{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XLTKSK4ZBCRBODORRUB6P6J547","short_pith_number":"pith:XLTKSK4Z","schema_version":"1.0","canonical_sha256":"bae6a92b9908a2170dd18d03e7f93de7f03e3e0f4d03c454ece4cb7aca349aba","source":{"kind":"arxiv","id":"2502.14865","version":1},"attestation_state":"computed","paper":{"title":"Time Travel: A Comprehensive Benchmark to Evaluate LMMs on Historical and Cultural Artifacts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Fahad Shahbaz Khan, Hisham Cholakkal, Ketan More, Omkar Thawakar, Rao Muhammad Anwer, Ritesh Thawkar, Salman Khan, Sara Ghaboura, Wafa Alghallabi","submitted_at":"2025-02-20T18:59:51Z","abstract_excerpt":"Understanding historical and cultural artifacts demands human expertise and advanced computational techniques, yet the process remains complex and time-intensive. While large multimodal models offer promising support, their evaluation and improvement require a standardized benchmark. To address this, we introduce TimeTravel, a benchmark of 10,250 expert-verified samples spanning 266 distinct cultures across 10 major historical regions. Designed for AI-driven analysis of manuscripts, artworks, inscriptions, and archaeological discoveries, TimeTravel provides a structured dataset and robust eval"},"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":"2502.14865","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-20T18:59:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6184a200a7c65774052a050dac095d4ea76e5b5bf373fb6b8f414085e74757fe","abstract_canon_sha256":"f0e55f31a3a624224a57e0ba54f51cdfd263e2ec572abe33dec4ae366762c5f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:33.742395Z","signature_b64":"caUpAmr7hp9OZef0gkay/LuWIH6DPfWCci33uoO9BKxj2tJ0en768lNtuJ8nDSh0vekl1LbkLPX5WoUe6aWtAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bae6a92b9908a2170dd18d03e7f93de7f03e3e0f4d03c454ece4cb7aca349aba","last_reissued_at":"2026-07-05T10:17:33.741876Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:33.741876Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Time Travel: A Comprehensive Benchmark to Evaluate LMMs on Historical and Cultural Artifacts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Fahad Shahbaz Khan, Hisham Cholakkal, Ketan More, Omkar Thawakar, Rao Muhammad Anwer, Ritesh Thawkar, Salman Khan, Sara Ghaboura, Wafa Alghallabi","submitted_at":"2025-02-20T18:59:51Z","abstract_excerpt":"Understanding historical and cultural artifacts demands human expertise and advanced computational techniques, yet the process remains complex and time-intensive. While large multimodal models offer promising support, their evaluation and improvement require a standardized benchmark. To address this, we introduce TimeTravel, a benchmark of 10,250 expert-verified samples spanning 266 distinct cultures across 10 major historical regions. Designed for AI-driven analysis of manuscripts, artworks, inscriptions, and archaeological discoveries, TimeTravel provides a structured dataset and robust eval"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14865","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/2502.14865/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":"2502.14865","created_at":"2026-07-05T10:17:33.741931+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.14865v1","created_at":"2026-07-05T10:17:33.741931+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14865","created_at":"2026-07-05T10:17:33.741931+00:00"},{"alias_kind":"pith_short_12","alias_value":"XLTKSK4ZBCRB","created_at":"2026-07-05T10:17:33.741931+00:00"},{"alias_kind":"pith_short_16","alias_value":"XLTKSK4ZBCRBODOR","created_at":"2026-07-05T10:17:33.741931+00:00"},{"alias_kind":"pith_short_8","alias_value":"XLTKSK4Z","created_at":"2026-07-05T10:17:33.741931+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09648","citing_title":"ArtiFact: A Large-Scale Multi-Modal Cultural Heritage Dataset","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01145","citing_title":"Reasoning4Sciences: Bridging Reasoning Language Models to All Scientific Branches","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01145","citing_title":"Reasoning4Sciences: Bridging Reasoning Language Models to All Scientific Branches","ref_index":95,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15071","citing_title":"On the Cultural Anachronism and Temporal Reasoning in Vision Language Models","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XLTKSK4ZBCRBODORRUB6P6J547","json":"https://pith.science/pith/XLTKSK4ZBCRBODORRUB6P6J547.json","graph_json":"https://pith.science/api/pith-number/XLTKSK4ZBCRBODORRUB6P6J547/graph.json","events_json":"https://pith.science/api/pith-number/XLTKSK4ZBCRBODORRUB6P6J547/events.json","paper":"https://pith.science/paper/XLTKSK4Z"},"agent_actions":{"view_html":"https://pith.science/pith/XLTKSK4ZBCRBODORRUB6P6J547","download_json":"https://pith.science/pith/XLTKSK4ZBCRBODORRUB6P6J547.json","view_paper":"https://pith.science/paper/XLTKSK4Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.14865&json=true","fetch_graph":"https://pith.science/api/pith-number/XLTKSK4ZBCRBODORRUB6P6J547/graph.json","fetch_events":"https://pith.science/api/pith-number/XLTKSK4ZBCRBODORRUB6P6J547/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XLTKSK4ZBCRBODORRUB6P6J547/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XLTKSK4ZBCRBODORRUB6P6J547/action/storage_attestation","attest_author":"https://pith.science/pith/XLTKSK4ZBCRBODORRUB6P6J547/action/author_attestation","sign_citation":"https://pith.science/pith/XLTKSK4ZBCRBODORRUB6P6J547/action/citation_signature","submit_replication":"https://pith.science/pith/XLTKSK4ZBCRBODORRUB6P6J547/action/replication_record"}},"created_at":"2026-07-05T10:17:33.741931+00:00","updated_at":"2026-07-05T10:17:33.741931+00:00"}