{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RBGVBPCHVKZTL5P3CPQHGYPNIF","short_pith_number":"pith:RBGVBPCH","schema_version":"1.0","canonical_sha256":"884d50bc47aab335f5fb13e07361ed4172eb699e2025f235b954573ab02b8670","source":{"kind":"arxiv","id":"2304.13455","version":4},"attestation_state":"computed","paper":{"title":"From Chaos Comes Order: Ordering Event Representations for Object Recognition and Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Daniel Gehrig, Davide Scaramuzza, Mathias Gehrig, Nikola Zubi\\'c","submitted_at":"2023-04-26T11:27:34Z","abstract_excerpt":"Today, state-of-the-art deep neural networks that process events first convert them into dense, grid-like input representations before using an off-the-shelf network. However, selecting the appropriate representation for the task traditionally requires training a neural network for each representation and selecting the best one based on the validation score, which is very time-consuming. This work eliminates this bottleneck by selecting representations based on the Gromov-Wasserstein Discrepancy (GWD) between raw events and their representation. It is about 200 times faster to compute than tra"},"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":"2304.13455","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-26T11:27:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"44de63e3fd0f39af426df42b5c63de234491671424e84b080bfd0b898e075622","abstract_canon_sha256":"810c72f664086eb167d83d13dc9ffbb063a239bb21786b9efad01fe24ebe7d36"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:46:22.171979Z","signature_b64":"KmjompW7QZT1JT0Li4SQJYjn/3ZKMNDVrprwNWR/FDh+/A2IC8ocjcJ4maDm7LHl/FsDeLds9op3wCzFwPqyBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"884d50bc47aab335f5fb13e07361ed4172eb699e2025f235b954573ab02b8670","last_reissued_at":"2026-07-05T06:46:22.171443Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:46:22.171443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Chaos Comes Order: Ordering Event Representations for Object Recognition and Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Daniel Gehrig, Davide Scaramuzza, Mathias Gehrig, Nikola Zubi\\'c","submitted_at":"2023-04-26T11:27:34Z","abstract_excerpt":"Today, state-of-the-art deep neural networks that process events first convert them into dense, grid-like input representations before using an off-the-shelf network. However, selecting the appropriate representation for the task traditionally requires training a neural network for each representation and selecting the best one based on the validation score, which is very time-consuming. This work eliminates this bottleneck by selecting representations based on the Gromov-Wasserstein Discrepancy (GWD) between raw events and their representation. It is about 200 times faster to compute than tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.13455","kind":"arxiv","version":4},"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/2304.13455/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":"2304.13455","created_at":"2026-07-05T06:46:22.171499+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.13455v4","created_at":"2026-07-05T06:46:22.171499+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.13455","created_at":"2026-07-05T06:46:22.171499+00:00"},{"alias_kind":"pith_short_12","alias_value":"RBGVBPCHVKZT","created_at":"2026-07-05T06:46:22.171499+00:00"},{"alias_kind":"pith_short_16","alias_value":"RBGVBPCHVKZTL5P3","created_at":"2026-07-05T06:46:22.171499+00:00"},{"alias_kind":"pith_short_8","alias_value":"RBGVBPCH","created_at":"2026-07-05T06:46:22.171499+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.21187","citing_title":"Making Every Event Count: Balancing Data Efficiency and Accuracy in Event Camera Subsampling","ref_index":49,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RBGVBPCHVKZTL5P3CPQHGYPNIF","json":"https://pith.science/pith/RBGVBPCHVKZTL5P3CPQHGYPNIF.json","graph_json":"https://pith.science/api/pith-number/RBGVBPCHVKZTL5P3CPQHGYPNIF/graph.json","events_json":"https://pith.science/api/pith-number/RBGVBPCHVKZTL5P3CPQHGYPNIF/events.json","paper":"https://pith.science/paper/RBGVBPCH"},"agent_actions":{"view_html":"https://pith.science/pith/RBGVBPCHVKZTL5P3CPQHGYPNIF","download_json":"https://pith.science/pith/RBGVBPCHVKZTL5P3CPQHGYPNIF.json","view_paper":"https://pith.science/paper/RBGVBPCH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.13455&json=true","fetch_graph":"https://pith.science/api/pith-number/RBGVBPCHVKZTL5P3CPQHGYPNIF/graph.json","fetch_events":"https://pith.science/api/pith-number/RBGVBPCHVKZTL5P3CPQHGYPNIF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RBGVBPCHVKZTL5P3CPQHGYPNIF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RBGVBPCHVKZTL5P3CPQHGYPNIF/action/storage_attestation","attest_author":"https://pith.science/pith/RBGVBPCHVKZTL5P3CPQHGYPNIF/action/author_attestation","sign_citation":"https://pith.science/pith/RBGVBPCHVKZTL5P3CPQHGYPNIF/action/citation_signature","submit_replication":"https://pith.science/pith/RBGVBPCHVKZTL5P3CPQHGYPNIF/action/replication_record"}},"created_at":"2026-07-05T06:46:22.171499+00:00","updated_at":"2026-07-05T06:46:22.171499+00:00"}