{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:DV3RCMSGJPFXENWOSOFM5K7UEV","short_pith_number":"pith:DV3RCMSG","canonical_record":{"source":{"id":"2601.20205","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-28T03:02:30Z","cross_cats_sorted":[],"title_canon_sha256":"03516cb2a06e1efcf98f2755ddb6a1be3492a907bd02395ab50aabca998a1df4","abstract_canon_sha256":"dd4e3931644a53159d8803c5c0821ad39c48fd24b49896b0a3680f09928cc352"},"schema_version":"1.0"},"canonical_sha256":"1d771132464bcb7236ce938aceabf425740033f551ee3820ccbd0bc4cc2918e9","source":{"kind":"arxiv","id":"2601.20205","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.20205","created_at":"2026-05-22T02:04:39Z"},{"alias_kind":"arxiv_version","alias_value":"2601.20205v3","created_at":"2026-05-22T02:04:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.20205","created_at":"2026-05-22T02:04:39Z"},{"alias_kind":"pith_short_12","alias_value":"DV3RCMSGJPFX","created_at":"2026-05-22T02:04:39Z"},{"alias_kind":"pith_short_16","alias_value":"DV3RCMSGJPFXENWO","created_at":"2026-05-22T02:04:39Z"},{"alias_kind":"pith_short_8","alias_value":"DV3RCMSG","created_at":"2026-05-22T02:04:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:DV3RCMSGJPFXENWOSOFM5K7UEV","target":"record","payload":{"canonical_record":{"source":{"id":"2601.20205","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-28T03:02:30Z","cross_cats_sorted":[],"title_canon_sha256":"03516cb2a06e1efcf98f2755ddb6a1be3492a907bd02395ab50aabca998a1df4","abstract_canon_sha256":"dd4e3931644a53159d8803c5c0821ad39c48fd24b49896b0a3680f09928cc352"},"schema_version":"1.0"},"canonical_sha256":"1d771132464bcb7236ce938aceabf425740033f551ee3820ccbd0bc4cc2918e9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T02:04:39.100897Z","signature_b64":"ndWKhqLTTuMpjVsqb0IXdL4PIWmXEuYPhNfBx9X7MSUsTpLjQwlTGTtBCzgYLHzvcUzjzLoYQoJeKtI8AmvIDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d771132464bcb7236ce938aceabf425740033f551ee3820ccbd0bc4cc2918e9","last_reissued_at":"2026-05-22T02:04:39.100008Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T02:04:39.100008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2601.20205","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-22T02:04:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c/6IQ/RFsmXVDmms93Z7lpfZ0U0PiIpkq+5ue5piBO0FMA0GBsrhkLfudovBhL+q9RfjKiYc2PPUAk0zyRJJCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T17:39:37.461144Z"},"content_sha256":"63aa8aba56b1668271e0544cc65ce9b3330dc403cabbd12c172a5af56e0ff176","schema_version":"1.0","event_id":"sha256:63aa8aba56b1668271e0544cc65ce9b3330dc403cabbd12c172a5af56e0ff176"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:DV3RCMSGJPFXENWOSOFM5K7UEV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hyperparameter Transfer with Mixture-of-Expert Layers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Blake Bordelon, Boris Hanin, Cengiz Pehlevan, Tianze Jiang","submitted_at":"2026-01-28T03:02:30Z","abstract_excerpt":"Mixture-of-Experts (MoE) layers have emerged as an important tool in scaling up modern neural networks by decoupling total trainable parameters from activated parameters in the forward pass for each token. However, sparse MoEs add complexity to training due to (i) new trainable parameters (router weights) that, like all other parameter groups, require hyperparameter (HP) tuning; (ii) new architecture scale dimensions (number of and size of experts) that must be chosen and potentially taken large. To make HP selection cheap and reliable, we propose a new parameterization for transformer models "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.20205","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/2601.20205/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-22T02:04:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vMWazoNUZs7FIxsSAxUyrtE0yIGq91GNgLK92mYkwvdd8pJ+jX1Ft1b3/g1IhiFuCBU096mMiMSA9uI4WKSMCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T17:39:37.461863Z"},"content_sha256":"3d3ef7fe04796b440b87615e17ce5d46f1371aea54d32ce9cf855365c53ec17f","schema_version":"1.0","event_id":"sha256:3d3ef7fe04796b440b87615e17ce5d46f1371aea54d32ce9cf855365c53ec17f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DV3RCMSGJPFXENWOSOFM5K7UEV/bundle.json","state_url":"https://pith.science/pith/DV3RCMSGJPFXENWOSOFM5K7UEV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DV3RCMSGJPFXENWOSOFM5K7UEV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-22T17:39:37Z","links":{"resolver":"https://pith.science/pith/DV3RCMSGJPFXENWOSOFM5K7UEV","bundle":"https://pith.science/pith/DV3RCMSGJPFXENWOSOFM5K7UEV/bundle.json","state":"https://pith.science/pith/DV3RCMSGJPFXENWOSOFM5K7UEV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DV3RCMSGJPFXENWOSOFM5K7UEV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DV3RCMSGJPFXENWOSOFM5K7UEV","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":"dd4e3931644a53159d8803c5c0821ad39c48fd24b49896b0a3680f09928cc352","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-28T03:02:30Z","title_canon_sha256":"03516cb2a06e1efcf98f2755ddb6a1be3492a907bd02395ab50aabca998a1df4"},"schema_version":"1.0","source":{"id":"2601.20205","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.20205","created_at":"2026-05-22T02:04:39Z"},{"alias_kind":"arxiv_version","alias_value":"2601.20205v3","created_at":"2026-05-22T02:04:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.20205","created_at":"2026-05-22T02:04:39Z"},{"alias_kind":"pith_short_12","alias_value":"DV3RCMSGJPFX","created_at":"2026-05-22T02:04:39Z"},{"alias_kind":"pith_short_16","alias_value":"DV3RCMSGJPFXENWO","created_at":"2026-05-22T02:04:39Z"},{"alias_kind":"pith_short_8","alias_value":"DV3RCMSG","created_at":"2026-05-22T02:04:39Z"}],"graph_snapshots":[{"event_id":"sha256:3d3ef7fe04796b440b87615e17ce5d46f1371aea54d32ce9cf855365c53ec17f","target":"graph","created_at":"2026-05-22T02:04:39Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2601.20205/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mixture-of-Experts (MoE) layers have emerged as an important tool in scaling up modern neural networks by decoupling total trainable parameters from activated parameters in the forward pass for each token. However, sparse MoEs add complexity to training due to (i) new trainable parameters (router weights) that, like all other parameter groups, require hyperparameter (HP) tuning; (ii) new architecture scale dimensions (number of and size of experts) that must be chosen and potentially taken large. To make HP selection cheap and reliable, we propose a new parameterization for transformer models ","authors_text":"Blake Bordelon, Boris Hanin, Cengiz Pehlevan, Tianze Jiang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-28T03:02:30Z","title":"Hyperparameter Transfer with Mixture-of-Expert Layers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.20205","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:63aa8aba56b1668271e0544cc65ce9b3330dc403cabbd12c172a5af56e0ff176","target":"record","created_at":"2026-05-22T02:04:39Z","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":"dd4e3931644a53159d8803c5c0821ad39c48fd24b49896b0a3680f09928cc352","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-28T03:02:30Z","title_canon_sha256":"03516cb2a06e1efcf98f2755ddb6a1be3492a907bd02395ab50aabca998a1df4"},"schema_version":"1.0","source":{"id":"2601.20205","kind":"arxiv","version":3}},"canonical_sha256":"1d771132464bcb7236ce938aceabf425740033f551ee3820ccbd0bc4cc2918e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d771132464bcb7236ce938aceabf425740033f551ee3820ccbd0bc4cc2918e9","first_computed_at":"2026-05-22T02:04:39.100008Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T02:04:39.100008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ndWKhqLTTuMpjVsqb0IXdL4PIWmXEuYPhNfBx9X7MSUsTpLjQwlTGTtBCzgYLHzvcUzjzLoYQoJeKtI8AmvIDQ==","signature_status":"signed_v1","signed_at":"2026-05-22T02:04:39.100897Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.20205","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:63aa8aba56b1668271e0544cc65ce9b3330dc403cabbd12c172a5af56e0ff176","sha256:3d3ef7fe04796b440b87615e17ce5d46f1371aea54d32ce9cf855365c53ec17f"],"state_sha256":"7d454bff50239a11b3c92eb605c9cf2c383005f2531bf7ed56ae0ea8fa31f430"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PWbMdHry1TnNbQh6So0N6Bh+r2y9hjwtsiXgGnMi9tfu86raWzjsI2ofbIMNGvDMyPQ8DRgR0l3dK5lJ6J69Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-22T17:39:37.465563Z","bundle_sha256":"bb199d3031b2e16ba44bbee5c931d23e85416dc4d58d2d4aaab0dec127024e07"}}