{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:JYA3P7RCBIJM4ZQBVOT4ND7SNE","short_pith_number":"pith:JYA3P7RC","canonical_record":{"source":{"id":"1809.05476","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-14T15:53:14Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"424dadc3643811a1bb615dd7e5955b62a8c78c57174f46f652f8f04afcbad9a3","abstract_canon_sha256":"d3bd2a034a3d5cb82b12ae42ad479d9273bbef387bbfe6db9df88b4db6e356e1"},"schema_version":"1.0"},"canonical_sha256":"4e01b7fe220a12ce6601aba7c68ff2690a6604fce6dd1e2b1db8ed9c62640940","source":{"kind":"arxiv","id":"1809.05476","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.05476","created_at":"2026-05-18T00:05:41Z"},{"alias_kind":"arxiv_version","alias_value":"1809.05476v1","created_at":"2026-05-18T00:05:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.05476","created_at":"2026-05-18T00:05:41Z"},{"alias_kind":"pith_short_12","alias_value":"JYA3P7RCBIJM","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"JYA3P7RCBIJM4ZQB","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"JYA3P7RC","created_at":"2026-05-18T12:32:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:JYA3P7RCBIJM4ZQBVOT4ND7SNE","target":"record","payload":{"canonical_record":{"source":{"id":"1809.05476","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-14T15:53:14Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"424dadc3643811a1bb615dd7e5955b62a8c78c57174f46f652f8f04afcbad9a3","abstract_canon_sha256":"d3bd2a034a3d5cb82b12ae42ad479d9273bbef387bbfe6db9df88b4db6e356e1"},"schema_version":"1.0"},"canonical_sha256":"4e01b7fe220a12ce6601aba7c68ff2690a6604fce6dd1e2b1db8ed9c62640940","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:41.328350Z","signature_b64":"y+cQu59s4FmzOhmlBuKpMbY5KrJ264NYoXXzxqZGEYns8SAGgX20OdW5C0p0XXYCla2aRcpS45mbC1Y5gKthAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e01b7fe220a12ce6601aba7c68ff2690a6604fce6dd1e2b1db8ed9c62640940","last_reissued_at":"2026-05-18T00:05:41.327643Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:41.327643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.05476","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":"2026-05-18T00:05:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/kP4vr6rL1H3mFd9xsv5ea5M+SJa1Xakvh/4RmPtkFQ3mfY+BnZdASGFOWoXhUPbARqA+QuqNcTiH50KUeEEAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T21:03:34.930469Z"},"content_sha256":"8ea30bea4830fa4082216bda188a26181173979a2f0194f9aac350f989965f0c","schema_version":"1.0","event_id":"sha256:8ea30bea4830fa4082216bda188a26181173979a2f0194f9aac350f989965f0c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:JYA3P7RCBIJM4ZQBVOT4ND7SNE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hardware-Aware Machine Learning: Modeling and Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Diana Marculescu, Dimitrios Stamoulis, Ermao Cai","submitted_at":"2018-09-14T15:53:14Z","abstract_excerpt":"Recent breakthroughs in Deep Learning (DL) applications have made DL models a key component in almost every modern computing system. The increased popularity of DL applications deployed on a wide-spectrum of platforms have resulted in a plethora of design challenges related to the constraints introduced by the hardware itself. What is the latency or energy cost for an inference made by a Deep Neural Network (DNN)? Is it possible to predict this latency or energy consumption before a model is trained? If yes, how can machine learners take advantage of these models to design the hardware-optimal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.05476","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":"2026-05-18T00:05:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5ehUwCuDz/ueMwo3aBEjzdtKRNo6quadDw2SgqPdN+NEcWpJX3F6tKbFU6AHb4xNfibV8nqYQZiLWJqh5ugkDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T21:03:34.931046Z"},"content_sha256":"03c0fde962092af481c43793375da1efd63bc4dca877f3b032bc121674aface8","schema_version":"1.0","event_id":"sha256:03c0fde962092af481c43793375da1efd63bc4dca877f3b032bc121674aface8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JYA3P7RCBIJM4ZQBVOT4ND7SNE/bundle.json","state_url":"https://pith.science/pith/JYA3P7RCBIJM4ZQBVOT4ND7SNE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JYA3P7RCBIJM4ZQBVOT4ND7SNE/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":"2026-06-06T21:03:34Z","links":{"resolver":"https://pith.science/pith/JYA3P7RCBIJM4ZQBVOT4ND7SNE","bundle":"https://pith.science/pith/JYA3P7RCBIJM4ZQBVOT4ND7SNE/bundle.json","state":"https://pith.science/pith/JYA3P7RCBIJM4ZQBVOT4ND7SNE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JYA3P7RCBIJM4ZQBVOT4ND7SNE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:JYA3P7RCBIJM4ZQBVOT4ND7SNE","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":"d3bd2a034a3d5cb82b12ae42ad479d9273bbef387bbfe6db9df88b4db6e356e1","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-14T15:53:14Z","title_canon_sha256":"424dadc3643811a1bb615dd7e5955b62a8c78c57174f46f652f8f04afcbad9a3"},"schema_version":"1.0","source":{"id":"1809.05476","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.05476","created_at":"2026-05-18T00:05:41Z"},{"alias_kind":"arxiv_version","alias_value":"1809.05476v1","created_at":"2026-05-18T00:05:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.05476","created_at":"2026-05-18T00:05:41Z"},{"alias_kind":"pith_short_12","alias_value":"JYA3P7RCBIJM","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"JYA3P7RCBIJM4ZQB","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"JYA3P7RC","created_at":"2026-05-18T12:32:33Z"}],"graph_snapshots":[{"event_id":"sha256:03c0fde962092af481c43793375da1efd63bc4dca877f3b032bc121674aface8","target":"graph","created_at":"2026-05-18T00:05:41Z","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":"Recent breakthroughs in Deep Learning (DL) applications have made DL models a key component in almost every modern computing system. The increased popularity of DL applications deployed on a wide-spectrum of platforms have resulted in a plethora of design challenges related to the constraints introduced by the hardware itself. What is the latency or energy cost for an inference made by a Deep Neural Network (DNN)? Is it possible to predict this latency or energy consumption before a model is trained? If yes, how can machine learners take advantage of these models to design the hardware-optimal","authors_text":"Diana Marculescu, Dimitrios Stamoulis, Ermao Cai","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-14T15:53:14Z","title":"Hardware-Aware Machine Learning: Modeling and Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.05476","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":"sha256:8ea30bea4830fa4082216bda188a26181173979a2f0194f9aac350f989965f0c","target":"record","created_at":"2026-05-18T00:05:41Z","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":"d3bd2a034a3d5cb82b12ae42ad479d9273bbef387bbfe6db9df88b4db6e356e1","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-14T15:53:14Z","title_canon_sha256":"424dadc3643811a1bb615dd7e5955b62a8c78c57174f46f652f8f04afcbad9a3"},"schema_version":"1.0","source":{"id":"1809.05476","kind":"arxiv","version":1}},"canonical_sha256":"4e01b7fe220a12ce6601aba7c68ff2690a6604fce6dd1e2b1db8ed9c62640940","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4e01b7fe220a12ce6601aba7c68ff2690a6604fce6dd1e2b1db8ed9c62640940","first_computed_at":"2026-05-18T00:05:41.327643Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:05:41.327643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y+cQu59s4FmzOhmlBuKpMbY5KrJ264NYoXXzxqZGEYns8SAGgX20OdW5C0p0XXYCla2aRcpS45mbC1Y5gKthAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:05:41.328350Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.05476","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ea30bea4830fa4082216bda188a26181173979a2f0194f9aac350f989965f0c","sha256:03c0fde962092af481c43793375da1efd63bc4dca877f3b032bc121674aface8"],"state_sha256":"184e47e66b21b588910b2a5e874083a1f7caf1603b7d543f7501128a0cb4dc1a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zvcwngarvvhWiA0x8vYftrnEJ24cmGoutm8dFLoq4CVkuIZEEyLbHB/b5vTQ1iJbb5QCMrFMnkb9UFFxhHA7DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T21:03:34.934305Z","bundle_sha256":"d56afa3f65132c1f675ac27cae36418e6d31888eba6e4fe1317ce5929d957309"}}