{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:D7GFMC3AX2IZR7ROIIP2X3BAAT","short_pith_number":"pith:D7GFMC3A","canonical_record":{"source":{"id":"1810.12823","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-30T15:48:30Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"899fb40fdd38079794f87525f732aa79925085187032db471867f7e09bf2acf9","abstract_canon_sha256":"2341c3ba949827bf571977774e56c9a47656f8a46c6972a641b9bc44b48187f3"},"schema_version":"1.0"},"canonical_sha256":"1fcc560b60be9198fe2e421fabec2004db7de6e782b8dea837d885f2319569b3","source":{"kind":"arxiv","id":"1810.12823","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.12823","created_at":"2026-05-18T00:01:54Z"},{"alias_kind":"arxiv_version","alias_value":"1810.12823v1","created_at":"2026-05-18T00:01:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.12823","created_at":"2026-05-18T00:01:54Z"},{"alias_kind":"pith_short_12","alias_value":"D7GFMC3AX2IZ","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"D7GFMC3AX2IZR7RO","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"D7GFMC3A","created_at":"2026-05-18T12:32:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:D7GFMC3AX2IZR7ROIIP2X3BAAT","target":"record","payload":{"canonical_record":{"source":{"id":"1810.12823","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-30T15:48:30Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"899fb40fdd38079794f87525f732aa79925085187032db471867f7e09bf2acf9","abstract_canon_sha256":"2341c3ba949827bf571977774e56c9a47656f8a46c6972a641b9bc44b48187f3"},"schema_version":"1.0"},"canonical_sha256":"1fcc560b60be9198fe2e421fabec2004db7de6e782b8dea837d885f2319569b3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:54.057427Z","signature_b64":"H4oplDsfYrNyK1mMrU4a8TDdZqanduE9diknsxkQbDQ1xDqj59R9LiS4fspxFXwt/9RMnNHfqvjGjgkJ49SfAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1fcc560b60be9198fe2e421fabec2004db7de6e782b8dea837d885f2319569b3","last_reissued_at":"2026-05-18T00:01:54.056929Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:54.056929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.12823","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":"2026-05-18T00:01:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/mOag1HrghcQWj9IxRm0z0O0AiMGKRFrQzEcJEdVCfhfQvehBLKEj4YZp3Bgrl2w1kJ+w1zu6FqZlwgHtlfUAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T23:17:59.698860Z"},"content_sha256":"5b8a1df8389084ba8347af2183f6bdb749b14e1ced45122040ec3f62f7d7e30e","schema_version":"1.0","event_id":"sha256:5b8a1df8389084ba8347af2183f6bdb749b14e1ced45122040ec3f62f7d7e30e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:D7GFMC3AX2IZR7ROIIP2X3BAAT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DeepTwist: Learning Model Compression via Occasional Weight Distortion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Byeongwook Kim, Dongsoo Lee, Parichay Kapoor","submitted_at":"2018-10-30T15:48:30Z","abstract_excerpt":"Model compression has been introduced to reduce the required hardware resources while maintaining the model accuracy. Lots of techniques for model compression, such as pruning, quantization, and low-rank approximation, have been suggested along with different inference implementation characteristics. Adopting model compression is, however, still challenging because the design complexity of model compression is rapidly increasing due to additional hyper-parameters and computation overhead in order to achieve a high compression ratio. In this paper, we propose a simple and efficient model compre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.12823","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":""},"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":"2026-05-18T00:01:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xpInKZI9pmbTgO48vwiPxNPOMsfGSaPYYRaRvpuXTWQYLdYQgFrXG+Y/uPcDwE208KLsMPJZQ2ax/JU2fajFCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T23:17:59.699216Z"},"content_sha256":"0566b350f6d5606621fa17400d72e38a89f71f9d9304e2e4acfcd4c96f59719c","schema_version":"1.0","event_id":"sha256:0566b350f6d5606621fa17400d72e38a89f71f9d9304e2e4acfcd4c96f59719c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D7GFMC3AX2IZR7ROIIP2X3BAAT/bundle.json","state_url":"https://pith.science/pith/D7GFMC3AX2IZR7ROIIP2X3BAAT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D7GFMC3AX2IZR7ROIIP2X3BAAT/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":"2026-07-08T23:17:59Z","links":{"resolver":"https://pith.science/pith/D7GFMC3AX2IZR7ROIIP2X3BAAT","bundle":"https://pith.science/pith/D7GFMC3AX2IZR7ROIIP2X3BAAT/bundle.json","state":"https://pith.science/pith/D7GFMC3AX2IZR7ROIIP2X3BAAT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D7GFMC3AX2IZR7ROIIP2X3BAAT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:D7GFMC3AX2IZR7ROIIP2X3BAAT","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":"2341c3ba949827bf571977774e56c9a47656f8a46c6972a641b9bc44b48187f3","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-30T15:48:30Z","title_canon_sha256":"899fb40fdd38079794f87525f732aa79925085187032db471867f7e09bf2acf9"},"schema_version":"1.0","source":{"id":"1810.12823","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.12823","created_at":"2026-05-18T00:01:54Z"},{"alias_kind":"arxiv_version","alias_value":"1810.12823v1","created_at":"2026-05-18T00:01:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.12823","created_at":"2026-05-18T00:01:54Z"},{"alias_kind":"pith_short_12","alias_value":"D7GFMC3AX2IZ","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"D7GFMC3AX2IZR7RO","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"D7GFMC3A","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:0566b350f6d5606621fa17400d72e38a89f71f9d9304e2e4acfcd4c96f59719c","target":"graph","created_at":"2026-05-18T00:01:54Z","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":"Model compression has been introduced to reduce the required hardware resources while maintaining the model accuracy. Lots of techniques for model compression, such as pruning, quantization, and low-rank approximation, have been suggested along with different inference implementation characteristics. Adopting model compression is, however, still challenging because the design complexity of model compression is rapidly increasing due to additional hyper-parameters and computation overhead in order to achieve a high compression ratio. In this paper, we propose a simple and efficient model compre","authors_text":"Byeongwook Kim, Dongsoo Lee, Parichay Kapoor","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-30T15:48:30Z","title":"DeepTwist: Learning Model Compression via Occasional Weight Distortion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.12823","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":"sha256:5b8a1df8389084ba8347af2183f6bdb749b14e1ced45122040ec3f62f7d7e30e","target":"record","created_at":"2026-05-18T00:01:54Z","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":"2341c3ba949827bf571977774e56c9a47656f8a46c6972a641b9bc44b48187f3","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-30T15:48:30Z","title_canon_sha256":"899fb40fdd38079794f87525f732aa79925085187032db471867f7e09bf2acf9"},"schema_version":"1.0","source":{"id":"1810.12823","kind":"arxiv","version":1}},"canonical_sha256":"1fcc560b60be9198fe2e421fabec2004db7de6e782b8dea837d885f2319569b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1fcc560b60be9198fe2e421fabec2004db7de6e782b8dea837d885f2319569b3","first_computed_at":"2026-05-18T00:01:54.056929Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:01:54.056929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H4oplDsfYrNyK1mMrU4a8TDdZqanduE9diknsxkQbDQ1xDqj59R9LiS4fspxFXwt/9RMnNHfqvjGjgkJ49SfAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:01:54.057427Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.12823","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b8a1df8389084ba8347af2183f6bdb749b14e1ced45122040ec3f62f7d7e30e","sha256:0566b350f6d5606621fa17400d72e38a89f71f9d9304e2e4acfcd4c96f59719c"],"state_sha256":"f965dd4d6f14130af88438e37459dfa8e87ebaa223642b61f8fe5471d2102cca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2fdIZJbKWwEiITnog8xIWEN226BlE0b4lA9p3d9CzEC0k+LJz1dDgd1fkv3/7KBZP9tkuwx7+13lZnHxotLxCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T23:17:59.701219Z","bundle_sha256":"a81df0b54d5f52dca4a3009461fc55c6e8ec7f559054ecb2e5e172b0135f0aa6"}}