{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MBUVUZT44IANZZMEDFGQZYA5O6","short_pith_number":"pith:MBUVUZT4","schema_version":"1.0","canonical_sha256":"60695a667ce200dce584194d0ce01d77878f3577d7b0f7b1c0fa7abf9f5addc9","source":{"kind":"arxiv","id":"2605.24168","version":1},"attestation_state":"computed","paper":{"title":"Inference Time Context Sparsity: Illusion or Opportunity?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Aditya Desai, Agniva Chowdhury, Anshumali Shrivastava, Ion Stoica, Joseph E. Gonzalez, Kumar Krishna Agrawal, Prithvi Dixit, Sahil Joshi","submitted_at":"2026-05-22T19:38:23Z","abstract_excerpt":"Sparsity has long been a central theme in LLM efficiency, but its role in context processing remains unresolved. As LLM workloads shift toward longer contexts and agentic interactions, the compute and memory bottlenecks of attention become increasingly critical, raising the question of whether these constraints are fundamental. Our position is that these constraints are artificial and unnecessary, and that the future of LLM inference lies in extreme but principled sparsity along the context dimension. This position is supported by several strands of empirical and theoretical evidence. First, w"},"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":"2605.24168","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-22T19:38:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6a93d9760e03bf69517859b83a8ede16fa42a9ff6f6f59b28b3fcfd112b42f65","abstract_canon_sha256":"562538cccdb93d67745974b44bab949f2f444e14d8aa8ac8b1978927c401401b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:02:50.300076Z","signature_b64":"4b8Sye6IUnIOTu6fbxLjr0S2ajOsz0Eko8o7cZc1TQm+DBYzdpIta25Twlyr/ivpjyne+bEYmvG7mLEDrpWoAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60695a667ce200dce584194d0ce01d77878f3577d7b0f7b1c0fa7abf9f5addc9","last_reissued_at":"2026-05-26T01:02:50.299368Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:02:50.299368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Inference Time Context Sparsity: Illusion or Opportunity?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Aditya Desai, Agniva Chowdhury, Anshumali Shrivastava, Ion Stoica, Joseph E. Gonzalez, Kumar Krishna Agrawal, Prithvi Dixit, Sahil Joshi","submitted_at":"2026-05-22T19:38:23Z","abstract_excerpt":"Sparsity has long been a central theme in LLM efficiency, but its role in context processing remains unresolved. As LLM workloads shift toward longer contexts and agentic interactions, the compute and memory bottlenecks of attention become increasingly critical, raising the question of whether these constraints are fundamental. Our position is that these constraints are artificial and unnecessary, and that the future of LLM inference lies in extreme but principled sparsity along the context dimension. This position is supported by several strands of empirical and theoretical evidence. First, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24168","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/2605.24168/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":"2605.24168","created_at":"2026-05-26T01:02:50.299479+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.24168v1","created_at":"2026-05-26T01:02:50.299479+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24168","created_at":"2026-05-26T01:02:50.299479+00:00"},{"alias_kind":"pith_short_12","alias_value":"MBUVUZT44IAN","created_at":"2026-05-26T01:02:50.299479+00:00"},{"alias_kind":"pith_short_16","alias_value":"MBUVUZT44IANZZME","created_at":"2026-05-26T01:02:50.299479+00:00"},{"alias_kind":"pith_short_8","alias_value":"MBUVUZT4","created_at":"2026-05-26T01:02:50.299479+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/MBUVUZT44IANZZMEDFGQZYA5O6","json":"https://pith.science/pith/MBUVUZT44IANZZMEDFGQZYA5O6.json","graph_json":"https://pith.science/api/pith-number/MBUVUZT44IANZZMEDFGQZYA5O6/graph.json","events_json":"https://pith.science/api/pith-number/MBUVUZT44IANZZMEDFGQZYA5O6/events.json","paper":"https://pith.science/paper/MBUVUZT4"},"agent_actions":{"view_html":"https://pith.science/pith/MBUVUZT44IANZZMEDFGQZYA5O6","download_json":"https://pith.science/pith/MBUVUZT44IANZZMEDFGQZYA5O6.json","view_paper":"https://pith.science/paper/MBUVUZT4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.24168&json=true","fetch_graph":"https://pith.science/api/pith-number/MBUVUZT44IANZZMEDFGQZYA5O6/graph.json","fetch_events":"https://pith.science/api/pith-number/MBUVUZT44IANZZMEDFGQZYA5O6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MBUVUZT44IANZZMEDFGQZYA5O6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MBUVUZT44IANZZMEDFGQZYA5O6/action/storage_attestation","attest_author":"https://pith.science/pith/MBUVUZT44IANZZMEDFGQZYA5O6/action/author_attestation","sign_citation":"https://pith.science/pith/MBUVUZT44IANZZMEDFGQZYA5O6/action/citation_signature","submit_replication":"https://pith.science/pith/MBUVUZT44IANZZMEDFGQZYA5O6/action/replication_record"}},"created_at":"2026-05-26T01:02:50.299479+00:00","updated_at":"2026-05-26T01:02:50.299479+00:00"}