{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LE7V35AFBMZDBHGL2VDYRZISVX","short_pith_number":"pith:LE7V35AF","schema_version":"1.0","canonical_sha256":"593f5df4050b32309ccbd54788e512add9665ec7f250411bee057f66d4f8d263","source":{"kind":"arxiv","id":"2602.10431","version":4},"attestation_state":"computed","paper":{"title":"QTALE: Quantization-Robust Token-Adaptive Layer Execution for LLMs","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jinheon Choi, Kanghyun Noh, Yulhwa Kim","submitted_at":"2026-02-11T02:19:11Z","abstract_excerpt":"Large language models (LLMs) demand substantial computational and memory resources, posing challenges for efficient deployment. Two complementary approaches have emerged to address these issues: token-adaptive layer execution, which reduces floating-point operations (FLOPs) by selectively bypassing layers, and quantization, which lowers memory footprint by reducing weight precision. However, naively integrating these techniques leads to additional accuracy degradation due to reduced redundancy in token-adaptive models. We propose QTALE (Quantization-Robust Token-Adaptive Layer Execution for LL"},"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":"2602.10431","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-11T02:19:11Z","cross_cats_sorted":[],"title_canon_sha256":"1d9c2af1d4aa86c2abc156368b53fe4578c2c485429ca2b9b7806bb4d19352c1","abstract_canon_sha256":"8ea4f0e0c4921a6adef7352a14acf96b46c06a8d59ef30649c3b1bf93dd40458"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:16:51.633683Z","signature_b64":"pBgNLAtZD/LAqATeq7t40w+yj+k6YrIac3DLDiYfvP3jLFgBLaXy/wvxOa94ChzpszSyapCNzrah+XlQPIuXCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"593f5df4050b32309ccbd54788e512add9665ec7f250411bee057f66d4f8d263","last_reissued_at":"2026-07-03T01:16:51.633109Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:16:51.633109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"QTALE: Quantization-Robust Token-Adaptive Layer Execution for LLMs","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jinheon Choi, Kanghyun Noh, Yulhwa Kim","submitted_at":"2026-02-11T02:19:11Z","abstract_excerpt":"Large language models (LLMs) demand substantial computational and memory resources, posing challenges for efficient deployment. Two complementary approaches have emerged to address these issues: token-adaptive layer execution, which reduces floating-point operations (FLOPs) by selectively bypassing layers, and quantization, which lowers memory footprint by reducing weight precision. However, naively integrating these techniques leads to additional accuracy degradation due to reduced redundancy in token-adaptive models. We propose QTALE (Quantization-Robust Token-Adaptive Layer Execution for LL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.10431","kind":"arxiv","version":4},"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/2602.10431/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":"2602.10431","created_at":"2026-07-03T01:16:51.633172+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.10431v4","created_at":"2026-07-03T01:16:51.633172+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.10431","created_at":"2026-07-03T01:16:51.633172+00:00"},{"alias_kind":"pith_short_12","alias_value":"LE7V35AFBMZD","created_at":"2026-07-03T01:16:51.633172+00:00"},{"alias_kind":"pith_short_16","alias_value":"LE7V35AFBMZDBHGL","created_at":"2026-07-03T01:16:51.633172+00:00"},{"alias_kind":"pith_short_8","alias_value":"LE7V35AF","created_at":"2026-07-03T01:16:51.633172+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/LE7V35AFBMZDBHGL2VDYRZISVX","json":"https://pith.science/pith/LE7V35AFBMZDBHGL2VDYRZISVX.json","graph_json":"https://pith.science/api/pith-number/LE7V35AFBMZDBHGL2VDYRZISVX/graph.json","events_json":"https://pith.science/api/pith-number/LE7V35AFBMZDBHGL2VDYRZISVX/events.json","paper":"https://pith.science/paper/LE7V35AF"},"agent_actions":{"view_html":"https://pith.science/pith/LE7V35AFBMZDBHGL2VDYRZISVX","download_json":"https://pith.science/pith/LE7V35AFBMZDBHGL2VDYRZISVX.json","view_paper":"https://pith.science/paper/LE7V35AF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.10431&json=true","fetch_graph":"https://pith.science/api/pith-number/LE7V35AFBMZDBHGL2VDYRZISVX/graph.json","fetch_events":"https://pith.science/api/pith-number/LE7V35AFBMZDBHGL2VDYRZISVX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LE7V35AFBMZDBHGL2VDYRZISVX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LE7V35AFBMZDBHGL2VDYRZISVX/action/storage_attestation","attest_author":"https://pith.science/pith/LE7V35AFBMZDBHGL2VDYRZISVX/action/author_attestation","sign_citation":"https://pith.science/pith/LE7V35AFBMZDBHGL2VDYRZISVX/action/citation_signature","submit_replication":"https://pith.science/pith/LE7V35AFBMZDBHGL2VDYRZISVX/action/replication_record"}},"created_at":"2026-07-03T01:16:51.633172+00:00","updated_at":"2026-07-03T01:16:51.633172+00:00"}