{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:AG3PAJ22332P5QMVIKKH75CXNK","short_pith_number":"pith:AG3PAJ22","canonical_record":{"source":{"id":"2603.28768","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2026-01-12T19:25:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"10780424b17d13211285838ab9156aa65bf4cec8be3ef5157d50a58d86fde8b0","abstract_canon_sha256":"b89c7b37ca673d9dc6512fd27da38c40255fe7818e7793997a701807fb10d4f7"},"schema_version":"1.0"},"canonical_sha256":"01b6f0275adef4fec19542947ff4576a8ee3ac748d00ef3257927d470ee800d4","source":{"kind":"arxiv","id":"2603.28768","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.28768","created_at":"2026-06-02T01:03:16Z"},{"alias_kind":"arxiv_version","alias_value":"2603.28768v2","created_at":"2026-06-02T01:03:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.28768","created_at":"2026-06-02T01:03:16Z"},{"alias_kind":"pith_short_12","alias_value":"AG3PAJ22332P","created_at":"2026-06-02T01:03:16Z"},{"alias_kind":"pith_short_16","alias_value":"AG3PAJ22332P5QMV","created_at":"2026-06-02T01:03:16Z"},{"alias_kind":"pith_short_8","alias_value":"AG3PAJ22","created_at":"2026-06-02T01:03:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:AG3PAJ22332P5QMVIKKH75CXNK","target":"record","payload":{"canonical_record":{"source":{"id":"2603.28768","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2026-01-12T19:25:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"10780424b17d13211285838ab9156aa65bf4cec8be3ef5157d50a58d86fde8b0","abstract_canon_sha256":"b89c7b37ca673d9dc6512fd27da38c40255fe7818e7793997a701807fb10d4f7"},"schema_version":"1.0"},"canonical_sha256":"01b6f0275adef4fec19542947ff4576a8ee3ac748d00ef3257927d470ee800d4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:16.008977Z","signature_b64":"vxaFQLemOvVW2ZYtL5ycaOayTvlYSxmvU0Y+yCnNc88ZLcBL5lT3xtLQMd4QSXLWwzo+BW7TYTKT7UBmC09AAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01b6f0275adef4fec19542947ff4576a8ee3ac748d00ef3257927d470ee800d4","last_reissued_at":"2026-06-02T01:03:16.008494Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:16.008494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2603.28768","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T01:03:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N9CX1zYNZy/AF7lYwz1HoOm2J893Jc1zPHIwl0NLzdx0n4GbZ9eYYokeITGQGzBc6T73cm6ko8GQdMGvRtTsDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T13:08:08.374752Z"},"content_sha256":"5511524888781c79c76013d86f01d673a277f599c6ccc26e4cfe347f781b2c56","schema_version":"1.0","event_id":"sha256:5511524888781c79c76013d86f01d673a277f599c6ccc26e4cfe347f781b2c56"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:AG3PAJ22332P5QMVIKKH75CXNK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CRAFT: Fine-Grained Cost-Aware Expert Replication For Efficient Mixture-of-Experts Serving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Adrian Zhao, Haozheng Fan, Jun Wu, Lingfan Yu, Nandita Vijaykumar, Yida Wang, Zhenkun Cai, Zhenyu Song","submitted_at":"2026-01-12T19:25:01Z","abstract_excerpt":"Mixture-of-Experts (MoE) has recently emerged as the mainstream architecture for efficiently scaling large language models while maintaining near-constant computational cost. Expert parallelism distributes parameters by partitioning experts across devices, but this introduces token-level load imbalance during inference. Expert replication is a widely adopted load-balancing technique in serving frameworks that alleviates load imbalance in large-scale deployments by replicating experts with high loads. In this work, we demonstrate that existing replication schemes often over-replicate, with many"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.28768","kind":"arxiv","version":2},"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/2603.28768/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":"2026-06-02T01:03:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CkBbmqji4m9Tts41OG8780zy8m0dvDdZeuksFXL5Xm7Adwd0y+1ynccLzi39MBoTOLq25ZGGl0TwLo5IjQ51CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T13:08:08.375134Z"},"content_sha256":"8985ee514b3dc9a73bfe126fa4c9ae27437d52abbd3d34d05bfa69d2853f8828","schema_version":"1.0","event_id":"sha256:8985ee514b3dc9a73bfe126fa4c9ae27437d52abbd3d34d05bfa69d2853f8828"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AG3PAJ22332P5QMVIKKH75CXNK/bundle.json","state_url":"https://pith.science/pith/AG3PAJ22332P5QMVIKKH75CXNK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AG3PAJ22332P5QMVIKKH75CXNK/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":"2026-06-03T13:08:08Z","links":{"resolver":"https://pith.science/pith/AG3PAJ22332P5QMVIKKH75CXNK","bundle":"https://pith.science/pith/AG3PAJ22332P5QMVIKKH75CXNK/bundle.json","state":"https://pith.science/pith/AG3PAJ22332P5QMVIKKH75CXNK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AG3PAJ22332P5QMVIKKH75CXNK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AG3PAJ22332P5QMVIKKH75CXNK","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":"b89c7b37ca673d9dc6512fd27da38c40255fe7818e7793997a701807fb10d4f7","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2026-01-12T19:25:01Z","title_canon_sha256":"10780424b17d13211285838ab9156aa65bf4cec8be3ef5157d50a58d86fde8b0"},"schema_version":"1.0","source":{"id":"2603.28768","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.28768","created_at":"2026-06-02T01:03:16Z"},{"alias_kind":"arxiv_version","alias_value":"2603.28768v2","created_at":"2026-06-02T01:03:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.28768","created_at":"2026-06-02T01:03:16Z"},{"alias_kind":"pith_short_12","alias_value":"AG3PAJ22332P","created_at":"2026-06-02T01:03:16Z"},{"alias_kind":"pith_short_16","alias_value":"AG3PAJ22332P5QMV","created_at":"2026-06-02T01:03:16Z"},{"alias_kind":"pith_short_8","alias_value":"AG3PAJ22","created_at":"2026-06-02T01:03:16Z"}],"graph_snapshots":[{"event_id":"sha256:8985ee514b3dc9a73bfe126fa4c9ae27437d52abbd3d34d05bfa69d2853f8828","target":"graph","created_at":"2026-06-02T01:03:16Z","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/2603.28768/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mixture-of-Experts (MoE) has recently emerged as the mainstream architecture for efficiently scaling large language models while maintaining near-constant computational cost. Expert parallelism distributes parameters by partitioning experts across devices, but this introduces token-level load imbalance during inference. Expert replication is a widely adopted load-balancing technique in serving frameworks that alleviates load imbalance in large-scale deployments by replicating experts with high loads. In this work, we demonstrate that existing replication schemes often over-replicate, with many","authors_text":"Adrian Zhao, Haozheng Fan, Jun Wu, Lingfan Yu, Nandita Vijaykumar, Yida Wang, Zhenkun Cai, Zhenyu Song","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2026-01-12T19:25:01Z","title":"CRAFT: Fine-Grained Cost-Aware Expert Replication For Efficient Mixture-of-Experts Serving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.28768","kind":"arxiv","version":2},"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":"sha256:5511524888781c79c76013d86f01d673a277f599c6ccc26e4cfe347f781b2c56","target":"record","created_at":"2026-06-02T01:03:16Z","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":"b89c7b37ca673d9dc6512fd27da38c40255fe7818e7793997a701807fb10d4f7","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2026-01-12T19:25:01Z","title_canon_sha256":"10780424b17d13211285838ab9156aa65bf4cec8be3ef5157d50a58d86fde8b0"},"schema_version":"1.0","source":{"id":"2603.28768","kind":"arxiv","version":2}},"canonical_sha256":"01b6f0275adef4fec19542947ff4576a8ee3ac748d00ef3257927d470ee800d4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"01b6f0275adef4fec19542947ff4576a8ee3ac748d00ef3257927d470ee800d4","first_computed_at":"2026-06-02T01:03:16.008494Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:03:16.008494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vxaFQLemOvVW2ZYtL5ycaOayTvlYSxmvU0Y+yCnNc88ZLcBL5lT3xtLQMd4QSXLWwzo+BW7TYTKT7UBmC09AAg==","signature_status":"signed_v1","signed_at":"2026-06-02T01:03:16.008977Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.28768","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5511524888781c79c76013d86f01d673a277f599c6ccc26e4cfe347f781b2c56","sha256:8985ee514b3dc9a73bfe126fa4c9ae27437d52abbd3d34d05bfa69d2853f8828"],"state_sha256":"1a7ac2e50ab382bc37366326f84cd1cf0cfd6e34c4b7a6e70a8b1a5df4ef92e5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xbRHZlV+P4ksS7R6WownlhN/6zslSEsj/Ngh30JY+gB08hi8q6GewE/i0FJo96XuvLHGF+qIVu44xvJyrREZCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T13:08:08.377434Z","bundle_sha256":"849c427f79ec82eb16b44cefa49ffff31e6865581701f05ded65149b2d8d60eb"}}