{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SZ5F37BQHOYBHQILB7ZU3VXL3V","short_pith_number":"pith:SZ5F37BQ","canonical_record":{"source":{"id":"2608.02691","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-03T09:24:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b1356e56d35267fbdad1053a90d4453ff16c0a88480c5302fc3342a988e2703c","abstract_canon_sha256":"74145ea453b317bfc7f9d6e3c03257acde870eceda69542a36eb57cfb349ed64"},"schema_version":"1.0"},"canonical_sha256":"967a5dfc303bb013c10b0ff34dd6ebdd5c69906ee635df8913f372fd8ed9260a","source":{"kind":"arxiv","id":"2608.02691","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.02691","created_at":"2026-08-05T00:39:25Z"},{"alias_kind":"arxiv_version","alias_value":"2608.02691v1","created_at":"2026-08-05T00:39:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02691","created_at":"2026-08-05T00:39:25Z"},{"alias_kind":"pith_short_12","alias_value":"SZ5F37BQHOYB","created_at":"2026-08-05T00:39:25Z"},{"alias_kind":"pith_short_16","alias_value":"SZ5F37BQHOYBHQIL","created_at":"2026-08-05T00:39:25Z"},{"alias_kind":"pith_short_8","alias_value":"SZ5F37BQ","created_at":"2026-08-05T00:39:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SZ5F37BQHOYBHQILB7ZU3VXL3V","target":"record","payload":{"canonical_record":{"source":{"id":"2608.02691","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-03T09:24:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b1356e56d35267fbdad1053a90d4453ff16c0a88480c5302fc3342a988e2703c","abstract_canon_sha256":"74145ea453b317bfc7f9d6e3c03257acde870eceda69542a36eb57cfb349ed64"},"schema_version":"1.0"},"canonical_sha256":"967a5dfc303bb013c10b0ff34dd6ebdd5c69906ee635df8913f372fd8ed9260a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T00:39:25.660783Z","signature_b64":"XJdzpoY8p3CoketVnaYLMOcu1Gzb56v9R0nCfZedcukzdumHrM1oMLV2GzLMG80LEr81IYEeWoEsZtJooznDAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"967a5dfc303bb013c10b0ff34dd6ebdd5c69906ee635df8913f372fd8ed9260a","last_reissued_at":"2026-08-05T00:39:25.656903Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T00:39:25.656903Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.02691","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":"2026-08-05T00:39:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z10kD5AxsyG1ICubheiTmmBTQLYWIQAKl1MmCG5X4va09TBryoOIhDx6m96uOvKRTAVHPJH/dIAkBNxumkAhDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T09:48:05.911068Z"},"content_sha256":"37c7d6b78dcd4e85fe47f693f30dc315e1f7cc4ca64c69987d188bb6a23b498e","schema_version":"1.0","event_id":"sha256:37c7d6b78dcd4e85fe47f693f30dc315e1f7cc4ca64c69987d188bb6a23b498e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SZ5F37BQHOYBHQILB7ZU3VXL3V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Output-Aware Rotation for INT2 KV-Cache Quantization","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Minsoo Cheong, Murali Annavaram, Sai Praneeth Karimireddy, Sungjoo Yoo, Sunwoo Lee, Vincent-Daniel Yun, Woosang Lim","submitted_at":"2026-08-03T09:24:23Z","abstract_excerpt":"The key-value (KV) cache has become a major memory and bandwidth bottleneck in long-context large language model inference, making ultra-low-bit quantization increasingly important. However, existing rotation-based INT2 methods optimize cache statistics or proxy errors before the complete attention readout, even though the model is ultimately affected by the error propagated through attention and the output projection $W_O$. To address this mismatch, we propose \\textit{OptR}, an output-aware rotation method that minimizes post-$W_O$ attention-output error. OptR decomposes the post-$W_O$ attent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02691","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/2608.02691/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":"2026-08-05T00:39:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CArLrtLKbw0p8wl5G/cl/7/jEIvUuZrNCnHK8sQ6bih6baynyaPHXmssOpP+NX74g++UwUhPom6mFcxb6U6rBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T09:48:05.912441Z"},"content_sha256":"a8ed3e5a67dbcecac96fb587a53b90ef571a2a5562f332a0c151bb24974616df","schema_version":"1.0","event_id":"sha256:a8ed3e5a67dbcecac96fb587a53b90ef571a2a5562f332a0c151bb24974616df"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SZ5F37BQHOYBHQILB7ZU3VXL3V/bundle.json","state_url":"https://pith.science/pith/SZ5F37BQHOYBHQILB7ZU3VXL3V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SZ5F37BQHOYBHQILB7ZU3VXL3V/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":"2026-08-13T09:48:05Z","links":{"resolver":"https://pith.science/pith/SZ5F37BQHOYBHQILB7ZU3VXL3V","bundle":"https://pith.science/pith/SZ5F37BQHOYBHQILB7ZU3VXL3V/bundle.json","state":"https://pith.science/pith/SZ5F37BQHOYBHQILB7ZU3VXL3V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SZ5F37BQHOYBHQILB7ZU3VXL3V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SZ5F37BQHOYBHQILB7ZU3VXL3V","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":"74145ea453b317bfc7f9d6e3c03257acde870eceda69542a36eb57cfb349ed64","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-03T09:24:23Z","title_canon_sha256":"b1356e56d35267fbdad1053a90d4453ff16c0a88480c5302fc3342a988e2703c"},"schema_version":"1.0","source":{"id":"2608.02691","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.02691","created_at":"2026-08-05T00:39:25Z"},{"alias_kind":"arxiv_version","alias_value":"2608.02691v1","created_at":"2026-08-05T00:39:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02691","created_at":"2026-08-05T00:39:25Z"},{"alias_kind":"pith_short_12","alias_value":"SZ5F37BQHOYB","created_at":"2026-08-05T00:39:25Z"},{"alias_kind":"pith_short_16","alias_value":"SZ5F37BQHOYBHQIL","created_at":"2026-08-05T00:39:25Z"},{"alias_kind":"pith_short_8","alias_value":"SZ5F37BQ","created_at":"2026-08-05T00:39:25Z"}],"graph_snapshots":[{"event_id":"sha256:a8ed3e5a67dbcecac96fb587a53b90ef571a2a5562f332a0c151bb24974616df","target":"graph","created_at":"2026-08-05T00:39:25Z","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/2608.02691/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The key-value (KV) cache has become a major memory and bandwidth bottleneck in long-context large language model inference, making ultra-low-bit quantization increasingly important. However, existing rotation-based INT2 methods optimize cache statistics or proxy errors before the complete attention readout, even though the model is ultimately affected by the error propagated through attention and the output projection $W_O$. To address this mismatch, we propose \\textit{OptR}, an output-aware rotation method that minimizes post-$W_O$ attention-output error. OptR decomposes the post-$W_O$ attent","authors_text":"Minsoo Cheong, Murali Annavaram, Sai Praneeth Karimireddy, Sungjoo Yoo, Sunwoo Lee, Vincent-Daniel Yun, Woosang Lim","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-03T09:24:23Z","title":"Output-Aware Rotation for INT2 KV-Cache Quantization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02691","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":"sha256:37c7d6b78dcd4e85fe47f693f30dc315e1f7cc4ca64c69987d188bb6a23b498e","target":"record","created_at":"2026-08-05T00:39:25Z","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":"74145ea453b317bfc7f9d6e3c03257acde870eceda69542a36eb57cfb349ed64","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-03T09:24:23Z","title_canon_sha256":"b1356e56d35267fbdad1053a90d4453ff16c0a88480c5302fc3342a988e2703c"},"schema_version":"1.0","source":{"id":"2608.02691","kind":"arxiv","version":1}},"canonical_sha256":"967a5dfc303bb013c10b0ff34dd6ebdd5c69906ee635df8913f372fd8ed9260a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"967a5dfc303bb013c10b0ff34dd6ebdd5c69906ee635df8913f372fd8ed9260a","first_computed_at":"2026-08-05T00:39:25.656903Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T00:39:25.656903Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XJdzpoY8p3CoketVnaYLMOcu1Gzb56v9R0nCfZedcukzdumHrM1oMLV2GzLMG80LEr81IYEeWoEsZtJooznDAg==","signature_status":"signed_v1","signed_at":"2026-08-05T00:39:25.660783Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.02691","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:37c7d6b78dcd4e85fe47f693f30dc315e1f7cc4ca64c69987d188bb6a23b498e","sha256:a8ed3e5a67dbcecac96fb587a53b90ef571a2a5562f332a0c151bb24974616df"],"state_sha256":"628463c5212d0d2b5794879ccd7eece49209f33488032464b160813b07a8429e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cUi0ZroIEYjqmU/adI0Ya5mszaTvGE61T8W5luir2iIDrxJVwCjedXuTtSQJTuHFY3DAoxt7RUQAzGUIuafCAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T09:48:05.921853Z","bundle_sha256":"832773cd30876f5b008d248ee6612784ef54470c29d9f15a850773efaffb738b"}}