{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:NTG2YGP3ABSD4ZAQB6ZDHXZTOS","short_pith_number":"pith:NTG2YGP3","schema_version":"1.0","canonical_sha256":"6ccdac19fb00643e64100fb233df3374aa46144a5f117523b52dd11c0f5f21aa","source":{"kind":"arxiv","id":"1907.06627","version":4},"attestation_state":"computed","paper":{"title":"Batch-Shaping for Learning Conditional Channel Gated Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Babak Ehteshami Bejnordi, Max Welling, Tijmen Blankevoort","submitted_at":"2019-07-15T17:58:04Z","abstract_excerpt":"We present a method that trains large capacity neural networks with significantly improved accuracy and lower dynamic computational cost. We achieve this by gating the deep-learning architecture on a fine-grained-level. Individual convolutional maps are turned on/off conditionally on features in the network. To achieve this, we introduce a new residual block architecture that gates convolutional channels in a fine-grained manner. We also introduce a generally applicable tool $batch$-$shaping$ that matches the marginal aggregate posteriors of features in a neural network to a pre-specified prio"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1907.06627","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-15T17:58:04Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"0e609b318f7488a7c1bf3ee1b8420e98b465ad595fbf11053e825d7e35222327","abstract_canon_sha256":"1c574d4214d8936f8f1d52fb8d75f48c5e1bb034beae7fb38cbca4592cdadbad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:52:26.918024Z","signature_b64":"HFwR6Ix6zOO8+vj5UQMr6+TWhcvvhX7R9Bm4SbXN7aUyjk5u1lfDIYDpiulHvPMV3XNibeWtvzkvaRZBt55oDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ccdac19fb00643e64100fb233df3374aa46144a5f117523b52dd11c0f5f21aa","last_reissued_at":"2026-07-05T00:52:26.917612Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:52:26.917612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Batch-Shaping for Learning Conditional Channel Gated Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Babak Ehteshami Bejnordi, Max Welling, Tijmen Blankevoort","submitted_at":"2019-07-15T17:58:04Z","abstract_excerpt":"We present a method that trains large capacity neural networks with significantly improved accuracy and lower dynamic computational cost. We achieve this by gating the deep-learning architecture on a fine-grained-level. Individual convolutional maps are turned on/off conditionally on features in the network. To achieve this, we introduce a new residual block architecture that gates convolutional channels in a fine-grained manner. We also introduce a generally applicable tool $batch$-$shaping$ that matches the marginal aggregate posteriors of features in a neural network to a pre-specified prio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.06627","kind":"arxiv","version":4},"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/1907.06627/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1907.06627","created_at":"2026-07-05T00:52:26.917667+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.06627v4","created_at":"2026-07-05T00:52:26.917667+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.06627","created_at":"2026-07-05T00:52:26.917667+00:00"},{"alias_kind":"pith_short_12","alias_value":"NTG2YGP3ABSD","created_at":"2026-07-05T00:52:26.917667+00:00"},{"alias_kind":"pith_short_16","alias_value":"NTG2YGP3ABSD4ZAQ","created_at":"2026-07-05T00:52:26.917667+00:00"},{"alias_kind":"pith_short_8","alias_value":"NTG2YGP3","created_at":"2026-07-05T00:52:26.917667+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NTG2YGP3ABSD4ZAQB6ZDHXZTOS","json":"https://pith.science/pith/NTG2YGP3ABSD4ZAQB6ZDHXZTOS.json","graph_json":"https://pith.science/api/pith-number/NTG2YGP3ABSD4ZAQB6ZDHXZTOS/graph.json","events_json":"https://pith.science/api/pith-number/NTG2YGP3ABSD4ZAQB6ZDHXZTOS/events.json","paper":"https://pith.science/paper/NTG2YGP3"},"agent_actions":{"view_html":"https://pith.science/pith/NTG2YGP3ABSD4ZAQB6ZDHXZTOS","download_json":"https://pith.science/pith/NTG2YGP3ABSD4ZAQB6ZDHXZTOS.json","view_paper":"https://pith.science/paper/NTG2YGP3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.06627&json=true","fetch_graph":"https://pith.science/api/pith-number/NTG2YGP3ABSD4ZAQB6ZDHXZTOS/graph.json","fetch_events":"https://pith.science/api/pith-number/NTG2YGP3ABSD4ZAQB6ZDHXZTOS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NTG2YGP3ABSD4ZAQB6ZDHXZTOS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NTG2YGP3ABSD4ZAQB6ZDHXZTOS/action/storage_attestation","attest_author":"https://pith.science/pith/NTG2YGP3ABSD4ZAQB6ZDHXZTOS/action/author_attestation","sign_citation":"https://pith.science/pith/NTG2YGP3ABSD4ZAQB6ZDHXZTOS/action/citation_signature","submit_replication":"https://pith.science/pith/NTG2YGP3ABSD4ZAQB6ZDHXZTOS/action/replication_record"}},"created_at":"2026-07-05T00:52:26.917667+00:00","updated_at":"2026-07-05T00:52:26.917667+00:00"}