{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:FPHUVVLFUOJWN3KPUNK52IICH6","short_pith_number":"pith:FPHUVVLF","canonical_record":{"source":{"id":"2306.05785","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-09T09:57:17Z","cross_cats_sorted":[],"title_canon_sha256":"0df9466c2bdec115316b72e41005bd80fd4fbf67c517cbd3ef34a5ec8795d350","abstract_canon_sha256":"9a11957742f9e8d7033b5407b7113aa8851c68c93062cad868767d5dc730af92"},"schema_version":"1.0"},"canonical_sha256":"2bcf4ad565a39366ed4fa355dd21023f894d3291eb75b691b808a38d7bfd9de2","source":{"kind":"arxiv","id":"2306.05785","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.05785","created_at":"2026-07-05T06:20:00Z"},{"alias_kind":"arxiv_version","alias_value":"2306.05785v2","created_at":"2026-07-05T06:20:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05785","created_at":"2026-07-05T06:20:00Z"},{"alias_kind":"pith_short_12","alias_value":"FPHUVVLFUOJW","created_at":"2026-07-05T06:20:00Z"},{"alias_kind":"pith_short_16","alias_value":"FPHUVVLFUOJWN3KP","created_at":"2026-07-05T06:20:00Z"},{"alias_kind":"pith_short_8","alias_value":"FPHUVVLF","created_at":"2026-07-05T06:20:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:FPHUVVLFUOJWN3KPUNK52IICH6","target":"record","payload":{"canonical_record":{"source":{"id":"2306.05785","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-09T09:57:17Z","cross_cats_sorted":[],"title_canon_sha256":"0df9466c2bdec115316b72e41005bd80fd4fbf67c517cbd3ef34a5ec8795d350","abstract_canon_sha256":"9a11957742f9e8d7033b5407b7113aa8851c68c93062cad868767d5dc730af92"},"schema_version":"1.0"},"canonical_sha256":"2bcf4ad565a39366ed4fa355dd21023f894d3291eb75b691b808a38d7bfd9de2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:20:00.586394Z","signature_b64":"Qte5mHBRgR5jiMLgigsegCL5VlcIV++x8KJ7eenOtnLCk0Xbnk+A7+BdcgWTN8VMW38iWtWMN0q8ILYfM2bLCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2bcf4ad565a39366ed4fa355dd21023f894d3291eb75b691b808a38d7bfd9de2","last_reissued_at":"2026-07-05T06:20:00.585986Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:20:00.585986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.05785","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:20:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XmYg42MzeiO4/ltZisvPLzNH0NliPMyvXmi5uXNfN10SgBRZSmeMZ+eHSbmg+KwSMNYH6uvU6HiaOcMJ9QN1DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:00:25.706714Z"},"content_sha256":"96f2499d36410e6b15827f22e06e620dd7654a1f28fcd0e1bc5a25cbdc3d356c","schema_version":"1.0","event_id":"sha256:96f2499d36410e6b15827f22e06e620dd7654a1f28fcd0e1bc5a25cbdc3d356c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:FPHUVVLFUOJWN3KPUNK52IICH6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"End-to-End Neural Network Compression via $\\frac{\\ell_1}{\\ell_2}$ Regularized Latency Surrogates","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anshul Nasery, Arun Sai Suggala, Hardik Shah, Prateek Jain","submitted_at":"2023-06-09T09:57:17Z","abstract_excerpt":"Neural network (NN) compression via techniques such as pruning, quantization requires setting compression hyperparameters (e.g., number of channels to be pruned, bitwidths for quantization) for each layer either manually or via neural architecture search (NAS) which can be computationally expensive. We address this problem by providing an end-to-end technique that optimizes for model's Floating Point Operations (FLOPs) or for on-device latency via a novel $\\frac{\\ell_1}{\\ell_2}$ latency surrogate. Our algorithm is versatile and can be used with many popular compression methods including prunin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05785","kind":"arxiv","version":2},"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/2306.05785/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":"2026-07-05T06:20:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RbzJg0kMTOsy4EhpleTRxV1yBzvYOWePfAGV4aVfoZ85Hg297N5vtnE/WRd1xbOYqUaxcVgBzkso92UL9P0xCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:00:25.707082Z"},"content_sha256":"3b72f11cf6240c2d7493a7dda42ef215680ce0e8c60ee428b7adecbc4bb8da09","schema_version":"1.0","event_id":"sha256:3b72f11cf6240c2d7493a7dda42ef215680ce0e8c60ee428b7adecbc4bb8da09"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FPHUVVLFUOJWN3KPUNK52IICH6/bundle.json","state_url":"https://pith.science/pith/FPHUVVLFUOJWN3KPUNK52IICH6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FPHUVVLFUOJWN3KPUNK52IICH6/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":"2026-07-06T17:00:25Z","links":{"resolver":"https://pith.science/pith/FPHUVVLFUOJWN3KPUNK52IICH6","bundle":"https://pith.science/pith/FPHUVVLFUOJWN3KPUNK52IICH6/bundle.json","state":"https://pith.science/pith/FPHUVVLFUOJWN3KPUNK52IICH6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FPHUVVLFUOJWN3KPUNK52IICH6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FPHUVVLFUOJWN3KPUNK52IICH6","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":"9a11957742f9e8d7033b5407b7113aa8851c68c93062cad868767d5dc730af92","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-09T09:57:17Z","title_canon_sha256":"0df9466c2bdec115316b72e41005bd80fd4fbf67c517cbd3ef34a5ec8795d350"},"schema_version":"1.0","source":{"id":"2306.05785","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.05785","created_at":"2026-07-05T06:20:00Z"},{"alias_kind":"arxiv_version","alias_value":"2306.05785v2","created_at":"2026-07-05T06:20:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05785","created_at":"2026-07-05T06:20:00Z"},{"alias_kind":"pith_short_12","alias_value":"FPHUVVLFUOJW","created_at":"2026-07-05T06:20:00Z"},{"alias_kind":"pith_short_16","alias_value":"FPHUVVLFUOJWN3KP","created_at":"2026-07-05T06:20:00Z"},{"alias_kind":"pith_short_8","alias_value":"FPHUVVLF","created_at":"2026-07-05T06:20:00Z"}],"graph_snapshots":[{"event_id":"sha256:3b72f11cf6240c2d7493a7dda42ef215680ce0e8c60ee428b7adecbc4bb8da09","target":"graph","created_at":"2026-07-05T06:20:00Z","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/2306.05785/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural network (NN) compression via techniques such as pruning, quantization requires setting compression hyperparameters (e.g., number of channels to be pruned, bitwidths for quantization) for each layer either manually or via neural architecture search (NAS) which can be computationally expensive. We address this problem by providing an end-to-end technique that optimizes for model's Floating Point Operations (FLOPs) or for on-device latency via a novel $\\frac{\\ell_1}{\\ell_2}$ latency surrogate. Our algorithm is versatile and can be used with many popular compression methods including prunin","authors_text":"Anshul Nasery, Arun Sai Suggala, Hardik Shah, Prateek Jain","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-09T09:57:17Z","title":"End-to-End Neural Network Compression via $\\frac{\\ell_1}{\\ell_2}$ Regularized Latency Surrogates"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05785","kind":"arxiv","version":2},"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":"sha256:96f2499d36410e6b15827f22e06e620dd7654a1f28fcd0e1bc5a25cbdc3d356c","target":"record","created_at":"2026-07-05T06:20:00Z","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":"9a11957742f9e8d7033b5407b7113aa8851c68c93062cad868767d5dc730af92","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-09T09:57:17Z","title_canon_sha256":"0df9466c2bdec115316b72e41005bd80fd4fbf67c517cbd3ef34a5ec8795d350"},"schema_version":"1.0","source":{"id":"2306.05785","kind":"arxiv","version":2}},"canonical_sha256":"2bcf4ad565a39366ed4fa355dd21023f894d3291eb75b691b808a38d7bfd9de2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2bcf4ad565a39366ed4fa355dd21023f894d3291eb75b691b808a38d7bfd9de2","first_computed_at":"2026-07-05T06:20:00.585986Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:20:00.585986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Qte5mHBRgR5jiMLgigsegCL5VlcIV++x8KJ7eenOtnLCk0Xbnk+A7+BdcgWTN8VMW38iWtWMN0q8ILYfM2bLCw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:20:00.586394Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.05785","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:96f2499d36410e6b15827f22e06e620dd7654a1f28fcd0e1bc5a25cbdc3d356c","sha256:3b72f11cf6240c2d7493a7dda42ef215680ce0e8c60ee428b7adecbc4bb8da09"],"state_sha256":"fdbc9da4aa3ce02e3c1e44ea86faea90087216175d3edca0db4d55d37d3d093a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wUca+TEdq3Q6jI0kf8dtAxdYpFz0mtXLqwM1JdqN/1KsCibTaBHwGfBvRQWllEVso2jMjf1hV0VgBgMcVBscCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T17:00:25.708971Z","bundle_sha256":"3a1c2a7a212caa8ee59840c907ecaba31fed6784d7e282eb7eb0328d3b75941d"}}