{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ESCJMZT7L2BNR4EAZC4UTDOLVZ","short_pith_number":"pith:ESCJMZT7","schema_version":"1.0","canonical_sha256":"248496667f5e82d8f080c8b9498dcbae57bc4063fd8a32a5f1ae2fa5389eeff6","source":{"kind":"arxiv","id":"2311.04894","version":1},"attestation_state":"computed","paper":{"title":"DAMEX: Dataset-aware Mixture-of-Experts for visual understanding of mixture-of-datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Harkirat Behl, Vibhav Vineet, Yash Jain, Zsolt Kira","submitted_at":"2023-11-08T18:55:24Z","abstract_excerpt":"Construction of a universal detector poses a crucial question: How can we most effectively train a model on a large mixture of datasets? The answer lies in learning dataset-specific features and ensembling their knowledge but do all this in a single model. Previous methods achieve this by having separate detection heads on a common backbone but that results in a significant increase in parameters. In this work, we present Mixture-of-Experts as a solution, highlighting that MoEs are much more than a scalability tool. We propose Dataset-Aware Mixture-of-Experts, DAMEX where we train the experts "},"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":"2311.04894","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-08T18:55:24Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6080f1e259beefa974cee7f6aa8cebdda7f45b46faa13024704fa39d164451eb","abstract_canon_sha256":"85057c2926aa470c6f0f753935799da8af1b560c924a0974c9890f44eeb25173"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:10:44.033846Z","signature_b64":"18/2DfGQpyAtTzkKnZRVyB6scmubT963X8h+zgx1kOmKt4EaofCJ+6YV3sVLTtZFJQdXOE7dMfIC3BEYxL9qCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"248496667f5e82d8f080c8b9498dcbae57bc4063fd8a32a5f1ae2fa5389eeff6","last_reissued_at":"2026-07-05T07:10:44.033344Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:10:44.033344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DAMEX: Dataset-aware Mixture-of-Experts for visual understanding of mixture-of-datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Harkirat Behl, Vibhav Vineet, Yash Jain, Zsolt Kira","submitted_at":"2023-11-08T18:55:24Z","abstract_excerpt":"Construction of a universal detector poses a crucial question: How can we most effectively train a model on a large mixture of datasets? The answer lies in learning dataset-specific features and ensembling their knowledge but do all this in a single model. Previous methods achieve this by having separate detection heads on a common backbone but that results in a significant increase in parameters. In this work, we present Mixture-of-Experts as a solution, highlighting that MoEs are much more than a scalability tool. We propose Dataset-Aware Mixture-of-Experts, DAMEX where we train the experts "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.04894","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/2311.04894/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":"2311.04894","created_at":"2026-07-05T07:10:44.033404+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.04894v1","created_at":"2026-07-05T07:10:44.033404+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.04894","created_at":"2026-07-05T07:10:44.033404+00:00"},{"alias_kind":"pith_short_12","alias_value":"ESCJMZT7L2BN","created_at":"2026-07-05T07:10:44.033404+00:00"},{"alias_kind":"pith_short_16","alias_value":"ESCJMZT7L2BNR4EA","created_at":"2026-07-05T07:10:44.033404+00:00"},{"alias_kind":"pith_short_8","alias_value":"ESCJMZT7","created_at":"2026-07-05T07:10:44.033404+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.04908","citing_title":"HI-MoE: Hierarchical Instance-Conditioned Mixture-of-Experts for Object Detection","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ESCJMZT7L2BNR4EAZC4UTDOLVZ","json":"https://pith.science/pith/ESCJMZT7L2BNR4EAZC4UTDOLVZ.json","graph_json":"https://pith.science/api/pith-number/ESCJMZT7L2BNR4EAZC4UTDOLVZ/graph.json","events_json":"https://pith.science/api/pith-number/ESCJMZT7L2BNR4EAZC4UTDOLVZ/events.json","paper":"https://pith.science/paper/ESCJMZT7"},"agent_actions":{"view_html":"https://pith.science/pith/ESCJMZT7L2BNR4EAZC4UTDOLVZ","download_json":"https://pith.science/pith/ESCJMZT7L2BNR4EAZC4UTDOLVZ.json","view_paper":"https://pith.science/paper/ESCJMZT7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.04894&json=true","fetch_graph":"https://pith.science/api/pith-number/ESCJMZT7L2BNR4EAZC4UTDOLVZ/graph.json","fetch_events":"https://pith.science/api/pith-number/ESCJMZT7L2BNR4EAZC4UTDOLVZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ESCJMZT7L2BNR4EAZC4UTDOLVZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ESCJMZT7L2BNR4EAZC4UTDOLVZ/action/storage_attestation","attest_author":"https://pith.science/pith/ESCJMZT7L2BNR4EAZC4UTDOLVZ/action/author_attestation","sign_citation":"https://pith.science/pith/ESCJMZT7L2BNR4EAZC4UTDOLVZ/action/citation_signature","submit_replication":"https://pith.science/pith/ESCJMZT7L2BNR4EAZC4UTDOLVZ/action/replication_record"}},"created_at":"2026-07-05T07:10:44.033404+00:00","updated_at":"2026-07-05T07:10:44.033404+00:00"}