{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:FBMC6IY2YTORKOJISIEZA5VUVG","short_pith_number":"pith:FBMC6IY2","canonical_record":{"source":{"id":"1810.06401","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2018-10-09T18:44:22Z","cross_cats_sorted":["cs.LG","math.IT","stat.ML"],"title_canon_sha256":"08c781d0f0f6535fe0c10499d04f7d9b7192ed754768ed53934fe9a4fcd129f0","abstract_canon_sha256":"460e4d114dc0466f23c983632d5c4b324f15c8479a58ccca9770e5fe1ecf3004"},"schema_version":"1.0"},"canonical_sha256":"28582f231ac4dd15392892099076b4a9958ce021f132d524f09882b787bd700c","source":{"kind":"arxiv","id":"1810.06401","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.06401","created_at":"2026-05-17T23:55:38Z"},{"alias_kind":"arxiv_version","alias_value":"1810.06401v2","created_at":"2026-05-17T23:55:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.06401","created_at":"2026-05-17T23:55:38Z"},{"alias_kind":"pith_short_12","alias_value":"FBMC6IY2YTOR","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"FBMC6IY2YTORKOJI","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"FBMC6IY2","created_at":"2026-05-18T12:32:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:FBMC6IY2YTORKOJISIEZA5VUVG","target":"record","payload":{"canonical_record":{"source":{"id":"1810.06401","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2018-10-09T18:44:22Z","cross_cats_sorted":["cs.LG","math.IT","stat.ML"],"title_canon_sha256":"08c781d0f0f6535fe0c10499d04f7d9b7192ed754768ed53934fe9a4fcd129f0","abstract_canon_sha256":"460e4d114dc0466f23c983632d5c4b324f15c8479a58ccca9770e5fe1ecf3004"},"schema_version":"1.0"},"canonical_sha256":"28582f231ac4dd15392892099076b4a9958ce021f132d524f09882b787bd700c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:38.343001Z","signature_b64":"pw3ZDRfX+9WOzOLSBN61MjbDyP37VmWoIH8Inc6/0p0y6qZW1sniPsN+A/v/r7LGRbV4H6eiO6fY7r7RBlaMDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28582f231ac4dd15392892099076b4a9958ce021f132d524f09882b787bd700c","last_reissued_at":"2026-05-17T23:55:38.342387Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:38.342387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.06401","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":"2026-05-17T23:55:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WMeRyo3J0WbxkScmID+rdSeL2mLbOsj4eI4mbUBVIX0A04s1Ce3ySjhOZ2r6W/0DLrZyjdfUleLveWx2MBpWDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T16:24:55.114642Z"},"content_sha256":"02a5cb1d92b2667cc3563c37a43aa82a3591bec5bba9717f8db9559b7bccc6c5","schema_version":"1.0","event_id":"sha256:02a5cb1d92b2667cc3563c37a43aa82a3591bec5bba9717f8db9559b7bccc6c5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:FBMC6IY2YTORKOJISIEZA5VUVG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rate Distortion For Model Compression: From Theory To Practice","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.IT","stat.ML"],"primary_cat":"cs.IT","authors_text":"Chong Wang, Sewoong Oh, Weihao Gao, Yu-Han Liu","submitted_at":"2018-10-09T18:44:22Z","abstract_excerpt":"The enormous size of modern deep neural networks makes it challenging to deploy those models in memory and communication limited scenarios. Thus, compressing a trained model without a significant loss in performance has become an increasingly important task. Tremendous advances has been made recently, where the main technical building blocks are parameter pruning, parameter sharing (quantization), and low-rank factorization. In this paper, we propose principled approaches to improve upon the common heuristics used in those building blocks, namely pruning and quantization.\n  We first study the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.06401","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":""},"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":"2026-05-17T23:55:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ruR7SQCO22Wcim0Tfk7hB2gMgu4mMDQrucAz6L7xepg3R58DQeIxlTb4H8XCdqkqhy2lmE9pxHxAuw9eUL3LCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T16:24:55.114988Z"},"content_sha256":"88d035e65a2298da427e09c45c1e88f133b00c4ea416bc693688a2a8e5524632","schema_version":"1.0","event_id":"sha256:88d035e65a2298da427e09c45c1e88f133b00c4ea416bc693688a2a8e5524632"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FBMC6IY2YTORKOJISIEZA5VUVG/bundle.json","state_url":"https://pith.science/pith/FBMC6IY2YTORKOJISIEZA5VUVG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FBMC6IY2YTORKOJISIEZA5VUVG/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":"2026-06-09T16:24:55Z","links":{"resolver":"https://pith.science/pith/FBMC6IY2YTORKOJISIEZA5VUVG","bundle":"https://pith.science/pith/FBMC6IY2YTORKOJISIEZA5VUVG/bundle.json","state":"https://pith.science/pith/FBMC6IY2YTORKOJISIEZA5VUVG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FBMC6IY2YTORKOJISIEZA5VUVG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:FBMC6IY2YTORKOJISIEZA5VUVG","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":"460e4d114dc0466f23c983632d5c4b324f15c8479a58ccca9770e5fe1ecf3004","cross_cats_sorted":["cs.LG","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2018-10-09T18:44:22Z","title_canon_sha256":"08c781d0f0f6535fe0c10499d04f7d9b7192ed754768ed53934fe9a4fcd129f0"},"schema_version":"1.0","source":{"id":"1810.06401","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.06401","created_at":"2026-05-17T23:55:38Z"},{"alias_kind":"arxiv_version","alias_value":"1810.06401v2","created_at":"2026-05-17T23:55:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.06401","created_at":"2026-05-17T23:55:38Z"},{"alias_kind":"pith_short_12","alias_value":"FBMC6IY2YTOR","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"FBMC6IY2YTORKOJI","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"FBMC6IY2","created_at":"2026-05-18T12:32:22Z"}],"graph_snapshots":[{"event_id":"sha256:88d035e65a2298da427e09c45c1e88f133b00c4ea416bc693688a2a8e5524632","target":"graph","created_at":"2026-05-17T23:55:38Z","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"},"paper":{"abstract_excerpt":"The enormous size of modern deep neural networks makes it challenging to deploy those models in memory and communication limited scenarios. Thus, compressing a trained model without a significant loss in performance has become an increasingly important task. Tremendous advances has been made recently, where the main technical building blocks are parameter pruning, parameter sharing (quantization), and low-rank factorization. In this paper, we propose principled approaches to improve upon the common heuristics used in those building blocks, namely pruning and quantization.\n  We first study the ","authors_text":"Chong Wang, Sewoong Oh, Weihao Gao, Yu-Han Liu","cross_cats":["cs.LG","math.IT","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2018-10-09T18:44:22Z","title":"Rate Distortion For Model Compression: From Theory To Practice"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.06401","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":"sha256:02a5cb1d92b2667cc3563c37a43aa82a3591bec5bba9717f8db9559b7bccc6c5","target":"record","created_at":"2026-05-17T23:55:38Z","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":"460e4d114dc0466f23c983632d5c4b324f15c8479a58ccca9770e5fe1ecf3004","cross_cats_sorted":["cs.LG","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2018-10-09T18:44:22Z","title_canon_sha256":"08c781d0f0f6535fe0c10499d04f7d9b7192ed754768ed53934fe9a4fcd129f0"},"schema_version":"1.0","source":{"id":"1810.06401","kind":"arxiv","version":2}},"canonical_sha256":"28582f231ac4dd15392892099076b4a9958ce021f132d524f09882b787bd700c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"28582f231ac4dd15392892099076b4a9958ce021f132d524f09882b787bd700c","first_computed_at":"2026-05-17T23:55:38.342387Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:55:38.342387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pw3ZDRfX+9WOzOLSBN61MjbDyP37VmWoIH8Inc6/0p0y6qZW1sniPsN+A/v/r7LGRbV4H6eiO6fY7r7RBlaMDw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:55:38.343001Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.06401","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:02a5cb1d92b2667cc3563c37a43aa82a3591bec5bba9717f8db9559b7bccc6c5","sha256:88d035e65a2298da427e09c45c1e88f133b00c4ea416bc693688a2a8e5524632"],"state_sha256":"a2bdd5b93fa872260e7158ac99d3495cd2c00566a45a4fbdf011633a996ea115"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SV9AFrtfp+po4jrj4P3+oN8oJs86yaFYFBF16YTWt3W32yA8V0JguW+kQoKNaB5jlTGQLjsiOH7QNuj9B2RQDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T16:24:55.117070Z","bundle_sha256":"8e98f574ecb833f03e80d74695dfe7662cbdf6f557a87396e5c4829ded0932e6"}}