{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2DONSQVDOWDXUJM3ZACE5LN6DX","short_pith_number":"pith:2DONSQVD","schema_version":"1.0","canonical_sha256":"d0dcd942a375877a259bc8044eadbe1de65d3e7c896921e3f652fd564c156f64","source":{"kind":"arxiv","id":"2308.03135","version":6},"attestation_state":"computed","paper":{"title":"EventBind: Learning a Unified Representation to Bind Them All for Event-based Open-world Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiazhou Zhou, Lin Wang, Xu Zheng, Yuanhuiyi Lyu","submitted_at":"2023-08-06T15:05:42Z","abstract_excerpt":"In this paper, we propose EventBind, a novel and effective framework that unleashes the potential of vision-language models (VLMs) for event-based recognition to compensate for the lack of large-scale event-based datasets. In particular, due to the distinct modality gap with the image-text data and the lack of large-scale datasets, learning a common representation space for images, texts, and events is non-trivial.Intuitively, we need to address two key challenges: 1) how to generalize CLIP's visual encoder to event data while fully leveraging events' unique properties, e.g., sparsity and high"},"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":"2308.03135","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-06T15:05:42Z","cross_cats_sorted":[],"title_canon_sha256":"95fee443de35591dd4b2c6e293b813552a6955d315884d4386b179027108dd4c","abstract_canon_sha256":"163949c1922e370e2484cdd184027e77e737c6bc3fbf2f298564885443d2e6f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:47:46.486441Z","signature_b64":"/5QtkcFDfVLWNhVZ9ac0ng9pQ3pnhyrm/6aNRAGqqYdfVe0V/CTxanleBdEHJdcvW7wuITn00H7iLtdqEcw5Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0dcd942a375877a259bc8044eadbe1de65d3e7c896921e3f652fd564c156f64","last_reissued_at":"2026-07-05T08:47:46.485924Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:47:46.485924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EventBind: Learning a Unified Representation to Bind Them All for Event-based Open-world Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiazhou Zhou, Lin Wang, Xu Zheng, Yuanhuiyi Lyu","submitted_at":"2023-08-06T15:05:42Z","abstract_excerpt":"In this paper, we propose EventBind, a novel and effective framework that unleashes the potential of vision-language models (VLMs) for event-based recognition to compensate for the lack of large-scale event-based datasets. In particular, due to the distinct modality gap with the image-text data and the lack of large-scale datasets, learning a common representation space for images, texts, and events is non-trivial.Intuitively, we need to address two key challenges: 1) how to generalize CLIP's visual encoder to event data while fully leveraging events' unique properties, e.g., sparsity and high"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.03135","kind":"arxiv","version":6},"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/2308.03135/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":"2308.03135","created_at":"2026-07-05T08:47:46.485994+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.03135v6","created_at":"2026-07-05T08:47:46.485994+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.03135","created_at":"2026-07-05T08:47:46.485994+00:00"},{"alias_kind":"pith_short_12","alias_value":"2DONSQVDOWDX","created_at":"2026-07-05T08:47:46.485994+00:00"},{"alias_kind":"pith_short_16","alias_value":"2DONSQVDOWDXUJM3","created_at":"2026-07-05T08:47:46.485994+00:00"},{"alias_kind":"pith_short_8","alias_value":"2DONSQVD","created_at":"2026-07-05T08:47:46.485994+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.18328","citing_title":"EventCrab: Harnessing Frame and Point Synergy for Event-based Action Recognition and Beyond","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2DONSQVDOWDXUJM3ZACE5LN6DX","json":"https://pith.science/pith/2DONSQVDOWDXUJM3ZACE5LN6DX.json","graph_json":"https://pith.science/api/pith-number/2DONSQVDOWDXUJM3ZACE5LN6DX/graph.json","events_json":"https://pith.science/api/pith-number/2DONSQVDOWDXUJM3ZACE5LN6DX/events.json","paper":"https://pith.science/paper/2DONSQVD"},"agent_actions":{"view_html":"https://pith.science/pith/2DONSQVDOWDXUJM3ZACE5LN6DX","download_json":"https://pith.science/pith/2DONSQVDOWDXUJM3ZACE5LN6DX.json","view_paper":"https://pith.science/paper/2DONSQVD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.03135&json=true","fetch_graph":"https://pith.science/api/pith-number/2DONSQVDOWDXUJM3ZACE5LN6DX/graph.json","fetch_events":"https://pith.science/api/pith-number/2DONSQVDOWDXUJM3ZACE5LN6DX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2DONSQVDOWDXUJM3ZACE5LN6DX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2DONSQVDOWDXUJM3ZACE5LN6DX/action/storage_attestation","attest_author":"https://pith.science/pith/2DONSQVDOWDXUJM3ZACE5LN6DX/action/author_attestation","sign_citation":"https://pith.science/pith/2DONSQVDOWDXUJM3ZACE5LN6DX/action/citation_signature","submit_replication":"https://pith.science/pith/2DONSQVDOWDXUJM3ZACE5LN6DX/action/replication_record"}},"created_at":"2026-07-05T08:47:46.485994+00:00","updated_at":"2026-07-05T08:47:46.485994+00:00"}