{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:TXJNI7UXOOJCPLZ7TZQJ7WZEMY","short_pith_number":"pith:TXJNI7UX","canonical_record":{"source":{"id":"2606.11244","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2026-06-04T22:38:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"53a82636115a434647eff5e6377e6898003a4d0c22f005f959371d1621ef54b8","abstract_canon_sha256":"01f30ef06c0fb13155b810793aa0689737f24a979c8a83d384485365a513025f"},"schema_version":"1.0"},"canonical_sha256":"9dd2d47e97739227af3f9e609fdb24663922276ba5df90b2e850148a692a2313","source":{"kind":"arxiv","id":"2606.11244","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.11244","created_at":"2026-06-11T00:08:14Z"},{"alias_kind":"arxiv_version","alias_value":"2606.11244v1","created_at":"2026-06-11T00:08:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11244","created_at":"2026-06-11T00:08:14Z"},{"alias_kind":"pith_short_12","alias_value":"TXJNI7UXOOJC","created_at":"2026-06-11T00:08:14Z"},{"alias_kind":"pith_short_16","alias_value":"TXJNI7UXOOJCPLZ7","created_at":"2026-06-11T00:08:14Z"},{"alias_kind":"pith_short_8","alias_value":"TXJNI7UX","created_at":"2026-06-11T00:08:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:TXJNI7UXOOJCPLZ7TZQJ7WZEMY","target":"record","payload":{"canonical_record":{"source":{"id":"2606.11244","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2026-06-04T22:38:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"53a82636115a434647eff5e6377e6898003a4d0c22f005f959371d1621ef54b8","abstract_canon_sha256":"01f30ef06c0fb13155b810793aa0689737f24a979c8a83d384485365a513025f"},"schema_version":"1.0"},"canonical_sha256":"9dd2d47e97739227af3f9e609fdb24663922276ba5df90b2e850148a692a2313","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T00:08:14.621827Z","signature_b64":"7AVLrUMQWPKEO0FowGTfi3eYyOeNrXY8AHYhKDdXF5L0OiqU3eKhFc9akTpTY5N6hyahlsrfrKUbuFFJfwRoBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9dd2d47e97739227af3f9e609fdb24663922276ba5df90b2e850148a692a2313","last_reissued_at":"2026-06-11T00:08:14.620981Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T00:08:14.620981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.11244","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-11T00:08:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nVfhN6ztfXzrbm9d/Y61dGDxeJ6j4FX58yLLWhRRZtz2wY9c0S9w8z82YF19QmNVtoEcMDEXFJUVF20UnrqXCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T04:19:41.902006Z"},"content_sha256":"90eed7432dac7c1f0960ce954cc82ccaabf05e967ceecb35cbf6fc7f10cf3bc9","schema_version":"1.0","event_id":"sha256:90eed7432dac7c1f0960ce954cc82ccaabf05e967ceecb35cbf6fc7f10cf3bc9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:TXJNI7UXOOJCPLZ7TZQJ7WZEMY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SPEAR: A System for Post-Quantization Error-Adaptive Recovery Enabling Efficient Low-Bit LLM Serving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.AR","authors_text":"Guosheng Hu, Hongyuan Liu, Junming Shao, Qinli Yang, Yawei Li, Zhiqiang Que","submitted_at":"2026-06-04T22:38:53Z","abstract_excerpt":"Efficient large language model (LLM) serving is increasingly constrained by deployment cost. Quantization is a key technique for reducing serving cost, yet even state-of-the-art 4-bit quantizers exhibit a noticeable quality gap from FP16, particularly for smaller models where low-bit serving is most beneficial. We identify a fundamental cause of this gap: quantization error is highly input-dependent and varies substantially across tokens, while existing post-quantization compensation methods are static and apply identical corrections to all inputs. As a result, easy tokens are over-corrected w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11244","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/2606.11244/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-11T00:08:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zNyk/V5+BIltRDjXB6RMSX69xKfjIcLmX8OuStEsLzwgWndelbPRK7Xr3zsJhKZi5tW3N0v2eIRLB6ATFsEnDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T04:19:41.902745Z"},"content_sha256":"977356ec03ddb1176e99f0bff652e20e24ce50dd8216f52bae5c92b9819af8a0","schema_version":"1.0","event_id":"sha256:977356ec03ddb1176e99f0bff652e20e24ce50dd8216f52bae5c92b9819af8a0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TXJNI7UXOOJCPLZ7TZQJ7WZEMY/bundle.json","state_url":"https://pith.science/pith/TXJNI7UXOOJCPLZ7TZQJ7WZEMY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TXJNI7UXOOJCPLZ7TZQJ7WZEMY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-12T04:19:41Z","links":{"resolver":"https://pith.science/pith/TXJNI7UXOOJCPLZ7TZQJ7WZEMY","bundle":"https://pith.science/pith/TXJNI7UXOOJCPLZ7TZQJ7WZEMY/bundle.json","state":"https://pith.science/pith/TXJNI7UXOOJCPLZ7TZQJ7WZEMY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TXJNI7UXOOJCPLZ7TZQJ7WZEMY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TXJNI7UXOOJCPLZ7TZQJ7WZEMY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"01f30ef06c0fb13155b810793aa0689737f24a979c8a83d384485365a513025f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2026-06-04T22:38:53Z","title_canon_sha256":"53a82636115a434647eff5e6377e6898003a4d0c22f005f959371d1621ef54b8"},"schema_version":"1.0","source":{"id":"2606.11244","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.11244","created_at":"2026-06-11T00:08:14Z"},{"alias_kind":"arxiv_version","alias_value":"2606.11244v1","created_at":"2026-06-11T00:08:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11244","created_at":"2026-06-11T00:08:14Z"},{"alias_kind":"pith_short_12","alias_value":"TXJNI7UXOOJC","created_at":"2026-06-11T00:08:14Z"},{"alias_kind":"pith_short_16","alias_value":"TXJNI7UXOOJCPLZ7","created_at":"2026-06-11T00:08:14Z"},{"alias_kind":"pith_short_8","alias_value":"TXJNI7UX","created_at":"2026-06-11T00:08:14Z"}],"graph_snapshots":[{"event_id":"sha256:977356ec03ddb1176e99f0bff652e20e24ce50dd8216f52bae5c92b9819af8a0","target":"graph","created_at":"2026-06-11T00:08:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.11244/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Efficient large language model (LLM) serving is increasingly constrained by deployment cost. Quantization is a key technique for reducing serving cost, yet even state-of-the-art 4-bit quantizers exhibit a noticeable quality gap from FP16, particularly for smaller models where low-bit serving is most beneficial. We identify a fundamental cause of this gap: quantization error is highly input-dependent and varies substantially across tokens, while existing post-quantization compensation methods are static and apply identical corrections to all inputs. As a result, easy tokens are over-corrected w","authors_text":"Guosheng Hu, Hongyuan Liu, Junming Shao, Qinli Yang, Yawei Li, Zhiqiang Que","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2026-06-04T22:38:53Z","title":"SPEAR: A System for Post-Quantization Error-Adaptive Recovery Enabling Efficient Low-Bit LLM Serving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11244","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:90eed7432dac7c1f0960ce954cc82ccaabf05e967ceecb35cbf6fc7f10cf3bc9","target":"record","created_at":"2026-06-11T00:08:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"01f30ef06c0fb13155b810793aa0689737f24a979c8a83d384485365a513025f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2026-06-04T22:38:53Z","title_canon_sha256":"53a82636115a434647eff5e6377e6898003a4d0c22f005f959371d1621ef54b8"},"schema_version":"1.0","source":{"id":"2606.11244","kind":"arxiv","version":1}},"canonical_sha256":"9dd2d47e97739227af3f9e609fdb24663922276ba5df90b2e850148a692a2313","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9dd2d47e97739227af3f9e609fdb24663922276ba5df90b2e850148a692a2313","first_computed_at":"2026-06-11T00:08:14.620981Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-11T00:08:14.620981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7AVLrUMQWPKEO0FowGTfi3eYyOeNrXY8AHYhKDdXF5L0OiqU3eKhFc9akTpTY5N6hyahlsrfrKUbuFFJfwRoBw==","signature_status":"signed_v1","signed_at":"2026-06-11T00:08:14.621827Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.11244","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:90eed7432dac7c1f0960ce954cc82ccaabf05e967ceecb35cbf6fc7f10cf3bc9","sha256:977356ec03ddb1176e99f0bff652e20e24ce50dd8216f52bae5c92b9819af8a0"],"state_sha256":"c554d53ca5c9954bc315c85accb34b7db8505541365f227a3c49a8f89f7d379a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0lkHa/xQaLzN+Nt0LBoIfYoqqVImqbtHNqF4T87ivAgjEGmsRYoXM4nbAWFq95MNvVhFOYyeGxKcotbpyrJ1Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-12T04:19:41.905896Z","bundle_sha256":"8f0f53d423556f3aff3fbcbda7edd48188b7c9b5f630d60201e2677ddef5c189"}}