{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:64P6T2NDIDEEA5BQR5M4NUYSLC","short_pith_number":"pith:64P6T2ND","schema_version":"1.0","canonical_sha256":"f71fe9e9a340c84074308f59c6d31258b9f124c783da16998cdb38e327c4c294","source":{"kind":"arxiv","id":"2508.15371","version":1},"attestation_state":"computed","paper":{"title":"Confidence-Modulated Speculative Decoding for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hetvi Waghela, Jaydip Sen, Subhasis Dasgupta","submitted_at":"2025-08-21T09:06:31Z","abstract_excerpt":"Speculative decoding has emerged as an effective approach for accelerating autoregressive inference by parallelizing token generation through a draft-then-verify paradigm. However, existing methods rely on static drafting lengths and rigid verification criteria, limiting their adaptability across varying model uncertainties and input complexities. This paper proposes an information-theoretic framework for speculative decoding based on confidence-modulated drafting. By leveraging entropy and margin-based uncertainty measures over the drafter's output distribution, the proposed method dynamicall"},"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":"2508.15371","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-21T09:06:31Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"2f6fb5dea5eb82ea1b3c4d8ae04bc17af7614873688736443fa4df8876702f3e","abstract_canon_sha256":"55ef1a3eabdc48af53bbbb528013de5b9be14c5e83534c4dd3b9f9afbf254304"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:04:55.251640Z","signature_b64":"0jjKEIkKmcHWxnPs0rNsWcJF/kfm2xT+H0Rjm4vIjEw8Rli6m2QHfl40WdE28y7m/QiqkgYEGG6DNvLdWrdfCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f71fe9e9a340c84074308f59c6d31258b9f124c783da16998cdb38e327c4c294","last_reissued_at":"2026-05-29T01:04:55.251152Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:04:55.251152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Confidence-Modulated Speculative Decoding for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hetvi Waghela, Jaydip Sen, Subhasis Dasgupta","submitted_at":"2025-08-21T09:06:31Z","abstract_excerpt":"Speculative decoding has emerged as an effective approach for accelerating autoregressive inference by parallelizing token generation through a draft-then-verify paradigm. However, existing methods rely on static drafting lengths and rigid verification criteria, limiting their adaptability across varying model uncertainties and input complexities. This paper proposes an information-theoretic framework for speculative decoding based on confidence-modulated drafting. By leveraging entropy and margin-based uncertainty measures over the drafter's output distribution, the proposed method dynamicall"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.15371","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/2508.15371/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":"2508.15371","created_at":"2026-05-29T01:04:55.251204+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.15371v1","created_at":"2026-05-29T01:04:55.251204+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.15371","created_at":"2026-05-29T01:04:55.251204+00:00"},{"alias_kind":"pith_short_12","alias_value":"64P6T2NDIDEE","created_at":"2026-05-29T01:04:55.251204+00:00"},{"alias_kind":"pith_short_16","alias_value":"64P6T2NDIDEEA5BQ","created_at":"2026-05-29T01:04:55.251204+00:00"},{"alias_kind":"pith_short_8","alias_value":"64P6T2ND","created_at":"2026-05-29T01:04:55.251204+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/64P6T2NDIDEEA5BQR5M4NUYSLC","json":"https://pith.science/pith/64P6T2NDIDEEA5BQR5M4NUYSLC.json","graph_json":"https://pith.science/api/pith-number/64P6T2NDIDEEA5BQR5M4NUYSLC/graph.json","events_json":"https://pith.science/api/pith-number/64P6T2NDIDEEA5BQR5M4NUYSLC/events.json","paper":"https://pith.science/paper/64P6T2ND"},"agent_actions":{"view_html":"https://pith.science/pith/64P6T2NDIDEEA5BQR5M4NUYSLC","download_json":"https://pith.science/pith/64P6T2NDIDEEA5BQR5M4NUYSLC.json","view_paper":"https://pith.science/paper/64P6T2ND","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.15371&json=true","fetch_graph":"https://pith.science/api/pith-number/64P6T2NDIDEEA5BQR5M4NUYSLC/graph.json","fetch_events":"https://pith.science/api/pith-number/64P6T2NDIDEEA5BQR5M4NUYSLC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/64P6T2NDIDEEA5BQR5M4NUYSLC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/64P6T2NDIDEEA5BQR5M4NUYSLC/action/storage_attestation","attest_author":"https://pith.science/pith/64P6T2NDIDEEA5BQR5M4NUYSLC/action/author_attestation","sign_citation":"https://pith.science/pith/64P6T2NDIDEEA5BQR5M4NUYSLC/action/citation_signature","submit_replication":"https://pith.science/pith/64P6T2NDIDEEA5BQR5M4NUYSLC/action/replication_record"}},"created_at":"2026-05-29T01:04:55.251204+00:00","updated_at":"2026-05-29T01:04:55.251204+00:00"}