{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:FBJWUXJTYJILTZKCAIVH7ZAO3Q","short_pith_number":"pith:FBJWUXJT","canonical_record":{"source":{"id":"2311.09550","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-16T04:11:19Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"f1482c46a180b75b5861f1235ce53d5eb6214100100ea6d1f29c27d72e0373c4","abstract_canon_sha256":"60dbac1a4982f617c3235550d4b7b2ccf8910f315b6734c0ea0d3eac42e0a5cc"},"schema_version":"1.0"},"canonical_sha256":"28536a5d33c250b9e542022a7fe40edc1ebdb823ad69a8678286b7d645c30f95","source":{"kind":"arxiv","id":"2311.09550","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.09550","created_at":"2026-07-05T07:13:29Z"},{"alias_kind":"arxiv_version","alias_value":"2311.09550v1","created_at":"2026-07-05T07:13:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09550","created_at":"2026-07-05T07:13:29Z"},{"alias_kind":"pith_short_12","alias_value":"FBJWUXJTYJIL","created_at":"2026-07-05T07:13:29Z"},{"alias_kind":"pith_short_16","alias_value":"FBJWUXJTYJILTZKC","created_at":"2026-07-05T07:13:29Z"},{"alias_kind":"pith_short_8","alias_value":"FBJWUXJT","created_at":"2026-07-05T07:13:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:FBJWUXJTYJILTZKCAIVH7ZAO3Q","target":"record","payload":{"canonical_record":{"source":{"id":"2311.09550","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-16T04:11:19Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"f1482c46a180b75b5861f1235ce53d5eb6214100100ea6d1f29c27d72e0373c4","abstract_canon_sha256":"60dbac1a4982f617c3235550d4b7b2ccf8910f315b6734c0ea0d3eac42e0a5cc"},"schema_version":"1.0"},"canonical_sha256":"28536a5d33c250b9e542022a7fe40edc1ebdb823ad69a8678286b7d645c30f95","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:13:29.544860Z","signature_b64":"wMJpuxA7Rk8EpnpZnuP2blb9JyWVGNXui223CYyK6oOi1xbyQm8h5OhHZcvyuha9tGASQiiMUZTpZ9U+jCyrCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28536a5d33c250b9e542022a7fe40edc1ebdb823ad69a8678286b7d645c30f95","last_reissued_at":"2026-07-05T07:13:29.544401Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:13:29.544401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.09550","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":"2026-07-05T07:13:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GmUDhGRjyOaYN47aJYlwet/o3AevJBXR0+zPMkgwb3Vd3diqLhwuyWcdU1kBzXkiwj6S0H8NF6ehHtFp7PQ4Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:06:32.620278Z"},"content_sha256":"e0313c4d6bbea9c6bf2c12c99f1efda32f7830315f6c3bfec730e3ed9fead77d","schema_version":"1.0","event_id":"sha256:e0313c4d6bbea9c6bf2c12c99f1efda32f7830315f6c3bfec730e3ed9fead77d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:FBJWUXJTYJILTZKCAIVH7ZAO3Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Speed Odyssey for Deployable Quantization of LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Bo Zhang, Liang Li, Qingyuan Li, Ran Meng, Xiangxiang Chu, Yerui Sun, Yiduo Li, Yifan Lu, Yuchen Xie","submitted_at":"2023-11-16T04:11:19Z","abstract_excerpt":"The large language model era urges faster and less costly inference. Prior model compression works on LLMs tend to undertake a software-centric approach primarily focused on the simulated quantization performance. By neglecting the feasibility of deployment, these approaches are typically disabled in real practice. They used to drastically push down the quantization bit range for a reduced computation which might not be supported by the mainstream hardware, or involve sophisticated algorithms that introduce extra computation or memory access overhead. We argue that pursuing a hardware-centric "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09550","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/2311.09550/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":"2026-07-05T07:13:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o3eKW3RMHvDQNqqIJmvYFMP2O5Y8S1zdoZC/tptfhwPSWB8whQs++GIiPtfa9a5YbOSvt7W2JsUC3rAnSfaTDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:06:32.620672Z"},"content_sha256":"1b475332c0b1f55f8934a558bc72098645caca82bea36ccad800cc4b7c1f6b11","schema_version":"1.0","event_id":"sha256:1b475332c0b1f55f8934a558bc72098645caca82bea36ccad800cc4b7c1f6b11"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FBJWUXJTYJILTZKCAIVH7ZAO3Q/bundle.json","state_url":"https://pith.science/pith/FBJWUXJTYJILTZKCAIVH7ZAO3Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FBJWUXJTYJILTZKCAIVH7ZAO3Q/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":"2026-07-07T03:06:32Z","links":{"resolver":"https://pith.science/pith/FBJWUXJTYJILTZKCAIVH7ZAO3Q","bundle":"https://pith.science/pith/FBJWUXJTYJILTZKCAIVH7ZAO3Q/bundle.json","state":"https://pith.science/pith/FBJWUXJTYJILTZKCAIVH7ZAO3Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FBJWUXJTYJILTZKCAIVH7ZAO3Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FBJWUXJTYJILTZKCAIVH7ZAO3Q","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":"60dbac1a4982f617c3235550d4b7b2ccf8910f315b6734c0ea0d3eac42e0a5cc","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-16T04:11:19Z","title_canon_sha256":"f1482c46a180b75b5861f1235ce53d5eb6214100100ea6d1f29c27d72e0373c4"},"schema_version":"1.0","source":{"id":"2311.09550","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.09550","created_at":"2026-07-05T07:13:29Z"},{"alias_kind":"arxiv_version","alias_value":"2311.09550v1","created_at":"2026-07-05T07:13:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09550","created_at":"2026-07-05T07:13:29Z"},{"alias_kind":"pith_short_12","alias_value":"FBJWUXJTYJIL","created_at":"2026-07-05T07:13:29Z"},{"alias_kind":"pith_short_16","alias_value":"FBJWUXJTYJILTZKC","created_at":"2026-07-05T07:13:29Z"},{"alias_kind":"pith_short_8","alias_value":"FBJWUXJT","created_at":"2026-07-05T07:13:29Z"}],"graph_snapshots":[{"event_id":"sha256:1b475332c0b1f55f8934a558bc72098645caca82bea36ccad800cc4b7c1f6b11","target":"graph","created_at":"2026-07-05T07:13:29Z","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/2311.09550/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The large language model era urges faster and less costly inference. Prior model compression works on LLMs tend to undertake a software-centric approach primarily focused on the simulated quantization performance. By neglecting the feasibility of deployment, these approaches are typically disabled in real practice. They used to drastically push down the quantization bit range for a reduced computation which might not be supported by the mainstream hardware, or involve sophisticated algorithms that introduce extra computation or memory access overhead. We argue that pursuing a hardware-centric ","authors_text":"Bo Zhang, Liang Li, Qingyuan Li, Ran Meng, Xiangxiang Chu, Yerui Sun, Yiduo Li, Yifan Lu, Yuchen Xie","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-16T04:11:19Z","title":"A Speed Odyssey for Deployable Quantization of LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09550","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:e0313c4d6bbea9c6bf2c12c99f1efda32f7830315f6c3bfec730e3ed9fead77d","target":"record","created_at":"2026-07-05T07:13:29Z","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":"60dbac1a4982f617c3235550d4b7b2ccf8910f315b6734c0ea0d3eac42e0a5cc","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-16T04:11:19Z","title_canon_sha256":"f1482c46a180b75b5861f1235ce53d5eb6214100100ea6d1f29c27d72e0373c4"},"schema_version":"1.0","source":{"id":"2311.09550","kind":"arxiv","version":1}},"canonical_sha256":"28536a5d33c250b9e542022a7fe40edc1ebdb823ad69a8678286b7d645c30f95","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"28536a5d33c250b9e542022a7fe40edc1ebdb823ad69a8678286b7d645c30f95","first_computed_at":"2026-07-05T07:13:29.544401Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:13:29.544401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wMJpuxA7Rk8EpnpZnuP2blb9JyWVGNXui223CYyK6oOi1xbyQm8h5OhHZcvyuha9tGASQiiMUZTpZ9U+jCyrCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:13:29.544860Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.09550","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e0313c4d6bbea9c6bf2c12c99f1efda32f7830315f6c3bfec730e3ed9fead77d","sha256:1b475332c0b1f55f8934a558bc72098645caca82bea36ccad800cc4b7c1f6b11"],"state_sha256":"f519ce0daf97fca191275459a2dd703011b559194929a5006f6fd92d2d285480"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m5fwaM7Lzx7sD23qdKu3u4AeM8uK0hjYy8GgWABohkiILGiypR319/dCy634clUBnydpJ2aRDh8AOM017Qo8Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T03:06:32.622595Z","bundle_sha256":"23d384a171958f8dd8451eff93f71dfe2a31d2e3e9bb9468d228b5846eca29c0"}}