{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:P23HZNMCS3YT6S3VHQRUZDEMEX","short_pith_number":"pith:P23HZNMC","canonical_record":{"source":{"id":"2407.10960","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-15T17:55:42Z","cross_cats_sorted":["cs.CL","cs.DC"],"title_canon_sha256":"87745d22e979d7bb5d5a93283ebf14e1ea2ddf901e54510905aa458322b32a22","abstract_canon_sha256":"52c3289a47009d5e7686d89050f3de9c949841fbca6e8856856e8f899034cdc7"},"schema_version":"1.0"},"canonical_sha256":"7eb67cb58296f13f4b753c234c8c8c25d9a2e4186370b796195e0612916c197c","source":{"kind":"arxiv","id":"2407.10960","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.10960","created_at":"2026-07-05T10:02:04Z"},{"alias_kind":"arxiv_version","alias_value":"2407.10960v4","created_at":"2026-07-05T10:02:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10960","created_at":"2026-07-05T10:02:04Z"},{"alias_kind":"pith_short_12","alias_value":"P23HZNMCS3YT","created_at":"2026-07-05T10:02:04Z"},{"alias_kind":"pith_short_16","alias_value":"P23HZNMCS3YT6S3V","created_at":"2026-07-05T10:02:04Z"},{"alias_kind":"pith_short_8","alias_value":"P23HZNMC","created_at":"2026-07-05T10:02:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:P23HZNMCS3YT6S3VHQRUZDEMEX","target":"record","payload":{"canonical_record":{"source":{"id":"2407.10960","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-15T17:55:42Z","cross_cats_sorted":["cs.CL","cs.DC"],"title_canon_sha256":"87745d22e979d7bb5d5a93283ebf14e1ea2ddf901e54510905aa458322b32a22","abstract_canon_sha256":"52c3289a47009d5e7686d89050f3de9c949841fbca6e8856856e8f899034cdc7"},"schema_version":"1.0"},"canonical_sha256":"7eb67cb58296f13f4b753c234c8c8c25d9a2e4186370b796195e0612916c197c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:04.972111Z","signature_b64":"pqrzRMOUeBKJXPETMFk+R31Kvzzu/wO6tKOaIeYBvsxU8EZRlQujDAsH4+av/Ja13zoKcP+Hsgd5MvnqwSvJAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7eb67cb58296f13f4b753c234c8c8c25d9a2e4186370b796195e0612916c197c","last_reissued_at":"2026-07-05T10:02:04.971630Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:04.971630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.10960","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:02:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F3mOYRE4qXP70dOjgMxBj/5ifo8o+4jVrhJuY4rvaQW7TCooNkgazXriZ7f5cY7BAXPySgYqsJ4G4xMxZ7rjAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T08:16:05.536041Z"},"content_sha256":"f7bf4df2b86e7a6dd509b3ac4191d19e23a10c3b2c806f8e2ddc859b70ede617","schema_version":"1.0","event_id":"sha256:f7bf4df2b86e7a6dd509b3ac4191d19e23a10c3b2c806f8e2ddc859b70ede617"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:P23HZNMCS3YT6S3VHQRUZDEMEX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fast Matrix Multiplications for Lookup Table-Quantized LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.DC"],"primary_cat":"cs.LG","authors_text":"Eric P. Xing, Han Guo, Jonathan Ragan-Kelley, Radostin Cholakov, William Brandon, Yoon Kim","submitted_at":"2024-07-15T17:55:42Z","abstract_excerpt":"The deployment of large language models (LLMs) is often constrained by memory bandwidth, where the primary bottleneck is the cost of transferring model parameters from the GPU's global memory to its registers. When coupled with custom kernels that fuse the dequantization and matmul operations, weight-only quantization can thus enable faster inference by reducing the amount of memory movement. However, developing high-performance kernels for weight-quantized LLMs presents substantial challenges, especially when the weights are compressed to non-evenly-divisible bit widths (e.g., 3 bits) with no"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10960","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/2407.10960/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":"2026-07-05T10:02:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZHFSwuekWmNmlzkgI04ZCivAx6JNZPexA/tvvDrwwXo/1USXZDWuxUX3bEIEsrgbbETry3M01rW/WYmQeJSKAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T08:16:05.536566Z"},"content_sha256":"ad1e494b40fc9e00c50efa7c707ae7649ca0a0498cf088e56d968b38405c0e91","schema_version":"1.0","event_id":"sha256:ad1e494b40fc9e00c50efa7c707ae7649ca0a0498cf088e56d968b38405c0e91"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P23HZNMCS3YT6S3VHQRUZDEMEX/bundle.json","state_url":"https://pith.science/pith/P23HZNMCS3YT6S3VHQRUZDEMEX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P23HZNMCS3YT6S3VHQRUZDEMEX/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":"2026-08-15T08:16:05Z","links":{"resolver":"https://pith.science/pith/P23HZNMCS3YT6S3VHQRUZDEMEX","bundle":"https://pith.science/pith/P23HZNMCS3YT6S3VHQRUZDEMEX/bundle.json","state":"https://pith.science/pith/P23HZNMCS3YT6S3VHQRUZDEMEX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P23HZNMCS3YT6S3VHQRUZDEMEX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:P23HZNMCS3YT6S3VHQRUZDEMEX","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":"52c3289a47009d5e7686d89050f3de9c949841fbca6e8856856e8f899034cdc7","cross_cats_sorted":["cs.CL","cs.DC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-15T17:55:42Z","title_canon_sha256":"87745d22e979d7bb5d5a93283ebf14e1ea2ddf901e54510905aa458322b32a22"},"schema_version":"1.0","source":{"id":"2407.10960","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.10960","created_at":"2026-07-05T10:02:04Z"},{"alias_kind":"arxiv_version","alias_value":"2407.10960v4","created_at":"2026-07-05T10:02:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10960","created_at":"2026-07-05T10:02:04Z"},{"alias_kind":"pith_short_12","alias_value":"P23HZNMCS3YT","created_at":"2026-07-05T10:02:04Z"},{"alias_kind":"pith_short_16","alias_value":"P23HZNMCS3YT6S3V","created_at":"2026-07-05T10:02:04Z"},{"alias_kind":"pith_short_8","alias_value":"P23HZNMC","created_at":"2026-07-05T10:02:04Z"}],"graph_snapshots":[{"event_id":"sha256:ad1e494b40fc9e00c50efa7c707ae7649ca0a0498cf088e56d968b38405c0e91","target":"graph","created_at":"2026-07-05T10:02:04Z","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/2407.10960/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The deployment of large language models (LLMs) is often constrained by memory bandwidth, where the primary bottleneck is the cost of transferring model parameters from the GPU's global memory to its registers. When coupled with custom kernels that fuse the dequantization and matmul operations, weight-only quantization can thus enable faster inference by reducing the amount of memory movement. However, developing high-performance kernels for weight-quantized LLMs presents substantial challenges, especially when the weights are compressed to non-evenly-divisible bit widths (e.g., 3 bits) with no","authors_text":"Eric P. Xing, Han Guo, Jonathan Ragan-Kelley, Radostin Cholakov, William Brandon, Yoon Kim","cross_cats":["cs.CL","cs.DC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-15T17:55:42Z","title":"Fast Matrix Multiplications for Lookup Table-Quantized LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10960","kind":"arxiv","version":4},"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:f7bf4df2b86e7a6dd509b3ac4191d19e23a10c3b2c806f8e2ddc859b70ede617","target":"record","created_at":"2026-07-05T10:02:04Z","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":"52c3289a47009d5e7686d89050f3de9c949841fbca6e8856856e8f899034cdc7","cross_cats_sorted":["cs.CL","cs.DC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-15T17:55:42Z","title_canon_sha256":"87745d22e979d7bb5d5a93283ebf14e1ea2ddf901e54510905aa458322b32a22"},"schema_version":"1.0","source":{"id":"2407.10960","kind":"arxiv","version":4}},"canonical_sha256":"7eb67cb58296f13f4b753c234c8c8c25d9a2e4186370b796195e0612916c197c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7eb67cb58296f13f4b753c234c8c8c25d9a2e4186370b796195e0612916c197c","first_computed_at":"2026-07-05T10:02:04.971630Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:02:04.971630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pqrzRMOUeBKJXPETMFk+R31Kvzzu/wO6tKOaIeYBvsxU8EZRlQujDAsH4+av/Ja13zoKcP+Hsgd5MvnqwSvJAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:02:04.972111Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.10960","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f7bf4df2b86e7a6dd509b3ac4191d19e23a10c3b2c806f8e2ddc859b70ede617","sha256:ad1e494b40fc9e00c50efa7c707ae7649ca0a0498cf088e56d968b38405c0e91"],"state_sha256":"c74f6d5a0c07d189328b637e9daa5fe71774aeb2342fa87bc5d41bee04f50e30"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B2K9pxSwa5RMV9IrJ+aUxEsdnGQCChY9pnxwhnsGUEBmh0JFMYI3yK+rOCPWxgkbA6dhjfLZOVlfPg75j2LNDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T08:16:05.541797Z","bundle_sha256":"51a518703ec4059e2683fb0b668007ae6bd7b4d7de13ce979d5c7a0a332f3c9d"}}