{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:KBJZ7NVKPAETYKP6AKDMLFXRRS","short_pith_number":"pith:KBJZ7NVK","canonical_record":{"source":{"id":"2210.03671","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-07T16:25:18Z","cross_cats_sorted":[],"title_canon_sha256":"1e3bcdfa968cd58465cd13f441b9b7048e29497c6f125b3e7216bf091394fc2c","abstract_canon_sha256":"fe1d8766ab730738e709ca2c1f9925d1c766ebf0a5836208038f01ad85854bd5"},"schema_version":"1.0"},"canonical_sha256":"50539fb6aa78093c29fe0286c596f18c817bad2f783510e46f0aee20717f15e3","source":{"kind":"arxiv","id":"2210.03671","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.03671","created_at":"2026-07-05T05:04:22Z"},{"alias_kind":"arxiv_version","alias_value":"2210.03671v1","created_at":"2026-07-05T05:04:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.03671","created_at":"2026-07-05T05:04:22Z"},{"alias_kind":"pith_short_12","alias_value":"KBJZ7NVKPAET","created_at":"2026-07-05T05:04:22Z"},{"alias_kind":"pith_short_16","alias_value":"KBJZ7NVKPAETYKP6","created_at":"2026-07-05T05:04:22Z"},{"alias_kind":"pith_short_8","alias_value":"KBJZ7NVK","created_at":"2026-07-05T05:04:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:KBJZ7NVKPAETYKP6AKDMLFXRRS","target":"record","payload":{"canonical_record":{"source":{"id":"2210.03671","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-07T16:25:18Z","cross_cats_sorted":[],"title_canon_sha256":"1e3bcdfa968cd58465cd13f441b9b7048e29497c6f125b3e7216bf091394fc2c","abstract_canon_sha256":"fe1d8766ab730738e709ca2c1f9925d1c766ebf0a5836208038f01ad85854bd5"},"schema_version":"1.0"},"canonical_sha256":"50539fb6aa78093c29fe0286c596f18c817bad2f783510e46f0aee20717f15e3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:04:22.695084Z","signature_b64":"QptIGo3/RgaA9hKAzQXg0Pz34yuvqg5X6yBrMMmh3usFLdviBijEyD8WQ+NeIEmNNGue7ZbTW66Vr5c1b/mFDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50539fb6aa78093c29fe0286c596f18c817bad2f783510e46f0aee20717f15e3","last_reissued_at":"2026-07-05T05:04:22.694658Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:04:22.694658Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.03671","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":"2026-07-05T05:04:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v5nx7dnMCClAH+LX3CvZy9V1HZT5Gd80MQEKxN7OfN31Loq/odzlcNKb8RtV1esYLbxVlPj2OVRvV7RACvcMBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T18:22:13.543733Z"},"content_sha256":"5cb5c85c93a137bdd3208ed8643364c9e7ef11565021f9a9ca7fa01249c06809","schema_version":"1.0","event_id":"sha256:5cb5c85c93a137bdd3208ed8643364c9e7ef11565021f9a9ca7fa01249c06809"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:KBJZ7NVKPAETYKP6AKDMLFXRRS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Closer Look at Hardware-Friendly Weight Quantization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Piotr Zielinski, Satrajit Chatterjee, Sungmin Bae","submitted_at":"2022-10-07T16:25:18Z","abstract_excerpt":"Quantizing a Deep Neural Network (DNN) model to be used on a custom accelerator with efficient fixed-point hardware implementations, requires satisfying many stringent hardware-friendly quantization constraints to train the model. We evaluate the two main classes of hardware-friendly quantization methods in the context of weight quantization: the traditional Mean Squared Quantization Error (MSQE)-based methods and the more recent gradient-based methods. We study the two methods on MobileNetV1 and MobileNetV2 using multiple empirical metrics to identify the sources of performance differences be"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.03671","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/2210.03671/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":"2026-07-05T05:04:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9wzClrPeOM60Fs7eT24vE7eRQKh/bbE2uQV2Co6MFzbMXOwFySG2VKAm9jj+W25NqI1CVO3Tj+I2twrxUbnlCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T18:22:13.544385Z"},"content_sha256":"8669621209057819a6a3c61a677615c1ccead79cf606af3458b2e36663ebc653","schema_version":"1.0","event_id":"sha256:8669621209057819a6a3c61a677615c1ccead79cf606af3458b2e36663ebc653"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KBJZ7NVKPAETYKP6AKDMLFXRRS/bundle.json","state_url":"https://pith.science/pith/KBJZ7NVKPAETYKP6AKDMLFXRRS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KBJZ7NVKPAETYKP6AKDMLFXRRS/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":"2026-08-18T18:22:13Z","links":{"resolver":"https://pith.science/pith/KBJZ7NVKPAETYKP6AKDMLFXRRS","bundle":"https://pith.science/pith/KBJZ7NVKPAETYKP6AKDMLFXRRS/bundle.json","state":"https://pith.science/pith/KBJZ7NVKPAETYKP6AKDMLFXRRS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KBJZ7NVKPAETYKP6AKDMLFXRRS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:KBJZ7NVKPAETYKP6AKDMLFXRRS","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":"fe1d8766ab730738e709ca2c1f9925d1c766ebf0a5836208038f01ad85854bd5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-07T16:25:18Z","title_canon_sha256":"1e3bcdfa968cd58465cd13f441b9b7048e29497c6f125b3e7216bf091394fc2c"},"schema_version":"1.0","source":{"id":"2210.03671","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.03671","created_at":"2026-07-05T05:04:22Z"},{"alias_kind":"arxiv_version","alias_value":"2210.03671v1","created_at":"2026-07-05T05:04:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.03671","created_at":"2026-07-05T05:04:22Z"},{"alias_kind":"pith_short_12","alias_value":"KBJZ7NVKPAET","created_at":"2026-07-05T05:04:22Z"},{"alias_kind":"pith_short_16","alias_value":"KBJZ7NVKPAETYKP6","created_at":"2026-07-05T05:04:22Z"},{"alias_kind":"pith_short_8","alias_value":"KBJZ7NVK","created_at":"2026-07-05T05:04:22Z"}],"graph_snapshots":[{"event_id":"sha256:8669621209057819a6a3c61a677615c1ccead79cf606af3458b2e36663ebc653","target":"graph","created_at":"2026-07-05T05:04:22Z","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/2210.03671/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Quantizing a Deep Neural Network (DNN) model to be used on a custom accelerator with efficient fixed-point hardware implementations, requires satisfying many stringent hardware-friendly quantization constraints to train the model. We evaluate the two main classes of hardware-friendly quantization methods in the context of weight quantization: the traditional Mean Squared Quantization Error (MSQE)-based methods and the more recent gradient-based methods. We study the two methods on MobileNetV1 and MobileNetV2 using multiple empirical metrics to identify the sources of performance differences be","authors_text":"Piotr Zielinski, Satrajit Chatterjee, Sungmin Bae","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-07T16:25:18Z","title":"A Closer Look at Hardware-Friendly Weight Quantization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.03671","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":"sha256:5cb5c85c93a137bdd3208ed8643364c9e7ef11565021f9a9ca7fa01249c06809","target":"record","created_at":"2026-07-05T05:04:22Z","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":"fe1d8766ab730738e709ca2c1f9925d1c766ebf0a5836208038f01ad85854bd5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-07T16:25:18Z","title_canon_sha256":"1e3bcdfa968cd58465cd13f441b9b7048e29497c6f125b3e7216bf091394fc2c"},"schema_version":"1.0","source":{"id":"2210.03671","kind":"arxiv","version":1}},"canonical_sha256":"50539fb6aa78093c29fe0286c596f18c817bad2f783510e46f0aee20717f15e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"50539fb6aa78093c29fe0286c596f18c817bad2f783510e46f0aee20717f15e3","first_computed_at":"2026-07-05T05:04:22.694658Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:04:22.694658Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QptIGo3/RgaA9hKAzQXg0Pz34yuvqg5X6yBrMMmh3usFLdviBijEyD8WQ+NeIEmNNGue7ZbTW66Vr5c1b/mFDA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:04:22.695084Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.03671","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5cb5c85c93a137bdd3208ed8643364c9e7ef11565021f9a9ca7fa01249c06809","sha256:8669621209057819a6a3c61a677615c1ccead79cf606af3458b2e36663ebc653"],"state_sha256":"e72da765c4b14031448790cca38aa2715c063fdc058112a7cfcec0020804cfd9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CG+G6MzBIOu/QpBDK1S88yCAvbt4oYeApJIWR8sK9xZ5gkwH+gf7/aHIUeKZQBzKmxmV10UNllv6ZZcPKphjAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T18:22:13.549188Z","bundle_sha256":"f0f5e1c1322ad4710e2783f636973e0b5c79c5cfd48d48f824a2d26ca198e292"}}