{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KKE2T73NCPYCEF33375C3UQAKR","short_pith_number":"pith:KKE2T73N","schema_version":"1.0","canonical_sha256":"5289a9ff6d13f022177bdffa2dd2005455804febbc4cc2487ce8896568bf63b1","source":{"kind":"arxiv","id":"2409.20181","version":2},"attestation_state":"computed","paper":{"title":"Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hai Zhao, Lefei Zhang, Luohe Shi, Yao Yao, Zuchao Li","submitted_at":"2024-09-30T10:48:20Z","abstract_excerpt":"Large language models (LLMs) have rapidly advanced and demonstrated impressive capabilities. In-Context Learning (ICL) and Parameter-Efficient Fine-Tuning (PEFT) are currently two mainstream methods for augmenting LLMs to downstream tasks. ICL typically constructs a few-shot learning scenario, either manually or by setting up a Retrieval-Augmented Generation (RAG) system, helping models quickly grasp domain knowledge or question-answering patterns without changing model parameters. However, this approach involves trade-offs, such as slower inference speed and increased space occupancy. PEFT as"},"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":"2409.20181","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-30T10:48:20Z","cross_cats_sorted":[],"title_canon_sha256":"aabeb2fbb81a685e4612c294a1951bf495ac240dea5e18ebd5b59613803a422c","abstract_canon_sha256":"f05fb8641e8ec9f0ab0c76148f0bfbfb0a794618ffdf8b89559c950bd9af5107"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:37:56.732985Z","signature_b64":"65mV/+2qjTFmjBMXoE2EtRRXDRmLJr1JjdYZ9hQKm8nAwbCFVpEX55FDmH+4QRRG3FFhm+zHCDfTrAybqiVODw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5289a9ff6d13f022177bdffa2dd2005455804febbc4cc2487ce8896568bf63b1","last_reissued_at":"2026-07-05T09:37:56.732496Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:37:56.732496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hai Zhao, Lefei Zhang, Luohe Shi, Yao Yao, Zuchao Li","submitted_at":"2024-09-30T10:48:20Z","abstract_excerpt":"Large language models (LLMs) have rapidly advanced and demonstrated impressive capabilities. In-Context Learning (ICL) and Parameter-Efficient Fine-Tuning (PEFT) are currently two mainstream methods for augmenting LLMs to downstream tasks. ICL typically constructs a few-shot learning scenario, either manually or by setting up a Retrieval-Augmented Generation (RAG) system, helping models quickly grasp domain knowledge or question-answering patterns without changing model parameters. However, this approach involves trade-offs, such as slower inference speed and increased space occupancy. PEFT as"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.20181","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/2409.20181/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":"2409.20181","created_at":"2026-07-05T09:37:56.732560+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.20181v2","created_at":"2026-07-05T09:37:56.732560+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.20181","created_at":"2026-07-05T09:37:56.732560+00:00"},{"alias_kind":"pith_short_12","alias_value":"KKE2T73NCPYC","created_at":"2026-07-05T09:37:56.732560+00:00"},{"alias_kind":"pith_short_16","alias_value":"KKE2T73NCPYCEF33","created_at":"2026-07-05T09:37:56.732560+00:00"},{"alias_kind":"pith_short_8","alias_value":"KKE2T73N","created_at":"2026-07-05T09:37:56.732560+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/KKE2T73NCPYCEF33375C3UQAKR","json":"https://pith.science/pith/KKE2T73NCPYCEF33375C3UQAKR.json","graph_json":"https://pith.science/api/pith-number/KKE2T73NCPYCEF33375C3UQAKR/graph.json","events_json":"https://pith.science/api/pith-number/KKE2T73NCPYCEF33375C3UQAKR/events.json","paper":"https://pith.science/paper/KKE2T73N"},"agent_actions":{"view_html":"https://pith.science/pith/KKE2T73NCPYCEF33375C3UQAKR","download_json":"https://pith.science/pith/KKE2T73NCPYCEF33375C3UQAKR.json","view_paper":"https://pith.science/paper/KKE2T73N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.20181&json=true","fetch_graph":"https://pith.science/api/pith-number/KKE2T73NCPYCEF33375C3UQAKR/graph.json","fetch_events":"https://pith.science/api/pith-number/KKE2T73NCPYCEF33375C3UQAKR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KKE2T73NCPYCEF33375C3UQAKR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KKE2T73NCPYCEF33375C3UQAKR/action/storage_attestation","attest_author":"https://pith.science/pith/KKE2T73NCPYCEF33375C3UQAKR/action/author_attestation","sign_citation":"https://pith.science/pith/KKE2T73NCPYCEF33375C3UQAKR/action/citation_signature","submit_replication":"https://pith.science/pith/KKE2T73NCPYCEF33375C3UQAKR/action/replication_record"}},"created_at":"2026-07-05T09:37:56.732560+00:00","updated_at":"2026-07-05T09:37:56.732560+00:00"}