{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:W5CZEPLMD77474XLK4HUP3E5VN","short_pith_number":"pith:W5CZEPLM","canonical_record":{"source":{"id":"1802.06944","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-20T03:03:40Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3b3915ea039930d5a20729f34a61a6772d74c5c077d643b108b3f21549435042","abstract_canon_sha256":"053a354aec6cc494a65be593f339f64b56c8e1f1c4d9d1e640a0985bfa500d18"},"schema_version":"1.0"},"canonical_sha256":"b745923d6c1fffcff2eb570f47ec9dab6b1f6d4f53470002de62f49fda79074e","source":{"kind":"arxiv","id":"1802.06944","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.06944","created_at":"2026-05-18T00:22:53Z"},{"alias_kind":"arxiv_version","alias_value":"1802.06944v1","created_at":"2026-05-18T00:22:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.06944","created_at":"2026-05-18T00:22:53Z"},{"alias_kind":"pith_short_12","alias_value":"W5CZEPLMD774","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"W5CZEPLMD77474XL","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"W5CZEPLM","created_at":"2026-05-18T12:32:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:W5CZEPLMD77474XLK4HUP3E5VN","target":"record","payload":{"canonical_record":{"source":{"id":"1802.06944","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-20T03:03:40Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3b3915ea039930d5a20729f34a61a6772d74c5c077d643b108b3f21549435042","abstract_canon_sha256":"053a354aec6cc494a65be593f339f64b56c8e1f1c4d9d1e640a0985bfa500d18"},"schema_version":"1.0"},"canonical_sha256":"b745923d6c1fffcff2eb570f47ec9dab6b1f6d4f53470002de62f49fda79074e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:53.924556Z","signature_b64":"vpM79wyi1Zy3bTgtCmwZeVSYtIh1yCsF3uHZBYI1fPF5xbZOsUP+QNCZbMOdbQ95McpgONUX/NIzqa+5oiK5Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b745923d6c1fffcff2eb570f47ec9dab6b1f6d4f53470002de62f49fda79074e","last_reissued_at":"2026-05-18T00:22:53.924187Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:53.924187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.06944","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":"2026-05-18T00:22:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0brOSd0YrbDiWz17moel2KiXBGam1FdyB/T1gMpnxbCdys+1/mBRkksyx4g/jG+BpUHI3w54B51AZVXOvMzwAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T10:21:53.190217Z"},"content_sha256":"a8cd3f00fa1cdf41a877cc4475801a33fc95a0ca3bbd219aac46fc42d6e98906","schema_version":"1.0","event_id":"sha256:a8cd3f00fa1cdf41a877cc4475801a33fc95a0ca3bbd219aac46fc42d6e98906"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:W5CZEPLMD77474XLK4HUP3E5VN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DeepThin: A Self-Compressing Library for Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Matthew Sotoudeh, Sara S. Baghsorkhi","submitted_at":"2018-02-20T03:03:40Z","abstract_excerpt":"As the industry deploys increasingly large and complex neural networks to mobile devices, more pressure is put on the memory and compute resources of those devices. Deep compression, or compression of deep neural network weight matrices, is a technique to stretch resources for such scenarios. Existing compression methods cannot effectively compress models smaller than 1-2% of their original size. We develop a new compression technique, DeepThin, building on existing research in the area of low rank factorization. We identify and break artificial constraints imposed by low rank approximations b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.06944","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":"2026-05-18T00:22:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WGTQaHOEhXmPKifjY61Vl9xlK6EHzSrjvCGXPT7InsSGdwIEkL/y7HeyN1jRVlWfXG5G0+kH9hQzDAyW1r1zCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T10:21:53.190589Z"},"content_sha256":"c5abc4c82e4f68ba1a8ca63b1e732a0827d4b388dfc2c0f74243b607f78c79ba","schema_version":"1.0","event_id":"sha256:c5abc4c82e4f68ba1a8ca63b1e732a0827d4b388dfc2c0f74243b607f78c79ba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W5CZEPLMD77474XLK4HUP3E5VN/bundle.json","state_url":"https://pith.science/pith/W5CZEPLMD77474XLK4HUP3E5VN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W5CZEPLMD77474XLK4HUP3E5VN/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":"2026-06-26T10:21:53Z","links":{"resolver":"https://pith.science/pith/W5CZEPLMD77474XLK4HUP3E5VN","bundle":"https://pith.science/pith/W5CZEPLMD77474XLK4HUP3E5VN/bundle.json","state":"https://pith.science/pith/W5CZEPLMD77474XLK4HUP3E5VN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W5CZEPLMD77474XLK4HUP3E5VN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:W5CZEPLMD77474XLK4HUP3E5VN","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":"053a354aec6cc494a65be593f339f64b56c8e1f1c4d9d1e640a0985bfa500d18","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-20T03:03:40Z","title_canon_sha256":"3b3915ea039930d5a20729f34a61a6772d74c5c077d643b108b3f21549435042"},"schema_version":"1.0","source":{"id":"1802.06944","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.06944","created_at":"2026-05-18T00:22:53Z"},{"alias_kind":"arxiv_version","alias_value":"1802.06944v1","created_at":"2026-05-18T00:22:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.06944","created_at":"2026-05-18T00:22:53Z"},{"alias_kind":"pith_short_12","alias_value":"W5CZEPLMD774","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"W5CZEPLMD77474XL","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"W5CZEPLM","created_at":"2026-05-18T12:32:59Z"}],"graph_snapshots":[{"event_id":"sha256:c5abc4c82e4f68ba1a8ca63b1e732a0827d4b388dfc2c0f74243b607f78c79ba","target":"graph","created_at":"2026-05-18T00:22:53Z","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":"As the industry deploys increasingly large and complex neural networks to mobile devices, more pressure is put on the memory and compute resources of those devices. Deep compression, or compression of deep neural network weight matrices, is a technique to stretch resources for such scenarios. Existing compression methods cannot effectively compress models smaller than 1-2% of their original size. We develop a new compression technique, DeepThin, building on existing research in the area of low rank factorization. We identify and break artificial constraints imposed by low rank approximations b","authors_text":"Matthew Sotoudeh, Sara S. Baghsorkhi","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-20T03:03:40Z","title":"DeepThin: A Self-Compressing Library for Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.06944","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:a8cd3f00fa1cdf41a877cc4475801a33fc95a0ca3bbd219aac46fc42d6e98906","target":"record","created_at":"2026-05-18T00:22:53Z","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":"053a354aec6cc494a65be593f339f64b56c8e1f1c4d9d1e640a0985bfa500d18","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-20T03:03:40Z","title_canon_sha256":"3b3915ea039930d5a20729f34a61a6772d74c5c077d643b108b3f21549435042"},"schema_version":"1.0","source":{"id":"1802.06944","kind":"arxiv","version":1}},"canonical_sha256":"b745923d6c1fffcff2eb570f47ec9dab6b1f6d4f53470002de62f49fda79074e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b745923d6c1fffcff2eb570f47ec9dab6b1f6d4f53470002de62f49fda79074e","first_computed_at":"2026-05-18T00:22:53.924187Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:22:53.924187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vpM79wyi1Zy3bTgtCmwZeVSYtIh1yCsF3uHZBYI1fPF5xbZOsUP+QNCZbMOdbQ95McpgONUX/NIzqa+5oiK5Bg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:22:53.924556Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.06944","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a8cd3f00fa1cdf41a877cc4475801a33fc95a0ca3bbd219aac46fc42d6e98906","sha256:c5abc4c82e4f68ba1a8ca63b1e732a0827d4b388dfc2c0f74243b607f78c79ba"],"state_sha256":"662d8b03988c81a95567b0f0b90720ed958e3aa8eca2724a5cfb70082446fff5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UQEKeYvTRn+9sac1VTnx31g1HH3sDbCLUb02XgVaAbXbNiVVbnQuOoLiJIOBirT+bbwkDPKl6ojsYqKu1bstDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-26T10:21:53.192492Z","bundle_sha256":"63d6f6aee3b7f437b8b4c206d4c4a77b65e4f95cb72ff70099e2c062a57242b8"}}