{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:2CXNZYXSHK5ND5ONCTDIKK27FB","short_pith_number":"pith:2CXNZYXS","schema_version":"1.0","canonical_sha256":"d0aedce2f23abad1f5cd14c6852b5f2871dadc39610fc3c17eea4339fe4d8c0d","source":{"kind":"arxiv","id":"2106.05836","version":1},"attestation_state":"computed","paper":{"title":"EventDrop: data augmentation for event-based learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Fangwen Yu, Fuqiang Gu, Weicong Sng, Xuke Hu","submitted_at":"2021-06-07T11:53:14Z","abstract_excerpt":"The advantages of event-sensing over conventional sensors (e.g., higher dynamic range, lower time latency, and lower power consumption) have spurred research into machine learning for event data. Unsurprisingly, deep learning has emerged as a competitive methodology for learning with event sensors; in typical setups, discrete and asynchronous events are first converted into frame-like tensors on which standard deep networks can be applied. However, over-fitting remains a challenge, particularly since event datasets remain small relative to conventional datasets (e.g., ImageNet). In this paper,"},"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":"2106.05836","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-07T11:53:14Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"affab18940e6b01fea2b42d2b8120d83737fbe32c976b69ade9f212d676e1169","abstract_canon_sha256":"8c1b32685002446bae9eb8f3a44685a935697728abd4ffa23c02b2827a29f496"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:48:13.556140Z","signature_b64":"gtT9EnxQENgulrA6e0lKkd5jCtZxeOqfqueAIwR3S2h3Jd/XIfFyF7Q+UgFxLM1/hHFlA8NVUz9jmBqbp/HtBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0aedce2f23abad1f5cd14c6852b5f2871dadc39610fc3c17eea4339fe4d8c0d","last_reissued_at":"2026-07-05T02:48:13.555638Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:48:13.555638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EventDrop: data augmentation for event-based learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Fangwen Yu, Fuqiang Gu, Weicong Sng, Xuke Hu","submitted_at":"2021-06-07T11:53:14Z","abstract_excerpt":"The advantages of event-sensing over conventional sensors (e.g., higher dynamic range, lower time latency, and lower power consumption) have spurred research into machine learning for event data. Unsurprisingly, deep learning has emerged as a competitive methodology for learning with event sensors; in typical setups, discrete and asynchronous events are first converted into frame-like tensors on which standard deep networks can be applied. However, over-fitting remains a challenge, particularly since event datasets remain small relative to conventional datasets (e.g., ImageNet). In this paper,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.05836","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/2106.05836/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":"2106.05836","created_at":"2026-07-05T02:48:13.555714+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.05836v1","created_at":"2026-07-05T02:48:13.555714+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.05836","created_at":"2026-07-05T02:48:13.555714+00:00"},{"alias_kind":"pith_short_12","alias_value":"2CXNZYXSHK5N","created_at":"2026-07-05T02:48:13.555714+00:00"},{"alias_kind":"pith_short_16","alias_value":"2CXNZYXSHK5ND5ON","created_at":"2026-07-05T02:48:13.555714+00:00"},{"alias_kind":"pith_short_8","alias_value":"2CXNZYXS","created_at":"2026-07-05T02:48:13.555714+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/2CXNZYXSHK5ND5ONCTDIKK27FB","json":"https://pith.science/pith/2CXNZYXSHK5ND5ONCTDIKK27FB.json","graph_json":"https://pith.science/api/pith-number/2CXNZYXSHK5ND5ONCTDIKK27FB/graph.json","events_json":"https://pith.science/api/pith-number/2CXNZYXSHK5ND5ONCTDIKK27FB/events.json","paper":"https://pith.science/paper/2CXNZYXS"},"agent_actions":{"view_html":"https://pith.science/pith/2CXNZYXSHK5ND5ONCTDIKK27FB","download_json":"https://pith.science/pith/2CXNZYXSHK5ND5ONCTDIKK27FB.json","view_paper":"https://pith.science/paper/2CXNZYXS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.05836&json=true","fetch_graph":"https://pith.science/api/pith-number/2CXNZYXSHK5ND5ONCTDIKK27FB/graph.json","fetch_events":"https://pith.science/api/pith-number/2CXNZYXSHK5ND5ONCTDIKK27FB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2CXNZYXSHK5ND5ONCTDIKK27FB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2CXNZYXSHK5ND5ONCTDIKK27FB/action/storage_attestation","attest_author":"https://pith.science/pith/2CXNZYXSHK5ND5ONCTDIKK27FB/action/author_attestation","sign_citation":"https://pith.science/pith/2CXNZYXSHK5ND5ONCTDIKK27FB/action/citation_signature","submit_replication":"https://pith.science/pith/2CXNZYXSHK5ND5ONCTDIKK27FB/action/replication_record"}},"created_at":"2026-07-05T02:48:13.555714+00:00","updated_at":"2026-07-05T02:48:13.555714+00:00"}