{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MT6VCDRK7ILJVJEEJFVHOQYAAC","short_pith_number":"pith:MT6VCDRK","schema_version":"1.0","canonical_sha256":"64fd510e2afa169aa484496a77430000bf5aef12bc99ea66c3e06a10905d683d","source":{"kind":"arxiv","id":"2606.04581","version":1},"attestation_state":"computed","paper":{"title":"Multi-SPIN: Multi-Access Speculative Inference for Cooperative Token Generation at the Edge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NI"],"primary_cat":"cs.DC","authors_text":"Chang Cai, Haotian Zheng, Hongyang Du, Kaibin Huang, Mingyao Cui, Zhanwei Wang","submitted_at":"2026-06-03T08:16:14Z","abstract_excerpt":"Speculative inference (SPIN) was originally developed as an efficient architecture to accelerate Large Language Models (LLMs). In this work, we propose its distributed deployment to enable cooperative token generation in a multiuser edge system; its advantage is to effectively balance computational loads between resource-constrained devices and servers. The resulting architecture, termed Multi-access SPIN (Multi-SPIN), utilizes on-device small language models to generate and upload candidate token drafts, while an edge server operates the LLM to verify them in parallel batches. Given the sever"},"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":"2606.04581","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-06-03T08:16:14Z","cross_cats_sorted":["cs.AI","cs.NI"],"title_canon_sha256":"2011efcb80a8b844aedaaf92b41e7d9693c0241f59531fdd123c1874859dd933","abstract_canon_sha256":"e0bfaaf5b21122827703707b13eb327578379dc2b4a500cfbd28376b160b8589"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:09:19.156919Z","signature_b64":"QlC5EPoqMiwkiyg90B0Zq1V898DeNXIiu1nXoJXOcEpHVG2wH3jg4VJsLikOrZni46/eOevS/Ue5ukbivx5QDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64fd510e2afa169aa484496a77430000bf5aef12bc99ea66c3e06a10905d683d","last_reissued_at":"2026-06-04T01:09:19.156141Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:09:19.156141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-SPIN: Multi-Access Speculative Inference for Cooperative Token Generation at the Edge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NI"],"primary_cat":"cs.DC","authors_text":"Chang Cai, Haotian Zheng, Hongyang Du, Kaibin Huang, Mingyao Cui, Zhanwei Wang","submitted_at":"2026-06-03T08:16:14Z","abstract_excerpt":"Speculative inference (SPIN) was originally developed as an efficient architecture to accelerate Large Language Models (LLMs). In this work, we propose its distributed deployment to enable cooperative token generation in a multiuser edge system; its advantage is to effectively balance computational loads between resource-constrained devices and servers. The resulting architecture, termed Multi-access SPIN (Multi-SPIN), utilizes on-device small language models to generate and upload candidate token drafts, while an edge server operates the LLM to verify them in parallel batches. Given the sever"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04581","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/2606.04581/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":"2606.04581","created_at":"2026-06-04T01:09:19.156257+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.04581v1","created_at":"2026-06-04T01:09:19.156257+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04581","created_at":"2026-06-04T01:09:19.156257+00:00"},{"alias_kind":"pith_short_12","alias_value":"MT6VCDRK7ILJ","created_at":"2026-06-04T01:09:19.156257+00:00"},{"alias_kind":"pith_short_16","alias_value":"MT6VCDRK7ILJVJEE","created_at":"2026-06-04T01:09:19.156257+00:00"},{"alias_kind":"pith_short_8","alias_value":"MT6VCDRK","created_at":"2026-06-04T01:09:19.156257+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/MT6VCDRK7ILJVJEEJFVHOQYAAC","json":"https://pith.science/pith/MT6VCDRK7ILJVJEEJFVHOQYAAC.json","graph_json":"https://pith.science/api/pith-number/MT6VCDRK7ILJVJEEJFVHOQYAAC/graph.json","events_json":"https://pith.science/api/pith-number/MT6VCDRK7ILJVJEEJFVHOQYAAC/events.json","paper":"https://pith.science/paper/MT6VCDRK"},"agent_actions":{"view_html":"https://pith.science/pith/MT6VCDRK7ILJVJEEJFVHOQYAAC","download_json":"https://pith.science/pith/MT6VCDRK7ILJVJEEJFVHOQYAAC.json","view_paper":"https://pith.science/paper/MT6VCDRK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.04581&json=true","fetch_graph":"https://pith.science/api/pith-number/MT6VCDRK7ILJVJEEJFVHOQYAAC/graph.json","fetch_events":"https://pith.science/api/pith-number/MT6VCDRK7ILJVJEEJFVHOQYAAC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MT6VCDRK7ILJVJEEJFVHOQYAAC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MT6VCDRK7ILJVJEEJFVHOQYAAC/action/storage_attestation","attest_author":"https://pith.science/pith/MT6VCDRK7ILJVJEEJFVHOQYAAC/action/author_attestation","sign_citation":"https://pith.science/pith/MT6VCDRK7ILJVJEEJFVHOQYAAC/action/citation_signature","submit_replication":"https://pith.science/pith/MT6VCDRK7ILJVJEEJFVHOQYAAC/action/replication_record"}},"created_at":"2026-06-04T01:09:19.156257+00:00","updated_at":"2026-06-04T01:09:19.156257+00:00"}