction loss to improve representation learning and robustness. Unlike conventional Masked Autoencoders (MAE), which focus solely on reconstructing missing inputs, DenoMAE2.0 introduces position-aware classification of unmasked patches, enabling the model to capture fine-grained local features while maintaining global coherence. This dual-objective approach is particularly beneficial in semi-supervised learning for wireless communication, where h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.18202","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/2502.18202/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":"2502.18202","created_at":"2026-07-05T10:19:50.495915+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.18202v1","created_at":"2026-07-05T10:19:50.495915+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.18202","created_at":"2026-07-05T10:19:50.495915+00:00"},{"alias_kind":"pith_short_12","alias_value":"JMCHHK3JCXFQ","created_at":"2026-07-05T10:19:50.495915+00:00"},{"alias_kind":"pith_short_16","alias_value":"JMCHHK3JCXFQ6UON","created_at":"2026-07-05T10:19:50.495915+00:00"},{"alias_kind":"pith_short_8","alias_value":"JMCHHK3J","created_at":"2026-07-05T10:19:50.495915+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/JMCHHK3JCXFQ6UONAIWY3HML6D","json":"https://pith.science/pith/JMCHHK3JCXFQ6UONAIWY3HML6D.json","graph_json":"https://pith.science/api/pith-number/JMCHHK3JCXFQ6UONAIWY3HML6D/graph.json","events_json":"https://pith.science/api/pith-number/JMCHHK3JCXFQ6UONAIWY3HML6D/events.json","paper":"https://pith.science/paper/JMCHHK3J"},"agent_actions":{"view_html":"https://pith.science/pith/JMCHHK3JCXFQ6UONAIWY3HML6D","download_json":"https://pith.science/pith/JMCHHK3JCXFQ6UONAIWY3HML6D.json","view_paper":"https://pith.science/paper/JMCHHK3J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.18202&json=true","fetch_graph":"https://pith.science/api/pith-number/JMCHHK3JCXFQ6UONAIWY3HML6D/graph.json","fetch_events":"https://pith.science/api/pith-number/JMCHHK3JCXFQ6UONAIWY3HML6D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JMCHHK3JCXFQ6UONAIWY3HML6D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JMCHHK3JCXFQ6UONAIWY3HML6D/action/storage_attestation","attest_author":"https://pith.science/pith/JMCHHK3JCXFQ6UONAIWY3HML6D/action/author_attestation","sign_citation":"https://pith.science/pith/JMCHHK3JCXFQ6UONAIWY3HML6D/action/citation_signature","submit_replication":"https://pith.science/pith/JMCHHK3JCXFQ6UONAIWY3HML6D/action/replication_record"}},"created_at":"2026-07-05T10:19:50.495915+00:00","updated_at":"2026-07-05T10:19:50.495915+00:00"}