{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HMO7UOPQDAURD5MAEQZ7KDFNDM","short_pith_number":"pith:HMO7UOPQ","schema_version":"1.0","canonical_sha256":"3b1dfa39f0182911f5802433f50cad1b1644d5f972fcf373531609ed881bcdda","source":{"kind":"arxiv","id":"2412.01447","version":1},"attestation_state":"computed","paper":{"title":"PLD+: Accelerating LLM inference by leveraging Language Model Artifacts","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anirudh Phukan, Apoorv Saxena, Shwetha Somasundaram","submitted_at":"2024-12-02T12:36:27Z","abstract_excerpt":"To reduce the latency associated with autoretrogressive LLM inference, speculative decoding has emerged as a novel decoding paradigm, where future tokens are drafted and verified in parallel. However, the practical deployment of speculative decoding is hindered by its requirements for additional computational resources and fine-tuning, which limits its out-of-the-box usability. To address these challenges, we present PLD+, a suite of novel algorithms developed to accelerate the inference process of LLMs, particularly for input-guided tasks. These tasks, which include code editing, text editing"},"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":"2412.01447","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-02T12:36:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"452723d32eb94e8f168898ee230aeb2c82e8db330da49c11a68ae3ec7508bfe0","abstract_canon_sha256":"12849d3d97365944839fbc0993545c8ac6a7b21ce36a00dff7eb9770eee0dac7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:43:13.210544Z","signature_b64":"1xth68vP0FH/VMDvGflBcOgUHJ/2XxvOg99mvhn7c+Eub3z/S9M2HOtifn0+At7LjvyMOF9mT59ewnoFncwpDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b1dfa39f0182911f5802433f50cad1b1644d5f972fcf373531609ed881bcdda","last_reissued_at":"2026-07-05T09:43:13.208778Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:43:13.208778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PLD+: Accelerating LLM inference by leveraging Language Model Artifacts","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anirudh Phukan, Apoorv Saxena, Shwetha Somasundaram","submitted_at":"2024-12-02T12:36:27Z","abstract_excerpt":"To reduce the latency associated with autoretrogressive LLM inference, speculative decoding has emerged as a novel decoding paradigm, where future tokens are drafted and verified in parallel. However, the practical deployment of speculative decoding is hindered by its requirements for additional computational resources and fine-tuning, which limits its out-of-the-box usability. To address these challenges, we present PLD+, a suite of novel algorithms developed to accelerate the inference process of LLMs, particularly for input-guided tasks. These tasks, which include code editing, text editing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01447","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/2412.01447/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":"2412.01447","created_at":"2026-07-05T09:43:13.209993+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.01447v1","created_at":"2026-07-05T09:43:13.209993+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01447","created_at":"2026-07-05T09:43:13.209993+00:00"},{"alias_kind":"pith_short_12","alias_value":"HMO7UOPQDAUR","created_at":"2026-07-05T09:43:13.209993+00:00"},{"alias_kind":"pith_short_16","alias_value":"HMO7UOPQDAURD5MA","created_at":"2026-07-05T09:43:13.209993+00:00"},{"alias_kind":"pith_short_8","alias_value":"HMO7UOPQ","created_at":"2026-07-05T09:43:13.209993+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06763","citing_title":"Trees from Marginals: Autoregressive drafting with factorized priors","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2606.18394","citing_title":"JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Parallel Tree Drafting","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HMO7UOPQDAURD5MAEQZ7KDFNDM","json":"https://pith.science/pith/HMO7UOPQDAURD5MAEQZ7KDFNDM.json","graph_json":"https://pith.science/api/pith-number/HMO7UOPQDAURD5MAEQZ7KDFNDM/graph.json","events_json":"https://pith.science/api/pith-number/HMO7UOPQDAURD5MAEQZ7KDFNDM/events.json","paper":"https://pith.science/paper/HMO7UOPQ"},"agent_actions":{"view_html":"https://pith.science/pith/HMO7UOPQDAURD5MAEQZ7KDFNDM","download_json":"https://pith.science/pith/HMO7UOPQDAURD5MAEQZ7KDFNDM.json","view_paper":"https://pith.science/paper/HMO7UOPQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.01447&json=true","fetch_graph":"https://pith.science/api/pith-number/HMO7UOPQDAURD5MAEQZ7KDFNDM/graph.json","fetch_events":"https://pith.science/api/pith-number/HMO7UOPQDAURD5MAEQZ7KDFNDM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HMO7UOPQDAURD5MAEQZ7KDFNDM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HMO7UOPQDAURD5MAEQZ7KDFNDM/action/storage_attestation","attest_author":"https://pith.science/pith/HMO7UOPQDAURD5MAEQZ7KDFNDM/action/author_attestation","sign_citation":"https://pith.science/pith/HMO7UOPQDAURD5MAEQZ7KDFNDM/action/citation_signature","submit_replication":"https://pith.science/pith/HMO7UOPQDAURD5MAEQZ7KDFNDM/action/replication_record"}},"created_at":"2026-07-05T09:43:13.209993+00:00","updated_at":"2026-07-05T09:43:13.209993+00:00"}