{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NS6CD6GJTBXELVSEFX5VGOKNQZ","short_pith_number":"pith:NS6CD6GJ","canonical_record":{"source":{"id":"2410.19103","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-24T19:06:51Z","cross_cats_sorted":[],"title_canon_sha256":"a8cf569238b3b18cac623a45f6824e43d7ed15c63ae7c70ba36ae49890b69221","abstract_canon_sha256":"f6319af8d2b2bde10e310c31b8d4986156b72f46edb8acf3cc0629fabb473ed9"},"schema_version":"1.0"},"canonical_sha256":"6cbc21f8c9986e45d6442dfb53394d867efa24a2adc0256455b6a4124a573eb8","source":{"kind":"arxiv","id":"2410.19103","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.19103","created_at":"2026-07-05T09:25:51Z"},{"alias_kind":"arxiv_version","alias_value":"2410.19103v1","created_at":"2026-07-05T09:25:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.19103","created_at":"2026-07-05T09:25:51Z"},{"alias_kind":"pith_short_12","alias_value":"NS6CD6GJTBXE","created_at":"2026-07-05T09:25:51Z"},{"alias_kind":"pith_short_16","alias_value":"NS6CD6GJTBXELVSE","created_at":"2026-07-05T09:25:51Z"},{"alias_kind":"pith_short_8","alias_value":"NS6CD6GJ","created_at":"2026-07-05T09:25:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NS6CD6GJTBXELVSEFX5VGOKNQZ","target":"record","payload":{"canonical_record":{"source":{"id":"2410.19103","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-24T19:06:51Z","cross_cats_sorted":[],"title_canon_sha256":"a8cf569238b3b18cac623a45f6824e43d7ed15c63ae7c70ba36ae49890b69221","abstract_canon_sha256":"f6319af8d2b2bde10e310c31b8d4986156b72f46edb8acf3cc0629fabb473ed9"},"schema_version":"1.0"},"canonical_sha256":"6cbc21f8c9986e45d6442dfb53394d867efa24a2adc0256455b6a4124a573eb8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:51.479423Z","signature_b64":"7Nzq5p8T3POs7d/3IEvIansxlo6w4XPEA4LYUW80Se6C+IGYiB3F7i2N8O92dX6cOF+lcExISoWmbc3Etw9qAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6cbc21f8c9986e45d6442dfb53394d867efa24a2adc0256455b6a4124a573eb8","last_reissued_at":"2026-07-05T09:25:51.478900Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:51.478900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.19103","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":"2026-07-05T09:25:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w1layuAEeRMmxO1sJIZ1bu0oajiM6vHScIgdd6s/ZRjbnRzd9AgIJ9liEMn0HzTKtLgQpikSV/JED6/2sfWcDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:24:36.618586Z"},"content_sha256":"d9ce463aeb3d117b580fd334d0241605c7bbea4af08f2daa23486ae13d50d6a4","schema_version":"1.0","event_id":"sha256:d9ce463aeb3d117b580fd334d0241605c7bbea4af08f2daa23486ae13d50d6a4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NS6CD6GJTBXELVSEFX5VGOKNQZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TesseraQ: Ultra Low-Bit LLM Post-Training Quantization with Block Reconstruction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Priyadarshini Panda, Yuhang Li","submitted_at":"2024-10-24T19:06:51Z","abstract_excerpt":"Large language models (LLMs) have revolutionized natural language processing, albeit at the cost of immense memory and computation requirements. Post-training quantization (PTQ) is becoming the de facto method to reduce the memory footprint and improve the inference throughput of LLMs. In this work, we aim to push the upper limit of LLM PTQ by optimizing the weight rounding parameters with the block reconstruction technique, a predominant method in previous vision models. We propose TesseraQ, a new state-of-the-art PTQ technique, to quantize the weights of LLMs to ultra-low bits. To effectivel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.19103","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/2410.19103/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":"2026-07-05T09:25:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0GMG+RAcipajCrnF11+saL6j6adwmlzjmriZde82Go0U12UwPqGmNrXnWLCgyHRkQhb+q7VY5B/EeeVHskJ1Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:24:36.619069Z"},"content_sha256":"dfd821dd3ca86680e27a5272297e06c893a6231648cf8b866f197f6d855c4dfb","schema_version":"1.0","event_id":"sha256:dfd821dd3ca86680e27a5272297e06c893a6231648cf8b866f197f6d855c4dfb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NS6CD6GJTBXELVSEFX5VGOKNQZ/bundle.json","state_url":"https://pith.science/pith/NS6CD6GJTBXELVSEFX5VGOKNQZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NS6CD6GJTBXELVSEFX5VGOKNQZ/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":"2026-08-08T18:24:36Z","links":{"resolver":"https://pith.science/pith/NS6CD6GJTBXELVSEFX5VGOKNQZ","bundle":"https://pith.science/pith/NS6CD6GJTBXELVSEFX5VGOKNQZ/bundle.json","state":"https://pith.science/pith/NS6CD6GJTBXELVSEFX5VGOKNQZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NS6CD6GJTBXELVSEFX5VGOKNQZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NS6CD6GJTBXELVSEFX5VGOKNQZ","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":"f6319af8d2b2bde10e310c31b8d4986156b72f46edb8acf3cc0629fabb473ed9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-24T19:06:51Z","title_canon_sha256":"a8cf569238b3b18cac623a45f6824e43d7ed15c63ae7c70ba36ae49890b69221"},"schema_version":"1.0","source":{"id":"2410.19103","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.19103","created_at":"2026-07-05T09:25:51Z"},{"alias_kind":"arxiv_version","alias_value":"2410.19103v1","created_at":"2026-07-05T09:25:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.19103","created_at":"2026-07-05T09:25:51Z"},{"alias_kind":"pith_short_12","alias_value":"NS6CD6GJTBXE","created_at":"2026-07-05T09:25:51Z"},{"alias_kind":"pith_short_16","alias_value":"NS6CD6GJTBXELVSE","created_at":"2026-07-05T09:25:51Z"},{"alias_kind":"pith_short_8","alias_value":"NS6CD6GJ","created_at":"2026-07-05T09:25:51Z"}],"graph_snapshots":[{"event_id":"sha256:dfd821dd3ca86680e27a5272297e06c893a6231648cf8b866f197f6d855c4dfb","target":"graph","created_at":"2026-07-05T09:25:51Z","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/2410.19103/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have revolutionized natural language processing, albeit at the cost of immense memory and computation requirements. Post-training quantization (PTQ) is becoming the de facto method to reduce the memory footprint and improve the inference throughput of LLMs. In this work, we aim to push the upper limit of LLM PTQ by optimizing the weight rounding parameters with the block reconstruction technique, a predominant method in previous vision models. We propose TesseraQ, a new state-of-the-art PTQ technique, to quantize the weights of LLMs to ultra-low bits. To effectivel","authors_text":"Priyadarshini Panda, Yuhang Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-24T19:06:51Z","title":"TesseraQ: Ultra Low-Bit LLM Post-Training Quantization with Block Reconstruction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.19103","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:d9ce463aeb3d117b580fd334d0241605c7bbea4af08f2daa23486ae13d50d6a4","target":"record","created_at":"2026-07-05T09:25:51Z","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":"f6319af8d2b2bde10e310c31b8d4986156b72f46edb8acf3cc0629fabb473ed9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-24T19:06:51Z","title_canon_sha256":"a8cf569238b3b18cac623a45f6824e43d7ed15c63ae7c70ba36ae49890b69221"},"schema_version":"1.0","source":{"id":"2410.19103","kind":"arxiv","version":1}},"canonical_sha256":"6cbc21f8c9986e45d6442dfb53394d867efa24a2adc0256455b6a4124a573eb8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6cbc21f8c9986e45d6442dfb53394d867efa24a2adc0256455b6a4124a573eb8","first_computed_at":"2026-07-05T09:25:51.478900Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:25:51.478900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7Nzq5p8T3POs7d/3IEvIansxlo6w4XPEA4LYUW80Se6C+IGYiB3F7i2N8O92dX6cOF+lcExISoWmbc3Etw9qAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:25:51.479423Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.19103","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d9ce463aeb3d117b580fd334d0241605c7bbea4af08f2daa23486ae13d50d6a4","sha256:dfd821dd3ca86680e27a5272297e06c893a6231648cf8b866f197f6d855c4dfb"],"state_sha256":"434a967665f47bda465db9dbced4eb6d4649a7b7570f1adb92b7e5d429147730"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m2W53DoLFP98oiVJFVerGR9W1i8RmWsI/Re77w/ki491OtDW/Ds5du58+AmeLPzdwX4XqT6HtSGOEABglVsKAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T18:24:36.622369Z","bundle_sha256":"ce24bdfa322a934cf337f6c04ae5fc8fdbcd0e2bd57fe38cdd3e53719add85eb"}}