{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4LTGULOB5KS7DJBIBV7ZLYPB2M","short_pith_number":"pith:4LTGULOB","schema_version":"1.0","canonical_sha256":"e2e66a2dc1eaa5f1a4280d7f95e1e1d3120617df659e4c458480c4da0d329818","source":{"kind":"arxiv","id":"2410.10783","version":3},"attestation_state":"computed","paper":{"title":"LiveXiv -- A Multi-Modal Live Benchmark Based on Arxiv Papers Content","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Assaf Arbelle, Felipe Maia Polo, Leonid Karlinsky, Leshem Chosen, Mikhail Yurochkin, M. Jehanzeb Mirza, Nimrod Shabtay, Raja Giryes, Sivan Doveh, Wei Lin, Yuekai Sun","submitted_at":"2024-10-14T17:51:23Z","abstract_excerpt":"The large-scale training of multi-modal models on data scraped from the web has shown outstanding utility in infusing these models with the required world knowledge to perform effectively on multiple downstream tasks. However, one downside of scraping data from the web can be the potential sacrifice of the benchmarks on which the abilities of these models are often evaluated. To safeguard against test data contamination and to truly test the abilities of these foundation models we propose LiveXiv: A scalable evolving live benchmark based on scientific ArXiv papers. LiveXiv accesses domain-spec"},"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":"2410.10783","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-14T17:51:23Z","cross_cats_sorted":[],"title_canon_sha256":"81d8cca5eec7d45d543f9b9b71dd26a8b0181208c062ff8bf9a8b3c4faff8edb","abstract_canon_sha256":"ba99886d084d51d75e896b5e3b596d90301b607ce2af66105f0baf94f47181ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:15.103077Z","signature_b64":"qxgXWtNtdpSjvhaxGLM1GS1FHhre7UUwRqtV0z2E2Sc3NEWhz8RqOCPhDyrTijLq+D8062CThQdV+atBiYh9AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2e66a2dc1eaa5f1a4280d7f95e1e1d3120617df659e4c458480c4da0d329818","last_reissued_at":"2026-07-05T10:52:15.102596Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:15.102596Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LiveXiv -- A Multi-Modal Live Benchmark Based on Arxiv Papers Content","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Assaf Arbelle, Felipe Maia Polo, Leonid Karlinsky, Leshem Chosen, Mikhail Yurochkin, M. Jehanzeb Mirza, Nimrod Shabtay, Raja Giryes, Sivan Doveh, Wei Lin, Yuekai Sun","submitted_at":"2024-10-14T17:51:23Z","abstract_excerpt":"The large-scale training of multi-modal models on data scraped from the web has shown outstanding utility in infusing these models with the required world knowledge to perform effectively on multiple downstream tasks. However, one downside of scraping data from the web can be the potential sacrifice of the benchmarks on which the abilities of these models are often evaluated. To safeguard against test data contamination and to truly test the abilities of these foundation models we propose LiveXiv: A scalable evolving live benchmark based on scientific ArXiv papers. LiveXiv accesses domain-spec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10783","kind":"arxiv","version":3},"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/2410.10783/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":"2410.10783","created_at":"2026-07-05T10:52:15.102649+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.10783v3","created_at":"2026-07-05T10:52:15.102649+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10783","created_at":"2026-07-05T10:52:15.102649+00:00"},{"alias_kind":"pith_short_12","alias_value":"4LTGULOB5KS7","created_at":"2026-07-05T10:52:15.102649+00:00"},{"alias_kind":"pith_short_16","alias_value":"4LTGULOB5KS7DJBI","created_at":"2026-07-05T10:52:15.102649+00:00"},{"alias_kind":"pith_short_8","alias_value":"4LTGULOB","created_at":"2026-07-05T10:52:15.102649+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.20025","citing_title":"Region-based Cluster Discrimination for Visual Representation Learning","ref_index":58,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4LTGULOB5KS7DJBIBV7ZLYPB2M","json":"https://pith.science/pith/4LTGULOB5KS7DJBIBV7ZLYPB2M.json","graph_json":"https://pith.science/api/pith-number/4LTGULOB5KS7DJBIBV7ZLYPB2M/graph.json","events_json":"https://pith.science/api/pith-number/4LTGULOB5KS7DJBIBV7ZLYPB2M/events.json","paper":"https://pith.science/paper/4LTGULOB"},"agent_actions":{"view_html":"https://pith.science/pith/4LTGULOB5KS7DJBIBV7ZLYPB2M","download_json":"https://pith.science/pith/4LTGULOB5KS7DJBIBV7ZLYPB2M.json","view_paper":"https://pith.science/paper/4LTGULOB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.10783&json=true","fetch_graph":"https://pith.science/api/pith-number/4LTGULOB5KS7DJBIBV7ZLYPB2M/graph.json","fetch_events":"https://pith.science/api/pith-number/4LTGULOB5KS7DJBIBV7ZLYPB2M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4LTGULOB5KS7DJBIBV7ZLYPB2M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4LTGULOB5KS7DJBIBV7ZLYPB2M/action/storage_attestation","attest_author":"https://pith.science/pith/4LTGULOB5KS7DJBIBV7ZLYPB2M/action/author_attestation","sign_citation":"https://pith.science/pith/4LTGULOB5KS7DJBIBV7ZLYPB2M/action/citation_signature","submit_replication":"https://pith.science/pith/4LTGULOB5KS7DJBIBV7ZLYPB2M/action/replication_record"}},"created_at":"2026-07-05T10:52:15.102649+00:00","updated_at":"2026-07-05T10:52:15.102649+00:00"}