{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UNO437CPLDEI74GBY3GSPVSQLR","short_pith_number":"pith:UNO437CP","schema_version":"1.0","canonical_sha256":"a35dcdfc4f58c88ff0c1c6cd27d6505c55f9ea0bb882f3815b41d963bf6163e4","source":{"kind":"arxiv","id":"2406.11775","version":2},"attestation_state":"computed","paper":{"title":"Task Me Anything","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ali Farhadi, Aniruddha Kembhavi, Dong He, Jieyu Zhang, Oscar Michel, Ranjay Krishna, Tanmay Gupta, Wei-Chiu Ma, Weikai Huang, Zixian Ma","submitted_at":"2024-06-17T17:32:42Z","abstract_excerpt":"Benchmarks for large multimodal language models (MLMs) now serve to simultaneously assess the general capabilities of models instead of evaluating for a specific capability. As a result, when a developer wants to identify which models to use for their application, they are overwhelmed by the number of benchmarks and remain uncertain about which benchmark's results are most reflective of their specific use case. This paper introduces Task-Me-Anything, a benchmark generation engine which produces a benchmark tailored to a user's needs. Task-Me-Anything maintains an extendable taxonomy of visual "},"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":"2406.11775","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T17:32:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2395eb1244d1fadfbb20fd94b18ec68fe234bdd1f38026b7238fe020ef43476f","abstract_canon_sha256":"8e3bd6349ace23c24ec72e1a0ca1aeab81dac9967b365c489a2ac3fbe3545106"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:43.527507Z","signature_b64":"9ceHKSlMpu8yB959+poMZW/tJYOmf5V9T3NxEHZ6jvvzDwiYVsdA73qPGF7JxFWAHqrod5kt6k/ubnymhoH4BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a35dcdfc4f58c88ff0c1c6cd27d6505c55f9ea0bb882f3815b41d963bf6163e4","last_reissued_at":"2026-07-05T10:05:43.526948Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:43.526948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Task Me Anything","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ali Farhadi, Aniruddha Kembhavi, Dong He, Jieyu Zhang, Oscar Michel, Ranjay Krishna, Tanmay Gupta, Wei-Chiu Ma, Weikai Huang, Zixian Ma","submitted_at":"2024-06-17T17:32:42Z","abstract_excerpt":"Benchmarks for large multimodal language models (MLMs) now serve to simultaneously assess the general capabilities of models instead of evaluating for a specific capability. As a result, when a developer wants to identify which models to use for their application, they are overwhelmed by the number of benchmarks and remain uncertain about which benchmark's results are most reflective of their specific use case. This paper introduces Task-Me-Anything, a benchmark generation engine which produces a benchmark tailored to a user's needs. Task-Me-Anything maintains an extendable taxonomy of visual "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11775","kind":"arxiv","version":2},"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/2406.11775/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":"2406.11775","created_at":"2026-07-05T10:05:43.527027+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.11775v2","created_at":"2026-07-05T10:05:43.527027+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11775","created_at":"2026-07-05T10:05:43.527027+00:00"},{"alias_kind":"pith_short_12","alias_value":"UNO437CPLDEI","created_at":"2026-07-05T10:05:43.527027+00:00"},{"alias_kind":"pith_short_16","alias_value":"UNO437CPLDEI74GB","created_at":"2026-07-05T10:05:43.527027+00:00"},{"alias_kind":"pith_short_8","alias_value":"UNO437CP","created_at":"2026-07-05T10:05:43.527027+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/UNO437CPLDEI74GBY3GSPVSQLR","json":"https://pith.science/pith/UNO437CPLDEI74GBY3GSPVSQLR.json","graph_json":"https://pith.science/api/pith-number/UNO437CPLDEI74GBY3GSPVSQLR/graph.json","events_json":"https://pith.science/api/pith-number/UNO437CPLDEI74GBY3GSPVSQLR/events.json","paper":"https://pith.science/paper/UNO437CP"},"agent_actions":{"view_html":"https://pith.science/pith/UNO437CPLDEI74GBY3GSPVSQLR","download_json":"https://pith.science/pith/UNO437CPLDEI74GBY3GSPVSQLR.json","view_paper":"https://pith.science/paper/UNO437CP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.11775&json=true","fetch_graph":"https://pith.science/api/pith-number/UNO437CPLDEI74GBY3GSPVSQLR/graph.json","fetch_events":"https://pith.science/api/pith-number/UNO437CPLDEI74GBY3GSPVSQLR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UNO437CPLDEI74GBY3GSPVSQLR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UNO437CPLDEI74GBY3GSPVSQLR/action/storage_attestation","attest_author":"https://pith.science/pith/UNO437CPLDEI74GBY3GSPVSQLR/action/author_attestation","sign_citation":"https://pith.science/pith/UNO437CPLDEI74GBY3GSPVSQLR/action/citation_signature","submit_replication":"https://pith.science/pith/UNO437CPLDEI74GBY3GSPVSQLR/action/replication_record"}},"created_at":"2026-07-05T10:05:43.527027+00:00","updated_at":"2026-07-05T10:05:43.527027+00:00"}