{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:4QYVGIQ36353ZO24TGO5VTQNVC","short_pith_number":"pith:4QYVGIQ3","canonical_record":{"source":{"id":"2103.03014","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-04T13:22:16Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"415c59af0d636f106c316bd9652ed833dd23b9b7dfdad0175c2a75eda6a8f666","abstract_canon_sha256":"5346763652a3d9fdfcfb80114dc70047051b224b75e9eb92f589ee47cf682778"},"schema_version":"1.0"},"canonical_sha256":"e43153221bf6fbbcbb5c999ddace0da8804cdf82a53bd9c0f092625137617b3e","source":{"kind":"arxiv","id":"2103.03014","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.03014","created_at":"2026-07-05T02:20:23Z"},{"alias_kind":"arxiv_version","alias_value":"2103.03014v1","created_at":"2026-07-05T02:20:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.03014","created_at":"2026-07-05T02:20:23Z"},{"alias_kind":"pith_short_12","alias_value":"4QYVGIQ36353","created_at":"2026-07-05T02:20:23Z"},{"alias_kind":"pith_short_16","alias_value":"4QYVGIQ36353ZO24","created_at":"2026-07-05T02:20:23Z"},{"alias_kind":"pith_short_8","alias_value":"4QYVGIQ3","created_at":"2026-07-05T02:20:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:4QYVGIQ36353ZO24TGO5VTQNVC","target":"record","payload":{"canonical_record":{"source":{"id":"2103.03014","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-04T13:22:16Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"415c59af0d636f106c316bd9652ed833dd23b9b7dfdad0175c2a75eda6a8f666","abstract_canon_sha256":"5346763652a3d9fdfcfb80114dc70047051b224b75e9eb92f589ee47cf682778"},"schema_version":"1.0"},"canonical_sha256":"e43153221bf6fbbcbb5c999ddace0da8804cdf82a53bd9c0f092625137617b3e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:20:23.361921Z","signature_b64":"oCI946Z6LngK/9isVCxNTaYq8VTNoB8ypnf+soEXLwy3QzhGZWrav+JduNIP0VjajSDPZ+uYSDO12qktcQpMDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e43153221bf6fbbcbb5c999ddace0da8804cdf82a53bd9c0f092625137617b3e","last_reissued_at":"2026-07-05T02:20:23.361449Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:20:23.361449Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.03014","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":"2026-07-05T02:20:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MSbMDMzSeBUXPtXATKR2HysqFQ1IEtRLj3zUoP62v5jkExsZN5P4U5I0/8yj0mBtBLshROob5QMxLpf48D9XDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:59:11.447815Z"},"content_sha256":"c27a47c11b3eac12fcd0c0b4bbeae090d412a02c696ec0bfd1d89b22d7fe6021","schema_version":"1.0","event_id":"sha256:c27a47c11b3eac12fcd0c0b4bbeae090d412a02c696ec0bfd1d89b22d7fe6021"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:4QYVGIQ36353ZO24TGO5VTQNVC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Lost in Pruning: The Effects of Pruning Neural Networks beyond Test Accuracy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Brandon Carter, Cenk Baykal, Daniela Rus, David Gifford, Lucas Liebenwein","submitted_at":"2021-03-04T13:22:16Z","abstract_excerpt":"Neural network pruning is a popular technique used to reduce the inference costs of modern, potentially overparameterized, networks. Starting from a pre-trained network, the process is as follows: remove redundant parameters, retrain, and repeat while maintaining the same test accuracy. The result is a model that is a fraction of the size of the original with comparable predictive performance (test accuracy). Here, we reassess and evaluate whether the use of test accuracy alone in the terminating condition is sufficient to ensure that the resulting model performs well across a wide spectrum of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.03014","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/2103.03014/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":"2026-07-05T02:20:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EkEt3Sxx/HMAYqlsxVfS64RqrsIaUvGklEA7m/5uZgeo5WlutO5+1FuSx5cHddCoy/SHiKmX4MdrDMviTyAODw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:59:11.448197Z"},"content_sha256":"22379f08bb1902b46c45fecebe95bb54b082c5250233f29e5802e24602ba7373","schema_version":"1.0","event_id":"sha256:22379f08bb1902b46c45fecebe95bb54b082c5250233f29e5802e24602ba7373"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4QYVGIQ36353ZO24TGO5VTQNVC/bundle.json","state_url":"https://pith.science/pith/4QYVGIQ36353ZO24TGO5VTQNVC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4QYVGIQ36353ZO24TGO5VTQNVC/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":"2026-07-06T20:59:11Z","links":{"resolver":"https://pith.science/pith/4QYVGIQ36353ZO24TGO5VTQNVC","bundle":"https://pith.science/pith/4QYVGIQ36353ZO24TGO5VTQNVC/bundle.json","state":"https://pith.science/pith/4QYVGIQ36353ZO24TGO5VTQNVC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4QYVGIQ36353ZO24TGO5VTQNVC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:4QYVGIQ36353ZO24TGO5VTQNVC","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":"5346763652a3d9fdfcfb80114dc70047051b224b75e9eb92f589ee47cf682778","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-04T13:22:16Z","title_canon_sha256":"415c59af0d636f106c316bd9652ed833dd23b9b7dfdad0175c2a75eda6a8f666"},"schema_version":"1.0","source":{"id":"2103.03014","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.03014","created_at":"2026-07-05T02:20:23Z"},{"alias_kind":"arxiv_version","alias_value":"2103.03014v1","created_at":"2026-07-05T02:20:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.03014","created_at":"2026-07-05T02:20:23Z"},{"alias_kind":"pith_short_12","alias_value":"4QYVGIQ36353","created_at":"2026-07-05T02:20:23Z"},{"alias_kind":"pith_short_16","alias_value":"4QYVGIQ36353ZO24","created_at":"2026-07-05T02:20:23Z"},{"alias_kind":"pith_short_8","alias_value":"4QYVGIQ3","created_at":"2026-07-05T02:20:23Z"}],"graph_snapshots":[{"event_id":"sha256:22379f08bb1902b46c45fecebe95bb54b082c5250233f29e5802e24602ba7373","target":"graph","created_at":"2026-07-05T02:20:23Z","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/2103.03014/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural network pruning is a popular technique used to reduce the inference costs of modern, potentially overparameterized, networks. Starting from a pre-trained network, the process is as follows: remove redundant parameters, retrain, and repeat while maintaining the same test accuracy. The result is a model that is a fraction of the size of the original with comparable predictive performance (test accuracy). Here, we reassess and evaluate whether the use of test accuracy alone in the terminating condition is sufficient to ensure that the resulting model performs well across a wide spectrum of","authors_text":"Brandon Carter, Cenk Baykal, Daniela Rus, David Gifford, Lucas Liebenwein","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-04T13:22:16Z","title":"Lost in Pruning: The Effects of Pruning Neural Networks beyond Test Accuracy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.03014","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:c27a47c11b3eac12fcd0c0b4bbeae090d412a02c696ec0bfd1d89b22d7fe6021","target":"record","created_at":"2026-07-05T02:20:23Z","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":"5346763652a3d9fdfcfb80114dc70047051b224b75e9eb92f589ee47cf682778","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-04T13:22:16Z","title_canon_sha256":"415c59af0d636f106c316bd9652ed833dd23b9b7dfdad0175c2a75eda6a8f666"},"schema_version":"1.0","source":{"id":"2103.03014","kind":"arxiv","version":1}},"canonical_sha256":"e43153221bf6fbbcbb5c999ddace0da8804cdf82a53bd9c0f092625137617b3e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e43153221bf6fbbcbb5c999ddace0da8804cdf82a53bd9c0f092625137617b3e","first_computed_at":"2026-07-05T02:20:23.361449Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:20:23.361449Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oCI946Z6LngK/9isVCxNTaYq8VTNoB8ypnf+soEXLwy3QzhGZWrav+JduNIP0VjajSDPZ+uYSDO12qktcQpMDg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:20:23.361921Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.03014","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c27a47c11b3eac12fcd0c0b4bbeae090d412a02c696ec0bfd1d89b22d7fe6021","sha256:22379f08bb1902b46c45fecebe95bb54b082c5250233f29e5802e24602ba7373"],"state_sha256":"b9241bafe0e84f963e1b79f43dc3b442289c669083cacb30a7db24997ef2e7b4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qf11UU8Q9X85EncjgqHKTPSVJAVtC3Mjf1PJLRqL7RJstzMXLZckcOC9V1oFdABmUVLKcDZueGONY1JqnCNPBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T20:59:11.450198Z","bundle_sha256":"87b3eba0546544a5dd888db253e495db09c4ad2768508f3e110c24074ffdbad8"}}