{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QKH42KTRF4NH7HZ6NTHWXRQWBW","short_pith_number":"pith:QKH42KTR","schema_version":"1.0","canonical_sha256":"828fcd2a712f1a7f9f3e6ccf6bc6160d8525aa20a83a4cc4d5ea7e10095189f0","source":{"kind":"arxiv","id":"2412.09612","version":3},"attestation_state":"computed","paper":{"title":"Olympus: A Universal Task Router for Computer Vision Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Dongdong Chen, Philip H. S. Torr, Ronald Clark, Weijian Xu, Yuanze Lin, Yunsheng Li","submitted_at":"2024-12-12T18:59:40Z","abstract_excerpt":"We introduce Olympus, a new approach that transforms Multimodal Large Language Models (MLLMs) into a unified framework capable of handling a wide array of computer vision tasks. Utilizing a controller MLLM, Olympus delegates over 20 specialized tasks across images, videos, and 3D objects to dedicated modules. This instruction-based routing enables complex workflows through chained actions without the need for training heavy generative models. Olympus easily integrates with existing MLLMs, expanding their capabilities with comparable performance. Experimental results demonstrate that Olympus ac"},"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":"2412.09612","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T18:59:40Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"8fd2321859065afa24761cf468b74dae391d302ed8e003f94160da034f66da48","abstract_canon_sha256":"4f66719b6450bac49831e1d890af4e5e1a8f466d835f820b0b1d518c860da6e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:03.809098Z","signature_b64":"oxQ3p0drgYP86rNnZFKoLHHtuXkvEMbEwjYW7ADU3Kj+yIxQSDSgICLmDGcnlhJZJKfeTh3L6tjdL7viAHopBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"828fcd2a712f1a7f9f3e6ccf6bc6160d8525aa20a83a4cc4d5ea7e10095189f0","last_reissued_at":"2026-07-05T10:43:03.808571Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:03.808571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Olympus: A Universal Task Router for Computer Vision Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Dongdong Chen, Philip H. S. Torr, Ronald Clark, Weijian Xu, Yuanze Lin, Yunsheng Li","submitted_at":"2024-12-12T18:59:40Z","abstract_excerpt":"We introduce Olympus, a new approach that transforms Multimodal Large Language Models (MLLMs) into a unified framework capable of handling a wide array of computer vision tasks. Utilizing a controller MLLM, Olympus delegates over 20 specialized tasks across images, videos, and 3D objects to dedicated modules. This instruction-based routing enables complex workflows through chained actions without the need for training heavy generative models. Olympus easily integrates with existing MLLMs, expanding their capabilities with comparable performance. Experimental results demonstrate that Olympus ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09612","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/2412.09612/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":"2412.09612","created_at":"2026-07-05T10:43:03.808624+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.09612v3","created_at":"2026-07-05T10:43:03.808624+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09612","created_at":"2026-07-05T10:43:03.808624+00:00"},{"alias_kind":"pith_short_12","alias_value":"QKH42KTRF4NH","created_at":"2026-07-05T10:43:03.808624+00:00"},{"alias_kind":"pith_short_16","alias_value":"QKH42KTRF4NH7HZ6","created_at":"2026-07-05T10:43:03.808624+00:00"},{"alias_kind":"pith_short_8","alias_value":"QKH42KTR","created_at":"2026-07-05T10:43:03.808624+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.03150","citing_title":"IllumiCraft: Unified Geometry and Illumination Diffusion for Controllable Video Generation","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QKH42KTRF4NH7HZ6NTHWXRQWBW","json":"https://pith.science/pith/QKH42KTRF4NH7HZ6NTHWXRQWBW.json","graph_json":"https://pith.science/api/pith-number/QKH42KTRF4NH7HZ6NTHWXRQWBW/graph.json","events_json":"https://pith.science/api/pith-number/QKH42KTRF4NH7HZ6NTHWXRQWBW/events.json","paper":"https://pith.science/paper/QKH42KTR"},"agent_actions":{"view_html":"https://pith.science/pith/QKH42KTRF4NH7HZ6NTHWXRQWBW","download_json":"https://pith.science/pith/QKH42KTRF4NH7HZ6NTHWXRQWBW.json","view_paper":"https://pith.science/paper/QKH42KTR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.09612&json=true","fetch_graph":"https://pith.science/api/pith-number/QKH42KTRF4NH7HZ6NTHWXRQWBW/graph.json","fetch_events":"https://pith.science/api/pith-number/QKH42KTRF4NH7HZ6NTHWXRQWBW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QKH42KTRF4NH7HZ6NTHWXRQWBW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QKH42KTRF4NH7HZ6NTHWXRQWBW/action/storage_attestation","attest_author":"https://pith.science/pith/QKH42KTRF4NH7HZ6NTHWXRQWBW/action/author_attestation","sign_citation":"https://pith.science/pith/QKH42KTRF4NH7HZ6NTHWXRQWBW/action/citation_signature","submit_replication":"https://pith.science/pith/QKH42KTRF4NH7HZ6NTHWXRQWBW/action/replication_record"}},"created_at":"2026-07-05T10:43:03.808624+00:00","updated_at":"2026-07-05T10:43:03.808624+00:00"}