{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6TWXXKDD65JVPCBERR7FMSIVYQ","short_pith_number":"pith:6TWXXKDD","schema_version":"1.0","canonical_sha256":"f4ed7ba863f7535788248c7e564915c43f4b1bcb2ab3ae972ba822197082a195","source":{"kind":"arxiv","id":"2607.11586","version":1},"attestation_state":"computed","paper":{"title":"HCRMap: Pressure-Aware Hot-Expert Residency Mapping for 3.5D MoE Chiplet Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Yongqin Zhang","submitted_at":"2026-07-13T14:05:55Z","abstract_excerpt":"Mixture-of-Experts (MoE) large language models (LLM) activate only a small number of experts during inference, but token routing introduces persistent expert hotness skew: a small set of hot experts continuously receives most tokens, while the remaining experts are lightly loaded. On 3.5D multi-chiplet systems, this skew not only causes compute imbalance but also amplifies pressure on communication, memory bandwidth, I/O, and execution queues. Therefore, the core problem is not simply to reduce token movement, but to dynamically place and reuse hot expert replicas across different memory tiers"},"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":"2607.11586","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-13T14:05:55Z","cross_cats_sorted":[],"title_canon_sha256":"ea45ebdbecf05416ad3a2b76240806f41641d3552748e3cb32d90ee4e3a9c94c","abstract_canon_sha256":"ce4b8a5d677514016a80af1a2b4c7b26a1cd5b72dc30367c4b7244f635835145"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T02:22:13.526265Z","signature_b64":"QrNmVmSVPKNCy56oPpWtaME72+lHIOdmMQcX9lYduZkhsmHS5bBe/SbO+2B/jgib8IPcin00MekBExzwvWvMBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4ed7ba863f7535788248c7e564915c43f4b1bcb2ab3ae972ba822197082a195","last_reissued_at":"2026-07-14T02:22:13.525428Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T02:22:13.525428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HCRMap: Pressure-Aware Hot-Expert Residency Mapping for 3.5D MoE Chiplet Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Yongqin Zhang","submitted_at":"2026-07-13T14:05:55Z","abstract_excerpt":"Mixture-of-Experts (MoE) large language models (LLM) activate only a small number of experts during inference, but token routing introduces persistent expert hotness skew: a small set of hot experts continuously receives most tokens, while the remaining experts are lightly loaded. On 3.5D multi-chiplet systems, this skew not only causes compute imbalance but also amplifies pressure on communication, memory bandwidth, I/O, and execution queues. Therefore, the core problem is not simply to reduce token movement, but to dynamically place and reuse hot expert replicas across different memory tiers"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.11586","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/2607.11586/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":"2607.11586","created_at":"2026-07-14T02:22:13.525875+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.11586v1","created_at":"2026-07-14T02:22:13.525875+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.11586","created_at":"2026-07-14T02:22:13.525875+00:00"},{"alias_kind":"pith_short_12","alias_value":"6TWXXKDD65JV","created_at":"2026-07-14T02:22:13.525875+00:00"},{"alias_kind":"pith_short_16","alias_value":"6TWXXKDD65JVPCBE","created_at":"2026-07-14T02:22:13.525875+00:00"},{"alias_kind":"pith_short_8","alias_value":"6TWXXKDD","created_at":"2026-07-14T02:22:13.525875+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/6TWXXKDD65JVPCBERR7FMSIVYQ","json":"https://pith.science/pith/6TWXXKDD65JVPCBERR7FMSIVYQ.json","graph_json":"https://pith.science/api/pith-number/6TWXXKDD65JVPCBERR7FMSIVYQ/graph.json","events_json":"https://pith.science/api/pith-number/6TWXXKDD65JVPCBERR7FMSIVYQ/events.json","paper":"https://pith.science/paper/6TWXXKDD"},"agent_actions":{"view_html":"https://pith.science/pith/6TWXXKDD65JVPCBERR7FMSIVYQ","download_json":"https://pith.science/pith/6TWXXKDD65JVPCBERR7FMSIVYQ.json","view_paper":"https://pith.science/paper/6TWXXKDD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.11586&json=true","fetch_graph":"https://pith.science/api/pith-number/6TWXXKDD65JVPCBERR7FMSIVYQ/graph.json","fetch_events":"https://pith.science/api/pith-number/6TWXXKDD65JVPCBERR7FMSIVYQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6TWXXKDD65JVPCBERR7FMSIVYQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6TWXXKDD65JVPCBERR7FMSIVYQ/action/storage_attestation","attest_author":"https://pith.science/pith/6TWXXKDD65JVPCBERR7FMSIVYQ/action/author_attestation","sign_citation":"https://pith.science/pith/6TWXXKDD65JVPCBERR7FMSIVYQ/action/citation_signature","submit_replication":"https://pith.science/pith/6TWXXKDD65JVPCBERR7FMSIVYQ/action/replication_record"}},"created_at":"2026-07-14T02:22:13.525875+00:00","updated_at":"2026-07-14T02:22:13.525875+00:00"}