{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XZ6ERFVNCUVWIIMW4Z4YY2FKVB","short_pith_number":"pith:XZ6ERFVN","canonical_record":{"source":{"id":"2402.17985","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-28T02:00:34Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"fe96ff9fb90f6ae36365b27320377a77b15fbcd9d233dce81063c374308000cd","abstract_canon_sha256":"bb63faebf090479b6f0baac35f90a995ff87a1abf13044b08ab52e1022c0fd01"},"schema_version":"1.0"},"canonical_sha256":"be7c4896ad152b642196e6798c68aaa86fc8b6f5951f05a8f87143f773a2b2e3","source":{"kind":"arxiv","id":"2402.17985","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.17985","created_at":"2026-07-05T07:50:10Z"},{"alias_kind":"arxiv_version","alias_value":"2402.17985v1","created_at":"2026-07-05T07:50:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17985","created_at":"2026-07-05T07:50:10Z"},{"alias_kind":"pith_short_12","alias_value":"XZ6ERFVNCUVW","created_at":"2026-07-05T07:50:10Z"},{"alias_kind":"pith_short_16","alias_value":"XZ6ERFVNCUVWIIMW","created_at":"2026-07-05T07:50:10Z"},{"alias_kind":"pith_short_8","alias_value":"XZ6ERFVN","created_at":"2026-07-05T07:50:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XZ6ERFVNCUVWIIMW4Z4YY2FKVB","target":"record","payload":{"canonical_record":{"source":{"id":"2402.17985","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-28T02:00:34Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"fe96ff9fb90f6ae36365b27320377a77b15fbcd9d233dce81063c374308000cd","abstract_canon_sha256":"bb63faebf090479b6f0baac35f90a995ff87a1abf13044b08ab52e1022c0fd01"},"schema_version":"1.0"},"canonical_sha256":"be7c4896ad152b642196e6798c68aaa86fc8b6f5951f05a8f87143f773a2b2e3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:50:10.623892Z","signature_b64":"Ff5DpMOtAvkwzia/qjH7VadU/UT50EQI6otUCUQhuB+JnDixyqp3kdZtCh/j9pGgMgeIUiRvXDWV6qqeFuKhDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be7c4896ad152b642196e6798c68aaa86fc8b6f5951f05a8f87143f773a2b2e3","last_reissued_at":"2026-07-05T07:50:10.623461Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:50:10.623461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.17985","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":"2026-07-05T07:50:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jfRKlX8sEswbBBoBGaMv0jw6YZx0LmF7qc8fSRnCp8ry1Ks+RRS5yALH3sTyr9y8bgMzEcV836e9pACZT55gDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:14:00.675559Z"},"content_sha256":"f931ca8951afcfd8df81280087fce9e120d07532ac91a2e14c172d706bdc49de","schema_version":"1.0","event_id":"sha256:f931ca8951afcfd8df81280087fce9e120d07532ac91a2e14c172d706bdc49de"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XZ6ERFVNCUVWIIMW4Z4YY2FKVB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FlattenQuant: Breaking Through the Inference Compute-bound for Large Language Models with Per-tensor Quantization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Aimin Pan, Fangyu Wang, Fei Yang, Shuang Peng, Yi Zhang","submitted_at":"2024-02-28T02:00:34Z","abstract_excerpt":"Large language models (LLMs) have demonstrated state-of-the-art performance across various tasks. However, the latency of inference and the large GPU memory consumption of LLMs restrict their deployment performance. Recently, there have been some efficient attempts to quantize LLMs, yet inference with large batch size or long sequence still has the issue of being compute-bound. Fine-grained quantization methods have showcased their proficiency in achieving low-bit quantization for LLMs, while requiring FP16 data type for linear layer computations, which is time-consuming when dealing with larg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17985","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/2402.17985/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":"2026-07-05T07:50:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xNeh3EEpGove9L4+FAGHeurRd11R69Uv11jxPUgEhm+/M5N9pJcoRpi64Ii21DBrUx48HRSa4scuWWbAf+9vDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:14:00.676115Z"},"content_sha256":"9ec8c48b9dae562f43502e562830ace8f482c6790a90fefc28bf0948c9d61c5b","schema_version":"1.0","event_id":"sha256:9ec8c48b9dae562f43502e562830ace8f482c6790a90fefc28bf0948c9d61c5b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XZ6ERFVNCUVWIIMW4Z4YY2FKVB/bundle.json","state_url":"https://pith.science/pith/XZ6ERFVNCUVWIIMW4Z4YY2FKVB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XZ6ERFVNCUVWIIMW4Z4YY2FKVB/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":"2026-08-08T13:14:00Z","links":{"resolver":"https://pith.science/pith/XZ6ERFVNCUVWIIMW4Z4YY2FKVB","bundle":"https://pith.science/pith/XZ6ERFVNCUVWIIMW4Z4YY2FKVB/bundle.json","state":"https://pith.science/pith/XZ6ERFVNCUVWIIMW4Z4YY2FKVB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XZ6ERFVNCUVWIIMW4Z4YY2FKVB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XZ6ERFVNCUVWIIMW4Z4YY2FKVB","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":"bb63faebf090479b6f0baac35f90a995ff87a1abf13044b08ab52e1022c0fd01","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-28T02:00:34Z","title_canon_sha256":"fe96ff9fb90f6ae36365b27320377a77b15fbcd9d233dce81063c374308000cd"},"schema_version":"1.0","source":{"id":"2402.17985","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.17985","created_at":"2026-07-05T07:50:10Z"},{"alias_kind":"arxiv_version","alias_value":"2402.17985v1","created_at":"2026-07-05T07:50:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17985","created_at":"2026-07-05T07:50:10Z"},{"alias_kind":"pith_short_12","alias_value":"XZ6ERFVNCUVW","created_at":"2026-07-05T07:50:10Z"},{"alias_kind":"pith_short_16","alias_value":"XZ6ERFVNCUVWIIMW","created_at":"2026-07-05T07:50:10Z"},{"alias_kind":"pith_short_8","alias_value":"XZ6ERFVN","created_at":"2026-07-05T07:50:10Z"}],"graph_snapshots":[{"event_id":"sha256:9ec8c48b9dae562f43502e562830ace8f482c6790a90fefc28bf0948c9d61c5b","target":"graph","created_at":"2026-07-05T07:50:10Z","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/2402.17985/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have demonstrated state-of-the-art performance across various tasks. However, the latency of inference and the large GPU memory consumption of LLMs restrict their deployment performance. Recently, there have been some efficient attempts to quantize LLMs, yet inference with large batch size or long sequence still has the issue of being compute-bound. Fine-grained quantization methods have showcased their proficiency in achieving low-bit quantization for LLMs, while requiring FP16 data type for linear layer computations, which is time-consuming when dealing with larg","authors_text":"Aimin Pan, Fangyu Wang, Fei Yang, Shuang Peng, Yi Zhang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-28T02:00:34Z","title":"FlattenQuant: Breaking Through the Inference Compute-bound for Large Language Models with Per-tensor Quantization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17985","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:f931ca8951afcfd8df81280087fce9e120d07532ac91a2e14c172d706bdc49de","target":"record","created_at":"2026-07-05T07:50:10Z","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":"bb63faebf090479b6f0baac35f90a995ff87a1abf13044b08ab52e1022c0fd01","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-28T02:00:34Z","title_canon_sha256":"fe96ff9fb90f6ae36365b27320377a77b15fbcd9d233dce81063c374308000cd"},"schema_version":"1.0","source":{"id":"2402.17985","kind":"arxiv","version":1}},"canonical_sha256":"be7c4896ad152b642196e6798c68aaa86fc8b6f5951f05a8f87143f773a2b2e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"be7c4896ad152b642196e6798c68aaa86fc8b6f5951f05a8f87143f773a2b2e3","first_computed_at":"2026-07-05T07:50:10.623461Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:50:10.623461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ff5DpMOtAvkwzia/qjH7VadU/UT50EQI6otUCUQhuB+JnDixyqp3kdZtCh/j9pGgMgeIUiRvXDWV6qqeFuKhDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:50:10.623892Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.17985","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f931ca8951afcfd8df81280087fce9e120d07532ac91a2e14c172d706bdc49de","sha256:9ec8c48b9dae562f43502e562830ace8f482c6790a90fefc28bf0948c9d61c5b"],"state_sha256":"4d0548ecb3cf35939bc3dc1f23908598757cc254569f30dc288516780806f1ee"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3GGwoNcsWEFAtXEWozzj9MZxvGzn1UI0KSvGrxCiQL+UqhZocvhv/LhdPz5rXRHDlAPKfar4C20KV5PMp7D7DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T13:14:00.680603Z","bundle_sha256":"de03b26ac48112f1fc0f4fe681433d53f1c3588fd20d4e33450d0c73342a142f"}}