{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:2LBYXZJSOUBYMD5C346YKPRMIU","short_pith_number":"pith:2LBYXZJS","canonical_record":{"source":{"id":"2001.00218","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-01T15:04:43Z","cross_cats_sorted":["cs.DS","math.OC","stat.ML"],"title_canon_sha256":"8b571bbe1d1172dbadf8ccb7536c512afb8b09ab48e91ea15174d9c217ce884c","abstract_canon_sha256":"6f66c6b5204b51f3b71a1fe7b09cd690ac179ead83c0192611f7306015c83663"},"schema_version":"1.0"},"canonical_sha256":"d2c38be5327503860fa2df3d853e2c453cd6079586299875f82463ec3e9e56c3","source":{"kind":"arxiv","id":"2001.00218","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.00218","created_at":"2026-07-05T00:43:06Z"},{"alias_kind":"arxiv_version","alias_value":"2001.00218v3","created_at":"2026-07-05T00:43:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.00218","created_at":"2026-07-05T00:43:06Z"},{"alias_kind":"pith_short_12","alias_value":"2LBYXZJSOUBY","created_at":"2026-07-05T00:43:06Z"},{"alias_kind":"pith_short_16","alias_value":"2LBYXZJSOUBYMD5C","created_at":"2026-07-05T00:43:06Z"},{"alias_kind":"pith_short_8","alias_value":"2LBYXZJS","created_at":"2026-07-05T00:43:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:2LBYXZJSOUBYMD5C346YKPRMIU","target":"record","payload":{"canonical_record":{"source":{"id":"2001.00218","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-01T15:04:43Z","cross_cats_sorted":["cs.DS","math.OC","stat.ML"],"title_canon_sha256":"8b571bbe1d1172dbadf8ccb7536c512afb8b09ab48e91ea15174d9c217ce884c","abstract_canon_sha256":"6f66c6b5204b51f3b71a1fe7b09cd690ac179ead83c0192611f7306015c83663"},"schema_version":"1.0"},"canonical_sha256":"d2c38be5327503860fa2df3d853e2c453cd6079586299875f82463ec3e9e56c3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:43:06.539640Z","signature_b64":"Unip+r9WlBqkBCfC9naFOfsFYwVxPmmE2pK77coTuHyJd14KOD8Q8U0XRBchXJm9DUhYr+qx21NftqP2NyHkCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2c38be5327503860fa2df3d853e2c453cd6079586299875f82463ec3e9e56c3","last_reissued_at":"2026-07-05T00:43:06.539245Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:43:06.539245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2001.00218","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:43:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fAEv/JwW5kee8INSDcwJ2LEWITsQJO8JsKzx6VEAb8sZjd3NpaO90M5A3PP3nn3LuuOlLQdth86djJYgSHpQDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:41:35.469729Z"},"content_sha256":"53664036e7983e3fe7803fbfef3884966f2060debb5d779dfbc9e48554ceb7f3","schema_version":"1.0","event_id":"sha256:53664036e7983e3fe7803fbfef3884966f2060debb5d779dfbc9e48554ceb7f3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:2LBYXZJSOUBYMD5C346YKPRMIU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Lossless Compression of Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhinav Kumar, Srikumar Ramalingam, Thiago Serra","submitted_at":"2020-01-01T15:04:43Z","abstract_excerpt":"Deep neural networks have been successful in many predictive modeling tasks, such as image and language recognition, where large neural networks are often used to obtain good accuracy. Consequently, it is challenging to deploy these networks under limited computational resources, such as in mobile devices. In this work, we introduce an algorithm that removes units and layers of a neural network while not changing the output that is produced, which thus implies a lossless compression. This algorithm, which we denote as LEO (Lossless Expressiveness Optimization), relies on Mixed-Integer Linear P"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.00218","kind":"arxiv","version":3},"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/2001.00218/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":"2026-07-05T00:43:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"52R5OOiRqObKkLca4jjSLBiKvl+35pTvszl1qVrIRoqtcvdvYv0IRO+LkrighK4XKr9LeImIZPpKwm88Yn+bDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:41:35.470627Z"},"content_sha256":"6ac60bfe049b0579139c1838100668c490cbc0d605a3243d27ea23d0d3579812","schema_version":"1.0","event_id":"sha256:6ac60bfe049b0579139c1838100668c490cbc0d605a3243d27ea23d0d3579812"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2LBYXZJSOUBYMD5C346YKPRMIU/bundle.json","state_url":"https://pith.science/pith/2LBYXZJSOUBYMD5C346YKPRMIU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2LBYXZJSOUBYMD5C346YKPRMIU/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":"2026-08-09T18:41:35Z","links":{"resolver":"https://pith.science/pith/2LBYXZJSOUBYMD5C346YKPRMIU","bundle":"https://pith.science/pith/2LBYXZJSOUBYMD5C346YKPRMIU/bundle.json","state":"https://pith.science/pith/2LBYXZJSOUBYMD5C346YKPRMIU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2LBYXZJSOUBYMD5C346YKPRMIU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:2LBYXZJSOUBYMD5C346YKPRMIU","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":"6f66c6b5204b51f3b71a1fe7b09cd690ac179ead83c0192611f7306015c83663","cross_cats_sorted":["cs.DS","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-01T15:04:43Z","title_canon_sha256":"8b571bbe1d1172dbadf8ccb7536c512afb8b09ab48e91ea15174d9c217ce884c"},"schema_version":"1.0","source":{"id":"2001.00218","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.00218","created_at":"2026-07-05T00:43:06Z"},{"alias_kind":"arxiv_version","alias_value":"2001.00218v3","created_at":"2026-07-05T00:43:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.00218","created_at":"2026-07-05T00:43:06Z"},{"alias_kind":"pith_short_12","alias_value":"2LBYXZJSOUBY","created_at":"2026-07-05T00:43:06Z"},{"alias_kind":"pith_short_16","alias_value":"2LBYXZJSOUBYMD5C","created_at":"2026-07-05T00:43:06Z"},{"alias_kind":"pith_short_8","alias_value":"2LBYXZJS","created_at":"2026-07-05T00:43:06Z"}],"graph_snapshots":[{"event_id":"sha256:6ac60bfe049b0579139c1838100668c490cbc0d605a3243d27ea23d0d3579812","target":"graph","created_at":"2026-07-05T00:43:06Z","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/2001.00218/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep neural networks have been successful in many predictive modeling tasks, such as image and language recognition, where large neural networks are often used to obtain good accuracy. Consequently, it is challenging to deploy these networks under limited computational resources, such as in mobile devices. In this work, we introduce an algorithm that removes units and layers of a neural network while not changing the output that is produced, which thus implies a lossless compression. This algorithm, which we denote as LEO (Lossless Expressiveness Optimization), relies on Mixed-Integer Linear P","authors_text":"Abhinav Kumar, Srikumar Ramalingam, Thiago Serra","cross_cats":["cs.DS","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-01T15:04:43Z","title":"Lossless Compression of Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.00218","kind":"arxiv","version":3},"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":"sha256:53664036e7983e3fe7803fbfef3884966f2060debb5d779dfbc9e48554ceb7f3","target":"record","created_at":"2026-07-05T00:43:06Z","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":"6f66c6b5204b51f3b71a1fe7b09cd690ac179ead83c0192611f7306015c83663","cross_cats_sorted":["cs.DS","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-01T15:04:43Z","title_canon_sha256":"8b571bbe1d1172dbadf8ccb7536c512afb8b09ab48e91ea15174d9c217ce884c"},"schema_version":"1.0","source":{"id":"2001.00218","kind":"arxiv","version":3}},"canonical_sha256":"d2c38be5327503860fa2df3d853e2c453cd6079586299875f82463ec3e9e56c3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d2c38be5327503860fa2df3d853e2c453cd6079586299875f82463ec3e9e56c3","first_computed_at":"2026-07-05T00:43:06.539245Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:43:06.539245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Unip+r9WlBqkBCfC9naFOfsFYwVxPmmE2pK77coTuHyJd14KOD8Q8U0XRBchXJm9DUhYr+qx21NftqP2NyHkCg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:43:06.539640Z","signed_message":"canonical_sha256_bytes"},"source_id":"2001.00218","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:53664036e7983e3fe7803fbfef3884966f2060debb5d779dfbc9e48554ceb7f3","sha256:6ac60bfe049b0579139c1838100668c490cbc0d605a3243d27ea23d0d3579812"],"state_sha256":"284f3601b4aa119eabab7756fb930db4db46856af6a25ada2fcd04a6e5d4a9a8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CoDShUZNlbEY5YNRqk/HQkX4WZuSEOLKa+b8jAfFSSkHTRaKRYZLW7Er21eOViSPCGP0UXJ3kPC/GyJrt1QzBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T18:41:35.478149Z","bundle_sha256":"f666ecb926922102a6a3356b2f942b141ae1fb3af5624c16178ed11899027e18"}}