{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZQ3PWNHKP6AC7CXEC3SMPLMCOE","short_pith_number":"pith:ZQ3PWNHK","schema_version":"1.0","canonical_sha256":"cc36fb34ea7f802f8ae416e4c7ad8271331c6c20ce613d2e85fd3000d9b08408","source":{"kind":"arxiv","id":"2404.00489","version":2},"attestation_state":"computed","paper":{"title":"Prompt-SAW: Leveraging Relation-Aware Graphs for Textual Prompt Compression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Di Wang, Guimin Hu, Keyuan Cheng, Lijie Hu, Lu Yu, Muhammad Asif Ali, Shu Yang, Tianhao Huang, Weimin Lyu, Yang Cao, Zhengping Li","submitted_at":"2024-03-30T23:07:58Z","abstract_excerpt":"Large Language Models (LLMs) have shown exceptional abilities for multiple different natural language processing tasks. While prompting is a crucial tool for LLM inference, we observe that there is a significant cost associated with exceedingly lengthy prompts. Existing attempts to compress lengthy prompts lead to substandard results in terms of readability/interpretability of the compressed prompt, with a detrimental impact on prompt utility. To address this, we propose PromptSAW: Prompt compresSion via Relation AWare graphs, an effective strategy for prompt compression over task-agnostic and"},"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":"2404.00489","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-30T23:07:58Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"29098286efa9c6bfa4537bea61b4641045a30aebdecaf7def92d18f4740188dd","abstract_canon_sha256":"e65909dbdb1fdcf2612d735777bc13780ddd3f74a4657f7f2e688b836bf4ff0d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:42.535101Z","signature_b64":"Su+DGtt4j6CAiXMuEDAg06ozODKopTss6RgvOdOm5Qewwj9UJsxAXfvMQPe4euWvA+HeuoyHukZ9GbVThL1GBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc36fb34ea7f802f8ae416e4c7ad8271331c6c20ce613d2e85fd3000d9b08408","last_reissued_at":"2026-07-05T09:21:42.534589Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:42.534589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prompt-SAW: Leveraging Relation-Aware Graphs for Textual Prompt Compression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Di Wang, Guimin Hu, Keyuan Cheng, Lijie Hu, Lu Yu, Muhammad Asif Ali, Shu Yang, Tianhao Huang, Weimin Lyu, Yang Cao, Zhengping Li","submitted_at":"2024-03-30T23:07:58Z","abstract_excerpt":"Large Language Models (LLMs) have shown exceptional abilities for multiple different natural language processing tasks. While prompting is a crucial tool for LLM inference, we observe that there is a significant cost associated with exceedingly lengthy prompts. Existing attempts to compress lengthy prompts lead to substandard results in terms of readability/interpretability of the compressed prompt, with a detrimental impact on prompt utility. To address this, we propose PromptSAW: Prompt compresSion via Relation AWare graphs, an effective strategy for prompt compression over task-agnostic and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00489","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/2404.00489/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":"2404.00489","created_at":"2026-07-05T09:21:42.534653+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.00489v2","created_at":"2026-07-05T09:21:42.534653+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00489","created_at":"2026-07-05T09:21:42.534653+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZQ3PWNHKP6AC","created_at":"2026-07-05T09:21:42.534653+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZQ3PWNHKP6AC7CXE","created_at":"2026-07-05T09:21:42.534653+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZQ3PWNHK","created_at":"2026-07-05T09:21:42.534653+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01241","citing_title":"Mapping Text to Multiplex Graph: Prompt Compression as L\\'evy Walk-Guided Graph Pruning","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZQ3PWNHKP6AC7CXEC3SMPLMCOE","json":"https://pith.science/pith/ZQ3PWNHKP6AC7CXEC3SMPLMCOE.json","graph_json":"https://pith.science/api/pith-number/ZQ3PWNHKP6AC7CXEC3SMPLMCOE/graph.json","events_json":"https://pith.science/api/pith-number/ZQ3PWNHKP6AC7CXEC3SMPLMCOE/events.json","paper":"https://pith.science/paper/ZQ3PWNHK"},"agent_actions":{"view_html":"https://pith.science/pith/ZQ3PWNHKP6AC7CXEC3SMPLMCOE","download_json":"https://pith.science/pith/ZQ3PWNHKP6AC7CXEC3SMPLMCOE.json","view_paper":"https://pith.science/paper/ZQ3PWNHK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.00489&json=true","fetch_graph":"https://pith.science/api/pith-number/ZQ3PWNHKP6AC7CXEC3SMPLMCOE/graph.json","fetch_events":"https://pith.science/api/pith-number/ZQ3PWNHKP6AC7CXEC3SMPLMCOE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZQ3PWNHKP6AC7CXEC3SMPLMCOE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZQ3PWNHKP6AC7CXEC3SMPLMCOE/action/storage_attestation","attest_author":"https://pith.science/pith/ZQ3PWNHKP6AC7CXEC3SMPLMCOE/action/author_attestation","sign_citation":"https://pith.science/pith/ZQ3PWNHKP6AC7CXEC3SMPLMCOE/action/citation_signature","submit_replication":"https://pith.science/pith/ZQ3PWNHKP6AC7CXEC3SMPLMCOE/action/replication_record"}},"created_at":"2026-07-05T09:21:42.534653+00:00","updated_at":"2026-07-05T09:21:42.534653+00:00"}