{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7AV3Z75RPIXR36FRW3NLM56BYQ","short_pith_number":"pith:7AV3Z75R","schema_version":"1.0","canonical_sha256":"f82bbcffb17a2f1df8b1b6dab677c1c432031926582680cd47ab2882ac93dcfd","source":{"kind":"arxiv","id":"2606.28361","version":1},"attestation_state":"computed","paper":{"title":"ConCise: Training-Free Conclusion-Chain State Compression for Cost-Efficient Multi-Step RAG Services","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IT","math.IT"],"primary_cat":"cs.IR","authors_text":"Kuan Yan, Tian Wang, Weijia Jia, Zhiqing Tang","submitted_at":"2026-06-13T08:10:53Z","abstract_excerpt":"Multi-step retrieval-augmented generation (RAG) has been widely deployed as LLM-powered web services for complex question answering, where iterative retrieval-reasoning rounds deliver strong multi-hop accuracy. However, this paradigm causes historical documents and reasoning traces to accumulate across rounds, inflating cumulative input tokens approximately as $O(N^2)$ with progressively increasing noise density. In API-based service architectures, such growth directly amplifies per-request billing cost, network payload, and response latency. Existing compression approaches rely on pretrained "},"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":"2606.28361","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-06-13T08:10:53Z","cross_cats_sorted":["cs.AI","cs.IT","math.IT"],"title_canon_sha256":"525300392b4a6ea3c78f4cf87153668afcfe02e94c03c41f2b275e8ed29923ce","abstract_canon_sha256":"ee84895498ee252f016a917436ae2433135e7aa9cf76c33864dfddd12c53d817"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T00:15:11.988012Z","signature_b64":"e2yAy71bfh9Bi3pwSIOvnm72tH671nApSY/CXIpsN0epTBvn43bncvQbv2N7TNS0szTGLaVK1PbqkJLXJnfSDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f82bbcffb17a2f1df8b1b6dab677c1c432031926582680cd47ab2882ac93dcfd","last_reissued_at":"2026-06-30T00:15:11.987653Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T00:15:11.987653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ConCise: Training-Free Conclusion-Chain State Compression for Cost-Efficient Multi-Step RAG Services","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IT","math.IT"],"primary_cat":"cs.IR","authors_text":"Kuan Yan, Tian Wang, Weijia Jia, Zhiqing Tang","submitted_at":"2026-06-13T08:10:53Z","abstract_excerpt":"Multi-step retrieval-augmented generation (RAG) has been widely deployed as LLM-powered web services for complex question answering, where iterative retrieval-reasoning rounds deliver strong multi-hop accuracy. However, this paradigm causes historical documents and reasoning traces to accumulate across rounds, inflating cumulative input tokens approximately as $O(N^2)$ with progressively increasing noise density. In API-based service architectures, such growth directly amplifies per-request billing cost, network payload, and response latency. Existing compression approaches rely on pretrained "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28361","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/2606.28361/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":"2606.28361","created_at":"2026-06-30T00:15:11.987709+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.28361v1","created_at":"2026-06-30T00:15:11.987709+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28361","created_at":"2026-06-30T00:15:11.987709+00:00"},{"alias_kind":"pith_short_12","alias_value":"7AV3Z75RPIXR","created_at":"2026-06-30T00:15:11.987709+00:00"},{"alias_kind":"pith_short_16","alias_value":"7AV3Z75RPIXR36FR","created_at":"2026-06-30T00:15:11.987709+00:00"},{"alias_kind":"pith_short_8","alias_value":"7AV3Z75R","created_at":"2026-06-30T00:15:11.987709+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/7AV3Z75RPIXR36FRW3NLM56BYQ","json":"https://pith.science/pith/7AV3Z75RPIXR36FRW3NLM56BYQ.json","graph_json":"https://pith.science/api/pith-number/7AV3Z75RPIXR36FRW3NLM56BYQ/graph.json","events_json":"https://pith.science/api/pith-number/7AV3Z75RPIXR36FRW3NLM56BYQ/events.json","paper":"https://pith.science/paper/7AV3Z75R"},"agent_actions":{"view_html":"https://pith.science/pith/7AV3Z75RPIXR36FRW3NLM56BYQ","download_json":"https://pith.science/pith/7AV3Z75RPIXR36FRW3NLM56BYQ.json","view_paper":"https://pith.science/paper/7AV3Z75R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.28361&json=true","fetch_graph":"https://pith.science/api/pith-number/7AV3Z75RPIXR36FRW3NLM56BYQ/graph.json","fetch_events":"https://pith.science/api/pith-number/7AV3Z75RPIXR36FRW3NLM56BYQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7AV3Z75RPIXR36FRW3NLM56BYQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7AV3Z75RPIXR36FRW3NLM56BYQ/action/storage_attestation","attest_author":"https://pith.science/pith/7AV3Z75RPIXR36FRW3NLM56BYQ/action/author_attestation","sign_citation":"https://pith.science/pith/7AV3Z75RPIXR36FRW3NLM56BYQ/action/citation_signature","submit_replication":"https://pith.science/pith/7AV3Z75RPIXR36FRW3NLM56BYQ/action/replication_record"}},"created_at":"2026-06-30T00:15:11.987709+00:00","updated_at":"2026-06-30T00:15:11.987709+00:00"}