{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6PIULZTIKKSVQRSENXFRMTXNIQ","short_pith_number":"pith:6PIULZTI","schema_version":"1.0","canonical_sha256":"f3d145e66852a55846446dcb164eed442aa62c97d2ffbfc0c4678ba8e93766c0","source":{"kind":"arxiv","id":"2606.27743","version":1},"attestation_state":"computed","paper":{"title":"End-to-End Dynamic Sparsity for Resource-Adaptive LLM Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.IR","authors_text":"Chonglin Sun, Fei Tian, Frank Shyu, Jinhao Duan, Luke Simon, Mingfu Liang, Parish Aggarwal, Ruichen Zhang, Sandeep Pandey, Tianlong Chen, Xiaohan Wei, Xi Liu, Yuhang Chen, Yunchen Pu","submitted_at":"2026-06-26T05:48:21Z","abstract_excerpt":"Large Language Models (LLMs) inference is typically deployed under a static resource assumption, where models execute a fixed computational graph regardless of the runtime environment. However, real-world cloud infrastructure is inherently dynamic, characterized by fluctuating availability (e.g., spot instance preemption) and tiered Quality-of-Service requirements. In such volatile settings, static models are inflexible: they either crash under resource constraints or waste compute on redundant operations. To bridge this gap, we propose Learning to Allocate (L2A), an end-to-end framework for r"},"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":"2606.27743","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-06-26T05:48:21Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4456f62140c6d32f2639d4e062b10748a32200aa65ec12d3176f4a6cb0b30cbf","abstract_canon_sha256":"f3bdf391f1536a40d523f440447a9a2933eb2baf7df27bb465e9f38dab2b46bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T01:14:47.255970Z","signature_b64":"ddXoNtQNkzZEGTuIWDlnru2bV/Bi14wWyw5NDwGwd3wx/1JtzF9lRHU+nPckQTKOiH7vNpoZtPrrfnGHToyKCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3d145e66852a55846446dcb164eed442aa62c97d2ffbfc0c4678ba8e93766c0","last_reissued_at":"2026-06-29T01:14:47.255553Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T01:14:47.255553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-End Dynamic Sparsity for Resource-Adaptive LLM Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.IR","authors_text":"Chonglin Sun, Fei Tian, Frank Shyu, Jinhao Duan, Luke Simon, Mingfu Liang, Parish Aggarwal, Ruichen Zhang, Sandeep Pandey, Tianlong Chen, Xiaohan Wei, Xi Liu, Yuhang Chen, Yunchen Pu","submitted_at":"2026-06-26T05:48:21Z","abstract_excerpt":"Large Language Models (LLMs) inference is typically deployed under a static resource assumption, where models execute a fixed computational graph regardless of the runtime environment. However, real-world cloud infrastructure is inherently dynamic, characterized by fluctuating availability (e.g., spot instance preemption) and tiered Quality-of-Service requirements. In such volatile settings, static models are inflexible: they either crash under resource constraints or waste compute on redundant operations. To bridge this gap, we propose Learning to Allocate (L2A), an end-to-end framework for r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27743","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/2606.27743/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":"2606.27743","created_at":"2026-06-29T01:14:47.255609+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.27743v1","created_at":"2026-06-29T01:14:47.255609+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27743","created_at":"2026-06-29T01:14:47.255609+00:00"},{"alias_kind":"pith_short_12","alias_value":"6PIULZTIKKSV","created_at":"2026-06-29T01:14:47.255609+00:00"},{"alias_kind":"pith_short_16","alias_value":"6PIULZTIKKSVQRSE","created_at":"2026-06-29T01:14:47.255609+00:00"},{"alias_kind":"pith_short_8","alias_value":"6PIULZTI","created_at":"2026-06-29T01:14:47.255609+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/6PIULZTIKKSVQRSENXFRMTXNIQ","json":"https://pith.science/pith/6PIULZTIKKSVQRSENXFRMTXNIQ.json","graph_json":"https://pith.science/api/pith-number/6PIULZTIKKSVQRSENXFRMTXNIQ/graph.json","events_json":"https://pith.science/api/pith-number/6PIULZTIKKSVQRSENXFRMTXNIQ/events.json","paper":"https://pith.science/paper/6PIULZTI"},"agent_actions":{"view_html":"https://pith.science/pith/6PIULZTIKKSVQRSENXFRMTXNIQ","download_json":"https://pith.science/pith/6PIULZTIKKSVQRSENXFRMTXNIQ.json","view_paper":"https://pith.science/paper/6PIULZTI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.27743&json=true","fetch_graph":"https://pith.science/api/pith-number/6PIULZTIKKSVQRSENXFRMTXNIQ/graph.json","fetch_events":"https://pith.science/api/pith-number/6PIULZTIKKSVQRSENXFRMTXNIQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6PIULZTIKKSVQRSENXFRMTXNIQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6PIULZTIKKSVQRSENXFRMTXNIQ/action/storage_attestation","attest_author":"https://pith.science/pith/6PIULZTIKKSVQRSENXFRMTXNIQ/action/author_attestation","sign_citation":"https://pith.science/pith/6PIULZTIKKSVQRSENXFRMTXNIQ/action/citation_signature","submit_replication":"https://pith.science/pith/6PIULZTIKKSVQRSENXFRMTXNIQ/action/replication_record"}},"created_at":"2026-06-29T01:14:47.255609+00:00","updated_at":"2026-06-29T01:14:47.255609+00:00"}