{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HV67PEW5A4ENRLPMJVCY75JPUK","short_pith_number":"pith:HV67PEW5","schema_version":"1.0","canonical_sha256":"3d7df792dd0708d8adec4d458ff52fa2b90d5d46020f37ac29a1ec2dbe40a629","source":{"kind":"arxiv","id":"2605.24225","version":1},"attestation_state":"computed","paper":{"title":"ECo-MoE: Embodiment-Conditioned Mixture of Experts Increases the Evolvability of Robots","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Muhan Li, Sam Kriegman, Yibin Wang, Zihan Guo","submitted_at":"2026-05-22T21:11:47Z","abstract_excerpt":"In this paper, we introduce a model of evolution and learning in robots that co-optimizes a distribution of latent design vectors (genotypes) and a mixture of control experts (neural modules), which are gated by the latent coordinates of each decoded design (phenotype). This provides a scalable alternative to co-design algorithms that either train an individual policy for every robot, which is inefficient, or a monolithic universal controller for all robots, which results in overly conservative structures and behaviors. Our approach lies somewhere between these two extremes, preserving ancestr"},"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":"2605.24225","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-22T21:11:47Z","cross_cats_sorted":[],"title_canon_sha256":"fc6756f5f8b4a616b41bc0bb77e4bc6d28655679bc60c02477199b8c5afa6c63","abstract_canon_sha256":"4684f696cb869ce3d398fd33997a5b018b7522118a5fad8e7c56f67a9a69ee19"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:02:53.748255Z","signature_b64":"CGnJLwcdHzAf1jd5x9QXyVK/7N2MGk1sDKLP7ruxZRoCk7xWEC+VGvsro7ZDBxtvDYBZCqWSSFMhdMCAc/pFAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d7df792dd0708d8adec4d458ff52fa2b90d5d46020f37ac29a1ec2dbe40a629","last_reissued_at":"2026-05-26T01:02:53.747553Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:02:53.747553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ECo-MoE: Embodiment-Conditioned Mixture of Experts Increases the Evolvability of Robots","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Muhan Li, Sam Kriegman, Yibin Wang, Zihan Guo","submitted_at":"2026-05-22T21:11:47Z","abstract_excerpt":"In this paper, we introduce a model of evolution and learning in robots that co-optimizes a distribution of latent design vectors (genotypes) and a mixture of control experts (neural modules), which are gated by the latent coordinates of each decoded design (phenotype). This provides a scalable alternative to co-design algorithms that either train an individual policy for every robot, which is inefficient, or a monolithic universal controller for all robots, which results in overly conservative structures and behaviors. Our approach lies somewhere between these two extremes, preserving ancestr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24225","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/2605.24225/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":"2605.24225","created_at":"2026-05-26T01:02:53.747674+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.24225v1","created_at":"2026-05-26T01:02:53.747674+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24225","created_at":"2026-05-26T01:02:53.747674+00:00"},{"alias_kind":"pith_short_12","alias_value":"HV67PEW5A4EN","created_at":"2026-05-26T01:02:53.747674+00:00"},{"alias_kind":"pith_short_16","alias_value":"HV67PEW5A4ENRLPM","created_at":"2026-05-26T01:02:53.747674+00:00"},{"alias_kind":"pith_short_8","alias_value":"HV67PEW5","created_at":"2026-05-26T01:02:53.747674+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/HV67PEW5A4ENRLPMJVCY75JPUK","json":"https://pith.science/pith/HV67PEW5A4ENRLPMJVCY75JPUK.json","graph_json":"https://pith.science/api/pith-number/HV67PEW5A4ENRLPMJVCY75JPUK/graph.json","events_json":"https://pith.science/api/pith-number/HV67PEW5A4ENRLPMJVCY75JPUK/events.json","paper":"https://pith.science/paper/HV67PEW5"},"agent_actions":{"view_html":"https://pith.science/pith/HV67PEW5A4ENRLPMJVCY75JPUK","download_json":"https://pith.science/pith/HV67PEW5A4ENRLPMJVCY75JPUK.json","view_paper":"https://pith.science/paper/HV67PEW5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.24225&json=true","fetch_graph":"https://pith.science/api/pith-number/HV67PEW5A4ENRLPMJVCY75JPUK/graph.json","fetch_events":"https://pith.science/api/pith-number/HV67PEW5A4ENRLPMJVCY75JPUK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HV67PEW5A4ENRLPMJVCY75JPUK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HV67PEW5A4ENRLPMJVCY75JPUK/action/storage_attestation","attest_author":"https://pith.science/pith/HV67PEW5A4ENRLPMJVCY75JPUK/action/author_attestation","sign_citation":"https://pith.science/pith/HV67PEW5A4ENRLPMJVCY75JPUK/action/citation_signature","submit_replication":"https://pith.science/pith/HV67PEW5A4ENRLPMJVCY75JPUK/action/replication_record"}},"created_at":"2026-05-26T01:02:53.747674+00:00","updated_at":"2026-05-26T01:02:53.747674+00:00"}