{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RPLG2DVKSGYMDBFLIRJFX3S2JN","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3aa3a217704f9b0c325017760824d28952a28a30c249ed4157969d1e5a9e44a0","cross_cats_sorted":["cs.AI","physics.comp-ph"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T17:58:15Z","title_canon_sha256":"e3ffd0339810a48fb826ab881d1d8b954d43002bca137b6309b940ea388c0f60"},"schema_version":"1.0","source":{"id":"2605.15179","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15179","created_at":"2026-05-17T21:18:32Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15179v1","created_at":"2026-05-17T21:18:32Z"},{"alias_kind":"pith_short_12","alias_value":"RPLG2DVKSGYM","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"RPLG2DVKSGYMDBFL","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"RPLG2DVK","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:f412340eaf028f8886a5d33321431a77e6f90fb589707ead22fede63544b31c9","target":"graph","created_at":"2026-05-17T21:57:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":3,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"These results support sparse expert routing as a practical architectural mechanism for mitigating multi-physics interference in universal neural operators."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That a Top-1 soft-semantic router will reliably produce autonomous domain bifurcation and specialized parameter paths for incompatible PDE regimes without losing shared symmetries or requiring extensive hyperparameter tuning."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Shodh-MoE uses Top-1 routing on compressed latents from a divergence-free autoencoder to let distinct physics regimes train separate experts, yielding low MSE and autonomous domain separation in mixed pretraining."}],"snapshot_sha256":"e76be456e71c57d198b2ec7be7b925085850212f14cdefbdd6acfee8054a7dce"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Scaling Scientific Machine Learning (SciML) toward universal foundation models is bottlenecked by negative transfer: the simultaneous co-training of disparate partial differential equation (PDE) regimes can induce gradient conflict, unstable optimization, and plasticity loss in dense neural operators. In particular, broadband open-channel fluid dynamics and boundary-dominated porous media flows impose incompatible spectral and geometric demands on a single dense parameter path. We introduce Shodh-MoE, a sparse-activated latent transformer architecture for multi-physics transport. Shodh-MoE ope","authors_text":"Arastu Sharma, Ellwil Sharma","cross_cats":["cs.AI","physics.comp-ph"],"headline":"Shodh-MoE uses Top-1 routing on compressed latents from a divergence-free autoencoder to let distinct physics regimes train separate experts, yielding low MSE and autonomous domain separation in mixed pretraining.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T17:58:15Z","title":"Eradicating Negative Transfer in Multi-Physics Foundation Models via Sparse Mixture-of-Experts Routing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15179","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T03:18:39.052599Z","id":"11a974fb-0d35-4ed9-a551-8266fefc7ee9","model_set":{"reader":"grok-4.3"},"one_line_summary":"Shodh-MoE uses Top-1 routing on compressed latents from a divergence-free autoencoder to let distinct physics regimes train separate experts, yielding low MSE and autonomous domain separation in mixed pretraining.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"","strongest_claim":"These results support sparse expert routing as a practical architectural mechanism for mitigating multi-physics interference in universal neural operators.","weakest_assumption":"That a Top-1 soft-semantic router will reliably produce autonomous domain bifurcation and specialized parameter paths for incompatible PDE regimes without losing shared symmetries or requiring extensive hyperparameter tuning."}},"verdict_id":"11a974fb-0d35-4ed9-a551-8266fefc7ee9"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:288d9373b9e549df88982370e1659fc088840ccf5a83e6e08b019720593a226c","target":"record","created_at":"2026-05-17T21:18:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3aa3a217704f9b0c325017760824d28952a28a30c249ed4157969d1e5a9e44a0","cross_cats_sorted":["cs.AI","physics.comp-ph"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T17:58:15Z","title_canon_sha256":"e3ffd0339810a48fb826ab881d1d8b954d43002bca137b6309b940ea388c0f60"},"schema_version":"1.0","source":{"id":"2605.15179","kind":"arxiv","version":1}},"canonical_sha256":"8bd66d0eaa91b0c184ab44525bee5a4b6979d0de4233ced412911af3d7d5d732","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8bd66d0eaa91b0c184ab44525bee5a4b6979d0de4233ced412911af3d7d5d732","first_computed_at":"2026-05-17T21:40:25.187828Z","kind":"pith_receipt","last_reissued_at":"2026-05-17T21:57:18.547039Z","receipt_version":"0.2","signature_status":"unsigned_v0"},"source_id":"2605.15179","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:288d9373b9e549df88982370e1659fc088840ccf5a83e6e08b019720593a226c","sha256:f412340eaf028f8886a5d33321431a77e6f90fb589707ead22fede63544b31c9"],"state_sha256":"97b1fd320aaac422bd19faecc5c63a23e8336315cd20058bd35186389503b85e"}