{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:2S7MURTGC2VSRJXISGJWKOAOHD","short_pith_number":"pith:2S7MURTG","canonical_record":{"source":{"id":"1810.11764","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-28T06:15:51Z","cross_cats_sorted":["cond-mat.dis-nn","stat.ML"],"title_canon_sha256":"f224aae0e18d6bd457d4ff7a25c685239de29b601d4070266c5f964d1b6854ee","abstract_canon_sha256":"08440a059d53118dcaf5cf2b0e373c15d32c89320567aafea7296dd2c28167b1"},"schema_version":"1.0"},"canonical_sha256":"d4beca466616ab28a6e8919365380e38d3026fdca08d73760edbb0eb34100d0e","source":{"kind":"arxiv","id":"1810.11764","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.11764","created_at":"2026-05-18T00:02:07Z"},{"alias_kind":"arxiv_version","alias_value":"1810.11764v1","created_at":"2026-05-18T00:02:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.11764","created_at":"2026-05-18T00:02:07Z"},{"alias_kind":"pith_short_12","alias_value":"2S7MURTGC2VS","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"2S7MURTGC2VSRJXI","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"2S7MURTG","created_at":"2026-05-18T12:32:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:2S7MURTGC2VSRJXISGJWKOAOHD","target":"record","payload":{"canonical_record":{"source":{"id":"1810.11764","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-28T06:15:51Z","cross_cats_sorted":["cond-mat.dis-nn","stat.ML"],"title_canon_sha256":"f224aae0e18d6bd457d4ff7a25c685239de29b601d4070266c5f964d1b6854ee","abstract_canon_sha256":"08440a059d53118dcaf5cf2b0e373c15d32c89320567aafea7296dd2c28167b1"},"schema_version":"1.0"},"canonical_sha256":"d4beca466616ab28a6e8919365380e38d3026fdca08d73760edbb0eb34100d0e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:07.482560Z","signature_b64":"uoTlcxkNHwj3u4gcCuavWBGG9lubTuCXBAHosTtoR5plG72wGr/avMDCOFwFnk+3GHwhsNaSrx2D0071H65YDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4beca466616ab28a6e8919365380e38d3026fdca08d73760edbb0eb34100d0e","last_reissued_at":"2026-05-18T00:02:07.481883Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:07.481883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.11764","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":"2026-05-18T00:02:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V4Z2I1TtM7ZGXYlp1EnMEhky8S/yox+s/OexSfFEnlhUvVyoklukyHSRas+g/RLRjcphA3dX4LgEGxUx5tQqCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T01:23:31.172683Z"},"content_sha256":"8a85ee7cc3d7bac8935ce48bbcb9551b9f9d7c463671d9c99c84a6f71184be1a","schema_version":"1.0","event_id":"sha256:8a85ee7cc3d7bac8935ce48bbcb9551b9f9d7c463671d9c99c84a6f71184be1a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:2S7MURTGC2VSRJXISGJWKOAOHD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Sparse Neural Networks via Sensitivity-Driven Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn","stat.ML"],"primary_cat":"cs.LG","authors_text":"Attilio Fiandrotti, Enzo Tartaglione, Gianluca Francini, Skjalg Leps{\\o}y","submitted_at":"2018-10-28T06:15:51Z","abstract_excerpt":"The ever-increasing number of parameters in deep neural networks poses challenges for memory-limited applications. Regularize-and-prune methods aim at meeting these challenges by sparsifying the network weights. In this context we quantify the output sensitivity to the parameters (i.e. their relevance to the network output) and introduce a regularization term that gradually lowers the absolute value of parameters with low sensitivity. Thus, a very large fraction of the parameters approach zero and are eventually set to zero by simple thresholding. Our method surpasses most of the recent techni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.11764","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":"2026-05-18T00:02:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kdsw/IJzxXHsZOKcTT52wz40tau9ATVZVm5NJcsqDgDoT3yFqqlcqWV+upWwU9UbxiamXo/cBYbHLMxQx82ACQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T01:23:31.173397Z"},"content_sha256":"13252b8386752dd761fbc9fe82b39df22cd0fbf9361a54741c51a639522f6ea8","schema_version":"1.0","event_id":"sha256:13252b8386752dd761fbc9fe82b39df22cd0fbf9361a54741c51a639522f6ea8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2S7MURTGC2VSRJXISGJWKOAOHD/bundle.json","state_url":"https://pith.science/pith/2S7MURTGC2VSRJXISGJWKOAOHD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2S7MURTGC2VSRJXISGJWKOAOHD/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":"2026-06-05T01:23:31Z","links":{"resolver":"https://pith.science/pith/2S7MURTGC2VSRJXISGJWKOAOHD","bundle":"https://pith.science/pith/2S7MURTGC2VSRJXISGJWKOAOHD/bundle.json","state":"https://pith.science/pith/2S7MURTGC2VSRJXISGJWKOAOHD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2S7MURTGC2VSRJXISGJWKOAOHD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:2S7MURTGC2VSRJXISGJWKOAOHD","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":"08440a059d53118dcaf5cf2b0e373c15d32c89320567aafea7296dd2c28167b1","cross_cats_sorted":["cond-mat.dis-nn","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-28T06:15:51Z","title_canon_sha256":"f224aae0e18d6bd457d4ff7a25c685239de29b601d4070266c5f964d1b6854ee"},"schema_version":"1.0","source":{"id":"1810.11764","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.11764","created_at":"2026-05-18T00:02:07Z"},{"alias_kind":"arxiv_version","alias_value":"1810.11764v1","created_at":"2026-05-18T00:02:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.11764","created_at":"2026-05-18T00:02:07Z"},{"alias_kind":"pith_short_12","alias_value":"2S7MURTGC2VS","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"2S7MURTGC2VSRJXI","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"2S7MURTG","created_at":"2026-05-18T12:32:02Z"}],"graph_snapshots":[{"event_id":"sha256:13252b8386752dd761fbc9fe82b39df22cd0fbf9361a54741c51a639522f6ea8","target":"graph","created_at":"2026-05-18T00:02:07Z","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":"The ever-increasing number of parameters in deep neural networks poses challenges for memory-limited applications. Regularize-and-prune methods aim at meeting these challenges by sparsifying the network weights. In this context we quantify the output sensitivity to the parameters (i.e. their relevance to the network output) and introduce a regularization term that gradually lowers the absolute value of parameters with low sensitivity. Thus, a very large fraction of the parameters approach zero and are eventually set to zero by simple thresholding. Our method surpasses most of the recent techni","authors_text":"Attilio Fiandrotti, Enzo Tartaglione, Gianluca Francini, Skjalg Leps{\\o}y","cross_cats":["cond-mat.dis-nn","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-28T06:15:51Z","title":"Learning Sparse Neural Networks via Sensitivity-Driven Regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.11764","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":"sha256:8a85ee7cc3d7bac8935ce48bbcb9551b9f9d7c463671d9c99c84a6f71184be1a","target":"record","created_at":"2026-05-18T00:02:07Z","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":"08440a059d53118dcaf5cf2b0e373c15d32c89320567aafea7296dd2c28167b1","cross_cats_sorted":["cond-mat.dis-nn","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-28T06:15:51Z","title_canon_sha256":"f224aae0e18d6bd457d4ff7a25c685239de29b601d4070266c5f964d1b6854ee"},"schema_version":"1.0","source":{"id":"1810.11764","kind":"arxiv","version":1}},"canonical_sha256":"d4beca466616ab28a6e8919365380e38d3026fdca08d73760edbb0eb34100d0e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d4beca466616ab28a6e8919365380e38d3026fdca08d73760edbb0eb34100d0e","first_computed_at":"2026-05-18T00:02:07.481883Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:02:07.481883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uoTlcxkNHwj3u4gcCuavWBGG9lubTuCXBAHosTtoR5plG72wGr/avMDCOFwFnk+3GHwhsNaSrx2D0071H65YDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:02:07.482560Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.11764","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a85ee7cc3d7bac8935ce48bbcb9551b9f9d7c463671d9c99c84a6f71184be1a","sha256:13252b8386752dd761fbc9fe82b39df22cd0fbf9361a54741c51a639522f6ea8"],"state_sha256":"0ca0e34b1f0c09e1c6e7944a1caa420cef0d9b1792f0fb8a5e5ae21816815fe0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a8b0XeMQliGJ89sOE/TXxySkWtK27M7m/80SgFOdXx98jJpv5fdv+zn+XNTfO72HZUPpHVFi3f+GwUvHKBFIAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T01:23:31.176722Z","bundle_sha256":"10a70fa2622dd5db4de9c60a443a95a32db6d427a2ba608931f0bfe89b83b7f1"}}