{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GFPH3MNWNUKXGQOD44FEDYYEYQ","short_pith_number":"pith:GFPH3MNW","canonical_record":{"source":{"id":"2501.13987","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-23T08:24:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7d75047b4fb9c034ef70d0a477c4ef4adfccec6574d765c5468cf061b5a8eb5e","abstract_canon_sha256":"71ef5b3007642da7ee172d8116f336d4e4970e65c4cf2fce06fbe702abe19d26"},"schema_version":"1.0"},"canonical_sha256":"315e7db1b66d157341c3e70a41e304c40bba339c782280851006dc346681ac1d","source":{"kind":"arxiv","id":"2501.13987","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.13987","created_at":"2026-07-05T10:04:43Z"},{"alias_kind":"arxiv_version","alias_value":"2501.13987v1","created_at":"2026-07-05T10:04:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13987","created_at":"2026-07-05T10:04:43Z"},{"alias_kind":"pith_short_12","alias_value":"GFPH3MNWNUKX","created_at":"2026-07-05T10:04:43Z"},{"alias_kind":"pith_short_16","alias_value":"GFPH3MNWNUKXGQOD","created_at":"2026-07-05T10:04:43Z"},{"alias_kind":"pith_short_8","alias_value":"GFPH3MNW","created_at":"2026-07-05T10:04:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GFPH3MNWNUKXGQOD44FEDYYEYQ","target":"record","payload":{"canonical_record":{"source":{"id":"2501.13987","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-23T08:24:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7d75047b4fb9c034ef70d0a477c4ef4adfccec6574d765c5468cf061b5a8eb5e","abstract_canon_sha256":"71ef5b3007642da7ee172d8116f336d4e4970e65c4cf2fce06fbe702abe19d26"},"schema_version":"1.0"},"canonical_sha256":"315e7db1b66d157341c3e70a41e304c40bba339c782280851006dc346681ac1d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:43.517996Z","signature_b64":"dCcS16oZqJNNnHaqmEqOQLWm0bJqosMY6n2MtSUiAJ3S6zcfgDIorn6wX2dKJ8x0RVDTOpITBKf9KU1TMPZGAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"315e7db1b66d157341c3e70a41e304c40bba339c782280851006dc346681ac1d","last_reissued_at":"2026-07-05T10:04:43.517569Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:43.517569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.13987","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":"2026-07-05T10:04:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pd4AvPefNywiVw9Qtb1Av/nnL8IJHS7p0TThwCusfbwm3aqRRfstWDH3hyh6wAgTxIU9+m+9swqQJA15bx1ZAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T09:39:15.617110Z"},"content_sha256":"5f46233f10fab47de486c6177684b0493bc228294d7d5e8f441321fc6626f75c","schema_version":"1.0","event_id":"sha256:5f46233f10fab47de486c6177684b0493bc228294d7d5e8f441321fc6626f75c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GFPH3MNWNUKXGQOD44FEDYYEYQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"OstQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chen Xu, Dawei Yang, Jiangyong Yu, Sifan Zhou, Xing Hu, Yuan Cheng, Zhe Jiang, Zhihang Yuan, Zukang Xu","submitted_at":"2025-01-23T08:24:25Z","abstract_excerpt":"Post-training quantization (PTQ) has emerged as a widely adopted technique for compressing and accelerating Large Language Models (LLMs). The major challenge in LLM quantization is that uneven and heavy-tailed data distributions can expand the quantization range, thereby reducing bit precision for most values. Recent methods attempt to eliminate outliers and balance inter-channel differences by employing linear transformations; however, they remain heuristic and are often overlook optimizing the data distribution across the entire quantization space.In this paper, we introduce Quantization Spa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13987","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/2501.13987/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":"2026-07-05T10:04:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"398UqG8wRaDK1BYOjzn3L/D8/kMURuxBJXWZok3h5PWP9aAznwnzOg/Cy6modDCfSVNXCogu6tyC/o+tI5onCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T09:39:15.617502Z"},"content_sha256":"076bbc04476498e2be4175298a5e57b474ea6fce3d985b2f1c1afe9619035ca5","schema_version":"1.0","event_id":"sha256:076bbc04476498e2be4175298a5e57b474ea6fce3d985b2f1c1afe9619035ca5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GFPH3MNWNUKXGQOD44FEDYYEYQ/bundle.json","state_url":"https://pith.science/pith/GFPH3MNWNUKXGQOD44FEDYYEYQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GFPH3MNWNUKXGQOD44FEDYYEYQ/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":"2026-07-13T09:39:15Z","links":{"resolver":"https://pith.science/pith/GFPH3MNWNUKXGQOD44FEDYYEYQ","bundle":"https://pith.science/pith/GFPH3MNWNUKXGQOD44FEDYYEYQ/bundle.json","state":"https://pith.science/pith/GFPH3MNWNUKXGQOD44FEDYYEYQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GFPH3MNWNUKXGQOD44FEDYYEYQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GFPH3MNWNUKXGQOD44FEDYYEYQ","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":"71ef5b3007642da7ee172d8116f336d4e4970e65c4cf2fce06fbe702abe19d26","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-23T08:24:25Z","title_canon_sha256":"7d75047b4fb9c034ef70d0a477c4ef4adfccec6574d765c5468cf061b5a8eb5e"},"schema_version":"1.0","source":{"id":"2501.13987","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.13987","created_at":"2026-07-05T10:04:43Z"},{"alias_kind":"arxiv_version","alias_value":"2501.13987v1","created_at":"2026-07-05T10:04:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13987","created_at":"2026-07-05T10:04:43Z"},{"alias_kind":"pith_short_12","alias_value":"GFPH3MNWNUKX","created_at":"2026-07-05T10:04:43Z"},{"alias_kind":"pith_short_16","alias_value":"GFPH3MNWNUKXGQOD","created_at":"2026-07-05T10:04:43Z"},{"alias_kind":"pith_short_8","alias_value":"GFPH3MNW","created_at":"2026-07-05T10:04:43Z"}],"graph_snapshots":[{"event_id":"sha256:076bbc04476498e2be4175298a5e57b474ea6fce3d985b2f1c1afe9619035ca5","target":"graph","created_at":"2026-07-05T10:04:43Z","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/2501.13987/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Post-training quantization (PTQ) has emerged as a widely adopted technique for compressing and accelerating Large Language Models (LLMs). The major challenge in LLM quantization is that uneven and heavy-tailed data distributions can expand the quantization range, thereby reducing bit precision for most values. Recent methods attempt to eliminate outliers and balance inter-channel differences by employing linear transformations; however, they remain heuristic and are often overlook optimizing the data distribution across the entire quantization space.In this paper, we introduce Quantization Spa","authors_text":"Chen Xu, Dawei Yang, Jiangyong Yu, Sifan Zhou, Xing Hu, Yuan Cheng, Zhe Jiang, Zhihang Yuan, Zukang Xu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-23T08:24:25Z","title":"OstQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13987","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":"sha256:5f46233f10fab47de486c6177684b0493bc228294d7d5e8f441321fc6626f75c","target":"record","created_at":"2026-07-05T10:04:43Z","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":"71ef5b3007642da7ee172d8116f336d4e4970e65c4cf2fce06fbe702abe19d26","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-23T08:24:25Z","title_canon_sha256":"7d75047b4fb9c034ef70d0a477c4ef4adfccec6574d765c5468cf061b5a8eb5e"},"schema_version":"1.0","source":{"id":"2501.13987","kind":"arxiv","version":1}},"canonical_sha256":"315e7db1b66d157341c3e70a41e304c40bba339c782280851006dc346681ac1d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"315e7db1b66d157341c3e70a41e304c40bba339c782280851006dc346681ac1d","first_computed_at":"2026-07-05T10:04:43.517569Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:04:43.517569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dCcS16oZqJNNnHaqmEqOQLWm0bJqosMY6n2MtSUiAJ3S6zcfgDIorn6wX2dKJ8x0RVDTOpITBKf9KU1TMPZGAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:04:43.517996Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.13987","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5f46233f10fab47de486c6177684b0493bc228294d7d5e8f441321fc6626f75c","sha256:076bbc04476498e2be4175298a5e57b474ea6fce3d985b2f1c1afe9619035ca5"],"state_sha256":"5358f149922a8a5263f74c2bbb44c5f1c52e0a95af587896a360daf552f748fb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lOacuzUe18r81TOobw868rMGZZRGVH9G25Ut+TDZ54vzLyX1L/c0OS7xEJPgYHT6OoF7cbX6sYU9SHl98xaVBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T09:39:15.619670Z","bundle_sha256":"f3efb46464244b348b344d91783c8d94ba925a57636a94b8da3e8bc286e40339"}}