{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3PIBJYS3ZDFRIFKE6MB7M73CDA","short_pith_number":"pith:3PIBJYS3","schema_version":"1.0","canonical_sha256":"dbd014e25bc8cb141544f303f67f621808b763040ed45be8e3368bed5e579f5b","source":{"kind":"arxiv","id":"2409.01227","version":3},"attestation_state":"computed","paper":{"title":"Prompt Compression with Context-Aware Sentence Encoding for Fast and Improved LLM Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ali Etemad, Barys Liskavets, Mark Klibanov, Maxim Ushakov, Shane Luke, Shuvendu Roy","submitted_at":"2024-09-02T13:02:51Z","abstract_excerpt":"Large language models (LLMs) have triggered a new stream of research focusing on compressing the context length to reduce the computational cost while ensuring the retention of helpful information for LLMs to answer the given question. Token-based removal methods are one of the most prominent approaches in this direction, but risk losing the semantics of the context caused by intermediate token removal, especially under high compression ratios, while also facing challenges in computational efficiency. In this work, we propose context-aware prompt compression (CPC), a sentence-level prompt comp"},"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":"2409.01227","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-02T13:02:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ed049509016efc384f53569c06faeee10696f3fc79a0af439b05ff3d2211ba37","abstract_canon_sha256":"6a15b4b8d2d3edd3196148cea5930bad501840e98fda52bf5f09ba808bf51b7e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:36.245270Z","signature_b64":"a9TqLST76AGQvryv+mym0ZnE2esfuW8NV1nSGZ7Zbbp4fMuwMyXcP4rUYXyQxcIJ6QUg8KOgr22A1uehNcS8Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dbd014e25bc8cb141544f303f67f621808b763040ed45be8e3368bed5e579f5b","last_reissued_at":"2026-07-05T09:51:36.244739Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:36.244739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prompt Compression with Context-Aware Sentence Encoding for Fast and Improved LLM Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ali Etemad, Barys Liskavets, Mark Klibanov, Maxim Ushakov, Shane Luke, Shuvendu Roy","submitted_at":"2024-09-02T13:02:51Z","abstract_excerpt":"Large language models (LLMs) have triggered a new stream of research focusing on compressing the context length to reduce the computational cost while ensuring the retention of helpful information for LLMs to answer the given question. Token-based removal methods are one of the most prominent approaches in this direction, but risk losing the semantics of the context caused by intermediate token removal, especially under high compression ratios, while also facing challenges in computational efficiency. In this work, we propose context-aware prompt compression (CPC), a sentence-level prompt comp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.01227","kind":"arxiv","version":3},"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/2409.01227/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":"2409.01227","created_at":"2026-07-05T09:51:36.244810+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.01227v3","created_at":"2026-07-05T09:51:36.244810+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.01227","created_at":"2026-07-05T09:51:36.244810+00:00"},{"alias_kind":"pith_short_12","alias_value":"3PIBJYS3ZDFR","created_at":"2026-07-05T09:51:36.244810+00:00"},{"alias_kind":"pith_short_16","alias_value":"3PIBJYS3ZDFRIFKE","created_at":"2026-07-05T09:51:36.244810+00:00"},{"alias_kind":"pith_short_8","alias_value":"3PIBJYS3","created_at":"2026-07-05T09:51:36.244810+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.17512","citing_title":"ONTO: A Token-Efficient Columnar Notation for LLM Input Optimization","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3PIBJYS3ZDFRIFKE6MB7M73CDA","json":"https://pith.science/pith/3PIBJYS3ZDFRIFKE6MB7M73CDA.json","graph_json":"https://pith.science/api/pith-number/3PIBJYS3ZDFRIFKE6MB7M73CDA/graph.json","events_json":"https://pith.science/api/pith-number/3PIBJYS3ZDFRIFKE6MB7M73CDA/events.json","paper":"https://pith.science/paper/3PIBJYS3"},"agent_actions":{"view_html":"https://pith.science/pith/3PIBJYS3ZDFRIFKE6MB7M73CDA","download_json":"https://pith.science/pith/3PIBJYS3ZDFRIFKE6MB7M73CDA.json","view_paper":"https://pith.science/paper/3PIBJYS3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.01227&json=true","fetch_graph":"https://pith.science/api/pith-number/3PIBJYS3ZDFRIFKE6MB7M73CDA/graph.json","fetch_events":"https://pith.science/api/pith-number/3PIBJYS3ZDFRIFKE6MB7M73CDA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3PIBJYS3ZDFRIFKE6MB7M73CDA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3PIBJYS3ZDFRIFKE6MB7M73CDA/action/storage_attestation","attest_author":"https://pith.science/pith/3PIBJYS3ZDFRIFKE6MB7M73CDA/action/author_attestation","sign_citation":"https://pith.science/pith/3PIBJYS3ZDFRIFKE6MB7M73CDA/action/citation_signature","submit_replication":"https://pith.science/pith/3PIBJYS3ZDFRIFKE6MB7M73CDA/action/replication_record"}},"created_at":"2026-07-05T09:51:36.244810+00:00","updated_at":"2026-07-05T09:51:36.244810+00:00"}