{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GUKJCMCDU7QA7TYD3CWX2TUZPB","short_pith_number":"pith:GUKJCMCD","schema_version":"1.0","canonical_sha256":"3514913043a7e00fcf03d8ad7d4e997869bd84432dd294728fcca96c089cae15","source":{"kind":"arxiv","id":"2606.23961","version":1},"attestation_state":"computed","paper":{"title":"Forget Without Compromise: Nexus Sampling for Streaming KV-Cache Eviction Under Fixed Budgets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anshumali Shrivastava, Duc Duong, Hoang Anh Duy Le, Jianwen Xie, Zhaozhuo Xu","submitted_at":"2026-06-22T21:42:51Z","abstract_excerpt":"Long-context and agentic LLM workloads push the KV cache past any fixed memory budget, forcing the inference stack to permanently evict tokens at every step of a continuous-inference stream. Existing methods all share the same template, a per-step direct-attention score followed by deterministic top-$K$ selection, which converts a single below-cutoff step into an irreversible verdict and permanently erases any subtly important token that direct attention cannot single out from noise. To address this challenge, we propose Nexus Sampling, a training-free eviction method that pairs Nexus scoring,"},"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":"2606.23961","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T21:42:51Z","cross_cats_sorted":[],"title_canon_sha256":"889f0268f1b5e77564bb767ba6ce361d49b52231aee373f03510b97ce41a652e","abstract_canon_sha256":"2c1b7ef25981ef064f8af6f8ea5819cb0264d6f718fb152d6ea35f1690b1bfcc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T00:14:31.449334Z","signature_b64":"GbADDlE4Pk1jt/VL2eo/qQmBNUSYPEhakO263smNQt2mz8ZDfU1Dh2SZxuIxXK0qPLCgOCXBIl4s4o7s2gNyDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3514913043a7e00fcf03d8ad7d4e997869bd84432dd294728fcca96c089cae15","last_reissued_at":"2026-06-24T00:14:31.448928Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T00:14:31.448928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Forget Without Compromise: Nexus Sampling for Streaming KV-Cache Eviction Under Fixed Budgets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anshumali Shrivastava, Duc Duong, Hoang Anh Duy Le, Jianwen Xie, Zhaozhuo Xu","submitted_at":"2026-06-22T21:42:51Z","abstract_excerpt":"Long-context and agentic LLM workloads push the KV cache past any fixed memory budget, forcing the inference stack to permanently evict tokens at every step of a continuous-inference stream. Existing methods all share the same template, a per-step direct-attention score followed by deterministic top-$K$ selection, which converts a single below-cutoff step into an irreversible verdict and permanently erases any subtly important token that direct attention cannot single out from noise. To address this challenge, we propose Nexus Sampling, a training-free eviction method that pairs Nexus scoring,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23961","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/2606.23961/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":"2606.23961","created_at":"2026-06-24T00:14:31.448991+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.23961v1","created_at":"2026-06-24T00:14:31.448991+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23961","created_at":"2026-06-24T00:14:31.448991+00:00"},{"alias_kind":"pith_short_12","alias_value":"GUKJCMCDU7QA","created_at":"2026-06-24T00:14:31.448991+00:00"},{"alias_kind":"pith_short_16","alias_value":"GUKJCMCDU7QA7TYD","created_at":"2026-06-24T00:14:31.448991+00:00"},{"alias_kind":"pith_short_8","alias_value":"GUKJCMCD","created_at":"2026-06-24T00:14:31.448991+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/GUKJCMCDU7QA7TYD3CWX2TUZPB","json":"https://pith.science/pith/GUKJCMCDU7QA7TYD3CWX2TUZPB.json","graph_json":"https://pith.science/api/pith-number/GUKJCMCDU7QA7TYD3CWX2TUZPB/graph.json","events_json":"https://pith.science/api/pith-number/GUKJCMCDU7QA7TYD3CWX2TUZPB/events.json","paper":"https://pith.science/paper/GUKJCMCD"},"agent_actions":{"view_html":"https://pith.science/pith/GUKJCMCDU7QA7TYD3CWX2TUZPB","download_json":"https://pith.science/pith/GUKJCMCDU7QA7TYD3CWX2TUZPB.json","view_paper":"https://pith.science/paper/GUKJCMCD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.23961&json=true","fetch_graph":"https://pith.science/api/pith-number/GUKJCMCDU7QA7TYD3CWX2TUZPB/graph.json","fetch_events":"https://pith.science/api/pith-number/GUKJCMCDU7QA7TYD3CWX2TUZPB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GUKJCMCDU7QA7TYD3CWX2TUZPB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GUKJCMCDU7QA7TYD3CWX2TUZPB/action/storage_attestation","attest_author":"https://pith.science/pith/GUKJCMCDU7QA7TYD3CWX2TUZPB/action/author_attestation","sign_citation":"https://pith.science/pith/GUKJCMCDU7QA7TYD3CWX2TUZPB/action/citation_signature","submit_replication":"https://pith.science/pith/GUKJCMCDU7QA7TYD3CWX2TUZPB/action/replication_record"}},"created_at":"2026-06-24T00:14:31.448991+00:00","updated_at":"2026-06-24T00:14:31.448991+00:00"}