{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:3U35EHNXT3HICC26DLWYVC5V3Z","short_pith_number":"pith:3U35EHNX","canonical_record":{"source":{"id":"1906.06307","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-14T17:26:29Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"2c29ff0d1a34afb1b9bc73013bfeab9aa2c1f3b2c31c6feca9e54594e30976b4","abstract_canon_sha256":"4f65009a494ab206434b6d61508d5e1bf8f778d0e76972ef6784a0c1c1b79579"},"schema_version":"1.0"},"canonical_sha256":"dd37d21db79ece810b5e1aed8a8bb5de67d4d93f5db316fba2185dec19289b2e","source":{"kind":"arxiv","id":"1906.06307","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.06307","created_at":"2026-07-05T00:40:56Z"},{"alias_kind":"arxiv_version","alias_value":"1906.06307v2","created_at":"2026-07-05T00:40:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.06307","created_at":"2026-07-05T00:40:56Z"},{"alias_kind":"pith_short_12","alias_value":"3U35EHNXT3HI","created_at":"2026-07-05T00:40:56Z"},{"alias_kind":"pith_short_16","alias_value":"3U35EHNXT3HICC26","created_at":"2026-07-05T00:40:56Z"},{"alias_kind":"pith_short_8","alias_value":"3U35EHNX","created_at":"2026-07-05T00:40:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:3U35EHNXT3HICC26DLWYVC5V3Z","target":"record","payload":{"canonical_record":{"source":{"id":"1906.06307","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-14T17:26:29Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"2c29ff0d1a34afb1b9bc73013bfeab9aa2c1f3b2c31c6feca9e54594e30976b4","abstract_canon_sha256":"4f65009a494ab206434b6d61508d5e1bf8f778d0e76972ef6784a0c1c1b79579"},"schema_version":"1.0"},"canonical_sha256":"dd37d21db79ece810b5e1aed8a8bb5de67d4d93f5db316fba2185dec19289b2e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:40:56.209018Z","signature_b64":"Qefpc0M/KUoCNmZjqT5I8e8UM0NCdBLV2EtDLtkQVou10EKSg86XYz5iTvM4lIBNwdGMgNI8eUb+yjEOR4keCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd37d21db79ece810b5e1aed8a8bb5de67d4d93f5db316fba2185dec19289b2e","last_reissued_at":"2026-07-05T00:40:56.208479Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:40:56.208479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.06307","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:40:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4rQ23Nhwupbgn4V01pPkyMKq0bcL+JMMe1qaN2qn96UGNW7OkmqiznmjxM9Z6BvGN2f0/VAHmYVOkvhcOGFXBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T01:59:13.454349Z"},"content_sha256":"998b4062db08977a8816d1dd45c4c2e163e656ff0408100638aafa5333565144","schema_version":"1.0","event_id":"sha256:998b4062db08977a8816d1dd45c4c2e163e656ff0408100638aafa5333565144"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:3U35EHNXT3HICC26DLWYVC5V3Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Signal Propagation Perspective for Pruning Neural Networks at Initialization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Namhoon Lee, Philip H. S. Torr, Stephen Gould, Thalaiyasingam Ajanthan","submitted_at":"2019-06-14T17:26:29Z","abstract_excerpt":"Network pruning is a promising avenue for compressing deep neural networks. A typical approach to pruning starts by training a model and then removing redundant parameters while minimizing the impact on what is learned. Alternatively, a recent approach shows that pruning can be done at initialization prior to training, based on a saliency criterion called connection sensitivity. However, it remains unclear exactly why pruning an untrained, randomly initialized neural network is effective. In this work, by noting connection sensitivity as a form of gradient, we formally characterize initializat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.06307","kind":"arxiv","version":2},"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/1906.06307/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":"2026-07-05T00:40:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dghlPu+q4c3iTo8P0zQtelvm/xu7kwdeFdYKnOxQXo7BDv9Uwgw3p+0rWNWmLsQid4smBJ64E610wGcfCYJ2DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T01:59:13.454970Z"},"content_sha256":"50a22c3ea91932d9fe531afaec937ee44b4a9bbbe43e1fe051b095db3af564b0","schema_version":"1.0","event_id":"sha256:50a22c3ea91932d9fe531afaec937ee44b4a9bbbe43e1fe051b095db3af564b0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3U35EHNXT3HICC26DLWYVC5V3Z/bundle.json","state_url":"https://pith.science/pith/3U35EHNXT3HICC26DLWYVC5V3Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3U35EHNXT3HICC26DLWYVC5V3Z/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":"2026-07-07T01:59:13Z","links":{"resolver":"https://pith.science/pith/3U35EHNXT3HICC26DLWYVC5V3Z","bundle":"https://pith.science/pith/3U35EHNXT3HICC26DLWYVC5V3Z/bundle.json","state":"https://pith.science/pith/3U35EHNXT3HICC26DLWYVC5V3Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3U35EHNXT3HICC26DLWYVC5V3Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:3U35EHNXT3HICC26DLWYVC5V3Z","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":"4f65009a494ab206434b6d61508d5e1bf8f778d0e76972ef6784a0c1c1b79579","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-14T17:26:29Z","title_canon_sha256":"2c29ff0d1a34afb1b9bc73013bfeab9aa2c1f3b2c31c6feca9e54594e30976b4"},"schema_version":"1.0","source":{"id":"1906.06307","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.06307","created_at":"2026-07-05T00:40:56Z"},{"alias_kind":"arxiv_version","alias_value":"1906.06307v2","created_at":"2026-07-05T00:40:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.06307","created_at":"2026-07-05T00:40:56Z"},{"alias_kind":"pith_short_12","alias_value":"3U35EHNXT3HI","created_at":"2026-07-05T00:40:56Z"},{"alias_kind":"pith_short_16","alias_value":"3U35EHNXT3HICC26","created_at":"2026-07-05T00:40:56Z"},{"alias_kind":"pith_short_8","alias_value":"3U35EHNX","created_at":"2026-07-05T00:40:56Z"}],"graph_snapshots":[{"event_id":"sha256:50a22c3ea91932d9fe531afaec937ee44b4a9bbbe43e1fe051b095db3af564b0","target":"graph","created_at":"2026-07-05T00:40:56Z","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/1906.06307/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Network pruning is a promising avenue for compressing deep neural networks. A typical approach to pruning starts by training a model and then removing redundant parameters while minimizing the impact on what is learned. Alternatively, a recent approach shows that pruning can be done at initialization prior to training, based on a saliency criterion called connection sensitivity. However, it remains unclear exactly why pruning an untrained, randomly initialized neural network is effective. In this work, by noting connection sensitivity as a form of gradient, we formally characterize initializat","authors_text":"Namhoon Lee, Philip H. S. Torr, Stephen Gould, Thalaiyasingam Ajanthan","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-14T17:26:29Z","title":"A Signal Propagation Perspective for Pruning Neural Networks at Initialization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.06307","kind":"arxiv","version":2},"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":"sha256:998b4062db08977a8816d1dd45c4c2e163e656ff0408100638aafa5333565144","target":"record","created_at":"2026-07-05T00:40:56Z","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":"4f65009a494ab206434b6d61508d5e1bf8f778d0e76972ef6784a0c1c1b79579","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-14T17:26:29Z","title_canon_sha256":"2c29ff0d1a34afb1b9bc73013bfeab9aa2c1f3b2c31c6feca9e54594e30976b4"},"schema_version":"1.0","source":{"id":"1906.06307","kind":"arxiv","version":2}},"canonical_sha256":"dd37d21db79ece810b5e1aed8a8bb5de67d4d93f5db316fba2185dec19289b2e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dd37d21db79ece810b5e1aed8a8bb5de67d4d93f5db316fba2185dec19289b2e","first_computed_at":"2026-07-05T00:40:56.208479Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:40:56.208479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Qefpc0M/KUoCNmZjqT5I8e8UM0NCdBLV2EtDLtkQVou10EKSg86XYz5iTvM4lIBNwdGMgNI8eUb+yjEOR4keCg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:40:56.209018Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.06307","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:998b4062db08977a8816d1dd45c4c2e163e656ff0408100638aafa5333565144","sha256:50a22c3ea91932d9fe531afaec937ee44b4a9bbbe43e1fe051b095db3af564b0"],"state_sha256":"94e9ae654fdd4e2b033ae3f5281dc0ad65bfea7a6ef16d3d36457711f9777de9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d0ke3u5P8NAMSgwVTOVxoU3ETloV7iNE9JOw/sVPMj6Ve+EGcVGUpN58mjXwQ15B2CgN6B6ciWkJ6XVzFh1OCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T01:59:13.458547Z","bundle_sha256":"c9dcc92b42fd7aae55a8019aae41dc624b965783da3332da8d79d7346ca7fb38"}}