{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:VUIDRNWQB2KUVLBMT745GOG7XD","short_pith_number":"pith:VUIDRNWQ","canonical_record":{"source":{"id":"2307.00368","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-01T15:44:01Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"4563a97997c0e4a70fdbdb866bb53a57acc62ff068c8ca0f1b76d6824e744940","abstract_canon_sha256":"d2c9cefaa1b7e2450d85e766dd674324facd4816c50a38be70ad8b256ed63106"},"schema_version":"1.0"},"canonical_sha256":"ad1038b6d00e954aac2c9ff9d338dfb8e9d0044ee57f1e1375c349a98458504b","source":{"kind":"arxiv","id":"2307.00368","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.00368","created_at":"2026-07-05T06:26:55Z"},{"alias_kind":"arxiv_version","alias_value":"2307.00368v1","created_at":"2026-07-05T06:26:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.00368","created_at":"2026-07-05T06:26:55Z"},{"alias_kind":"pith_short_12","alias_value":"VUIDRNWQB2KU","created_at":"2026-07-05T06:26:55Z"},{"alias_kind":"pith_short_16","alias_value":"VUIDRNWQB2KUVLBM","created_at":"2026-07-05T06:26:55Z"},{"alias_kind":"pith_short_8","alias_value":"VUIDRNWQ","created_at":"2026-07-05T06:26:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:VUIDRNWQB2KUVLBMT745GOG7XD","target":"record","payload":{"canonical_record":{"source":{"id":"2307.00368","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-01T15:44:01Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"4563a97997c0e4a70fdbdb866bb53a57acc62ff068c8ca0f1b76d6824e744940","abstract_canon_sha256":"d2c9cefaa1b7e2450d85e766dd674324facd4816c50a38be70ad8b256ed63106"},"schema_version":"1.0"},"canonical_sha256":"ad1038b6d00e954aac2c9ff9d338dfb8e9d0044ee57f1e1375c349a98458504b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:26:55.343087Z","signature_b64":"7e3EkNTR1yebBqMe1HONcZz78Rfirzka0mThcRp/s5OoCbDzUxXwPPISTPJ5/E+7bxJuC3/Q9c+opdOjvedcAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad1038b6d00e954aac2c9ff9d338dfb8e9d0044ee57f1e1375c349a98458504b","last_reissued_at":"2026-07-05T06:26:55.342745Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:26:55.342745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.00368","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":"2026-07-05T06:26:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bFGy9QOElpBtz82VahIRsajuJDYlbHlDauEiCWYaSAWvC1YLQpAhik/ZNkQ+TZihkNYTHeZbwWbUrt7SSI7gAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T07:57:46.961947Z"},"content_sha256":"e7debac96d00f2f34ae43314f85cb31de8305f9a72de2bef907c5239b9004e18","schema_version":"1.0","event_id":"sha256:e7debac96d00f2f34ae43314f85cb31de8305f9a72de2bef907c5239b9004e18"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:VUIDRNWQB2KUVLBMT745GOG7XD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Minimizing Energy Consumption of Deep Learning Models by Energy-Aware Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Ambra Demontis, Antonio Emanuele Cin\\`a, Battista Biggio, Dario Lazzaro, Fabio Roli, Marcello Pelillo, Maura Pintor","submitted_at":"2023-07-01T15:44:01Z","abstract_excerpt":"Deep learning models undergo a significant increase in the number of parameters they possess, leading to the execution of a larger number of operations during inference. This expansion significantly contributes to higher energy consumption and prediction latency. In this work, we propose EAT, a gradient-based algorithm that aims to reduce energy consumption during model training. To this end, we leverage a differentiable approximation of the $\\ell_0$ norm, and use it as a sparse penalty over the training loss. Through our experimental analysis conducted on three datasets and two deep neural ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.00368","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2307.00368/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":"2026-07-05T06:26:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GzNwvP+CsL/2Od62niyBMPHLjYZWUl/Pwr6CGaQybWDnjb3thkdXOG00tzqPUYk+AHf15Q8FCYdLBxs44OVQDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T07:57:46.962448Z"},"content_sha256":"fb4fbac8ad09ac664b7a6bf3da729bc529d7c40e9210e8fe838548f0b885b537","schema_version":"1.0","event_id":"sha256:fb4fbac8ad09ac664b7a6bf3da729bc529d7c40e9210e8fe838548f0b885b537"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VUIDRNWQB2KUVLBMT745GOG7XD/bundle.json","state_url":"https://pith.science/pith/VUIDRNWQB2KUVLBMT745GOG7XD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VUIDRNWQB2KUVLBMT745GOG7XD/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":"2026-08-04T07:57:46Z","links":{"resolver":"https://pith.science/pith/VUIDRNWQB2KUVLBMT745GOG7XD","bundle":"https://pith.science/pith/VUIDRNWQB2KUVLBMT745GOG7XD/bundle.json","state":"https://pith.science/pith/VUIDRNWQB2KUVLBMT745GOG7XD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VUIDRNWQB2KUVLBMT745GOG7XD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VUIDRNWQB2KUVLBMT745GOG7XD","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":"d2c9cefaa1b7e2450d85e766dd674324facd4816c50a38be70ad8b256ed63106","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-01T15:44:01Z","title_canon_sha256":"4563a97997c0e4a70fdbdb866bb53a57acc62ff068c8ca0f1b76d6824e744940"},"schema_version":"1.0","source":{"id":"2307.00368","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.00368","created_at":"2026-07-05T06:26:55Z"},{"alias_kind":"arxiv_version","alias_value":"2307.00368v1","created_at":"2026-07-05T06:26:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.00368","created_at":"2026-07-05T06:26:55Z"},{"alias_kind":"pith_short_12","alias_value":"VUIDRNWQB2KU","created_at":"2026-07-05T06:26:55Z"},{"alias_kind":"pith_short_16","alias_value":"VUIDRNWQB2KUVLBM","created_at":"2026-07-05T06:26:55Z"},{"alias_kind":"pith_short_8","alias_value":"VUIDRNWQ","created_at":"2026-07-05T06:26:55Z"}],"graph_snapshots":[{"event_id":"sha256:fb4fbac8ad09ac664b7a6bf3da729bc529d7c40e9210e8fe838548f0b885b537","target":"graph","created_at":"2026-07-05T06:26:55Z","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/2307.00368/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep learning models undergo a significant increase in the number of parameters they possess, leading to the execution of a larger number of operations during inference. This expansion significantly contributes to higher energy consumption and prediction latency. In this work, we propose EAT, a gradient-based algorithm that aims to reduce energy consumption during model training. To this end, we leverage a differentiable approximation of the $\\ell_0$ norm, and use it as a sparse penalty over the training loss. Through our experimental analysis conducted on three datasets and two deep neural ne","authors_text":"Ambra Demontis, Antonio Emanuele Cin\\`a, Battista Biggio, Dario Lazzaro, Fabio Roli, Marcello Pelillo, Maura Pintor","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-01T15:44:01Z","title":"Minimizing Energy Consumption of Deep Learning Models by Energy-Aware Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.00368","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:e7debac96d00f2f34ae43314f85cb31de8305f9a72de2bef907c5239b9004e18","target":"record","created_at":"2026-07-05T06:26:55Z","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":"d2c9cefaa1b7e2450d85e766dd674324facd4816c50a38be70ad8b256ed63106","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-01T15:44:01Z","title_canon_sha256":"4563a97997c0e4a70fdbdb866bb53a57acc62ff068c8ca0f1b76d6824e744940"},"schema_version":"1.0","source":{"id":"2307.00368","kind":"arxiv","version":1}},"canonical_sha256":"ad1038b6d00e954aac2c9ff9d338dfb8e9d0044ee57f1e1375c349a98458504b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad1038b6d00e954aac2c9ff9d338dfb8e9d0044ee57f1e1375c349a98458504b","first_computed_at":"2026-07-05T06:26:55.342745Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:26:55.342745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7e3EkNTR1yebBqMe1HONcZz78Rfirzka0mThcRp/s5OoCbDzUxXwPPISTPJ5/E+7bxJuC3/Q9c+opdOjvedcAA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:26:55.343087Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.00368","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e7debac96d00f2f34ae43314f85cb31de8305f9a72de2bef907c5239b9004e18","sha256:fb4fbac8ad09ac664b7a6bf3da729bc529d7c40e9210e8fe838548f0b885b537"],"state_sha256":"e4c9ec6a56aaecc818c40e092b473967a22bb48e03e66c435529d3e081b81268"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9O3tF+cxyKm48eZGuGsyedAyYIS+C17SzmBRI/RfUU9nNTKrpZpsnRZJt5HMKM73z1rK9lwJyviLVG4ZgDy3BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T07:57:46.971137Z","bundle_sha256":"78f53b33a5bf2ea74e6cddaee44277d2ef5b59ed87e33ba1f06f1f06966f0a19"}}