{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:KCHC3AKSFPJDRBJPVTXLMMUKHZ","short_pith_number":"pith:KCHC3AKS","canonical_record":{"source":{"id":"1905.06435","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-15T21:10:28Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"8936ff48ae0361945c72f55002939110b2f3ab94d27b2d5faed954281712b880","abstract_canon_sha256":"bfefa93e8dfa65824c65444735a4545235c7481860d970d70d7a1eed0fb1b97b"},"schema_version":"1.0"},"canonical_sha256":"508e2d81522bd238852faceeb6328a3e5d8b3c6208ba38814cba27bdad06e9f3","source":{"kind":"arxiv","id":"1905.06435","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.06435","created_at":"2026-05-17T23:46:02Z"},{"alias_kind":"arxiv_version","alias_value":"1905.06435v1","created_at":"2026-05-17T23:46:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.06435","created_at":"2026-05-17T23:46:02Z"},{"alias_kind":"pith_short_12","alias_value":"KCHC3AKSFPJD","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"KCHC3AKSFPJDRBJP","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"KCHC3AKS","created_at":"2026-05-18T12:33:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:KCHC3AKSFPJDRBJPVTXLMMUKHZ","target":"record","payload":{"canonical_record":{"source":{"id":"1905.06435","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-15T21:10:28Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"8936ff48ae0361945c72f55002939110b2f3ab94d27b2d5faed954281712b880","abstract_canon_sha256":"bfefa93e8dfa65824c65444735a4545235c7481860d970d70d7a1eed0fb1b97b"},"schema_version":"1.0"},"canonical_sha256":"508e2d81522bd238852faceeb6328a3e5d8b3c6208ba38814cba27bdad06e9f3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:02.446800Z","signature_b64":"4oS5ePMzGx32rESligXEwDxiwkavYyuuvpAYz2TJo7U1DJsCtJmIemFUs/me458PiCj71UIV1xMvb1fVtGwYCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"508e2d81522bd238852faceeb6328a3e5d8b3c6208ba38814cba27bdad06e9f3","last_reissued_at":"2026-05-17T23:46:02.446238Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:02.446238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.06435","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":"2026-05-17T23:46:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AlQTUm+RGg8TPcfYo3YO3AQYY42/5vMjbP47WPJOLk2Bmz3bgYtU+E25ACeuPqjK8pnDYiLoVz49r82sVodwCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T12:57:40.042546Z"},"content_sha256":"7be4e78bb9e1331527956638dcf22f3d79f513081a128a9abb46ba2d4f3f9d16","schema_version":"1.0","event_id":"sha256:7be4e78bb9e1331527956638dcf22f3d79f513081a128a9abb46ba2d4f3f9d16"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:KCHC3AKSFPJDRBJPVTXLMMUKHZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dynamic Neural Network Channel Execution for Efficient Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Pietro Lio, Simeon E. Spasov","submitted_at":"2019-05-15T21:10:28Z","abstract_excerpt":"Existing methods for reducing the computational burden of neural networks at run-time, such as parameter pruning or dynamic computational path selection, focus solely on improving computational efficiency during inference. On the other hand, in this work, we propose a novel method which reduces the memory footprint and number of computing operations required for training and inference. Our framework efficiently integrates pruning as part of the training procedure by exploring and tracking the relative importance of convolutional channels. At each training step, we select only a subset of highl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.06435","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":"2026-05-17T23:46:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z5b5JxmgZPwxTbPUzKSVzzBnmCYAm4NJfutDIMceN4kryzltCPfpVJKtcF+8M/repm+R+yZ7W+dmXPLg+3mqBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T12:57:40.043249Z"},"content_sha256":"5ed9366159e0476a53fc22db86fe63c72c643d859b841361dee9f3ebcdeba12e","schema_version":"1.0","event_id":"sha256:5ed9366159e0476a53fc22db86fe63c72c643d859b841361dee9f3ebcdeba12e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KCHC3AKSFPJDRBJPVTXLMMUKHZ/bundle.json","state_url":"https://pith.science/pith/KCHC3AKSFPJDRBJPVTXLMMUKHZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KCHC3AKSFPJDRBJPVTXLMMUKHZ/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":"2026-05-31T12:57:40Z","links":{"resolver":"https://pith.science/pith/KCHC3AKSFPJDRBJPVTXLMMUKHZ","bundle":"https://pith.science/pith/KCHC3AKSFPJDRBJPVTXLMMUKHZ/bundle.json","state":"https://pith.science/pith/KCHC3AKSFPJDRBJPVTXLMMUKHZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KCHC3AKSFPJDRBJPVTXLMMUKHZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:KCHC3AKSFPJDRBJPVTXLMMUKHZ","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":"bfefa93e8dfa65824c65444735a4545235c7481860d970d70d7a1eed0fb1b97b","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-15T21:10:28Z","title_canon_sha256":"8936ff48ae0361945c72f55002939110b2f3ab94d27b2d5faed954281712b880"},"schema_version":"1.0","source":{"id":"1905.06435","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.06435","created_at":"2026-05-17T23:46:02Z"},{"alias_kind":"arxiv_version","alias_value":"1905.06435v1","created_at":"2026-05-17T23:46:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.06435","created_at":"2026-05-17T23:46:02Z"},{"alias_kind":"pith_short_12","alias_value":"KCHC3AKSFPJD","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"KCHC3AKSFPJDRBJP","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"KCHC3AKS","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:5ed9366159e0476a53fc22db86fe63c72c643d859b841361dee9f3ebcdeba12e","target":"graph","created_at":"2026-05-17T23:46:02Z","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":"Existing methods for reducing the computational burden of neural networks at run-time, such as parameter pruning or dynamic computational path selection, focus solely on improving computational efficiency during inference. On the other hand, in this work, we propose a novel method which reduces the memory footprint and number of computing operations required for training and inference. Our framework efficiently integrates pruning as part of the training procedure by exploring and tracking the relative importance of convolutional channels. At each training step, we select only a subset of highl","authors_text":"Pietro Lio, Simeon E. Spasov","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-15T21:10:28Z","title":"Dynamic Neural Network Channel Execution for Efficient Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.06435","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":"sha256:7be4e78bb9e1331527956638dcf22f3d79f513081a128a9abb46ba2d4f3f9d16","target":"record","created_at":"2026-05-17T23:46:02Z","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":"bfefa93e8dfa65824c65444735a4545235c7481860d970d70d7a1eed0fb1b97b","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-15T21:10:28Z","title_canon_sha256":"8936ff48ae0361945c72f55002939110b2f3ab94d27b2d5faed954281712b880"},"schema_version":"1.0","source":{"id":"1905.06435","kind":"arxiv","version":1}},"canonical_sha256":"508e2d81522bd238852faceeb6328a3e5d8b3c6208ba38814cba27bdad06e9f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"508e2d81522bd238852faceeb6328a3e5d8b3c6208ba38814cba27bdad06e9f3","first_computed_at":"2026-05-17T23:46:02.446238Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:02.446238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4oS5ePMzGx32rESligXEwDxiwkavYyuuvpAYz2TJo7U1DJsCtJmIemFUs/me458PiCj71UIV1xMvb1fVtGwYCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:02.446800Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.06435","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7be4e78bb9e1331527956638dcf22f3d79f513081a128a9abb46ba2d4f3f9d16","sha256:5ed9366159e0476a53fc22db86fe63c72c643d859b841361dee9f3ebcdeba12e"],"state_sha256":"f370c6d6328c0f8b4fafa2292339af73eb22a00e78476bd758b605dedfab1af4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"at0OCmUqxNzkv22ryAxgNNHd+i2KnFrOf8exN6jsP/4IU9ETzVm/3a8KeYp2J42rtktrN0lNgyiv+WFZ9faqCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T12:57:40.047071Z","bundle_sha256":"0d5cda53e3ccdd2b660b0b5fa5063980889de5372e7fbd9ce027a045c8957123"}}