{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:RHW45HHPZRTVEEPZQAD5WXD6DH","short_pith_number":"pith:RHW45HHP","schema_version":"1.0","canonical_sha256":"89edce9cefcc675211f98007db5c7e19d09e6936d69f4c1d43f499a90837c50c","source":{"kind":"arxiv","id":"1609.04557","version":2},"attestation_state":"computed","paper":{"title":"Structured Dropout for Weak Label and Multi-Instance Learning and Its Application to Score-Informed Source Separation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"cs.LG","authors_text":"Mark B. Sandler, Sebastian Ewert","submitted_at":"2016-09-15T09:50:55Z","abstract_excerpt":"Many success stories involving deep neural networks are instances of supervised learning, where available labels power gradient-based learning methods. Creating such labels, however, can be expensive and thus there is increasing interest in weak labels which only provide coarse information, with uncertainty regarding time, location or value. Using such labels often leads to considerable challenges for the learning process. Current methods for weak-label training often employ standard supervised approaches that additionally reassign or prune labels during the learning process. The information g"},"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":"1609.04557","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-09-15T09:50:55Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"88d4af3e98d403d2b374e2aff44e99ed12dda8cc9693795679a1828e9fca2730","abstract_canon_sha256":"ed0a6502feaba4b7cc0f53b70c96804f9d2a99acfaddab9901c844e83ab8baa4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:45.382814Z","signature_b64":"AgQSYEMEts2AWuS3m4PcyLZ7cddfqVdXn4ldjUb6h1YZTPGxe0wTzbv5q7eAbDEsXpJWzdAUgFk2/HUY20EgBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89edce9cefcc675211f98007db5c7e19d09e6936d69f4c1d43f499a90837c50c","last_reissued_at":"2026-05-18T00:31:45.382035Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:45.382035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structured Dropout for Weak Label and Multi-Instance Learning and Its Application to Score-Informed Source Separation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"cs.LG","authors_text":"Mark B. Sandler, Sebastian Ewert","submitted_at":"2016-09-15T09:50:55Z","abstract_excerpt":"Many success stories involving deep neural networks are instances of supervised learning, where available labels power gradient-based learning methods. Creating such labels, however, can be expensive and thus there is increasing interest in weak labels which only provide coarse information, with uncertainty regarding time, location or value. Using such labels often leads to considerable challenges for the learning process. Current methods for weak-label training often employ standard supervised approaches that additionally reassign or prune labels during the learning process. The information g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.04557","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":""},"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":"1609.04557","created_at":"2026-05-18T00:31:45.382164+00:00"},{"alias_kind":"arxiv_version","alias_value":"1609.04557v2","created_at":"2026-05-18T00:31:45.382164+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.04557","created_at":"2026-05-18T00:31:45.382164+00:00"},{"alias_kind":"pith_short_12","alias_value":"RHW45HHPZRTV","created_at":"2026-05-18T12:30:41.710351+00:00"},{"alias_kind":"pith_short_16","alias_value":"RHW45HHPZRTVEEPZ","created_at":"2026-05-18T12:30:41.710351+00:00"},{"alias_kind":"pith_short_8","alias_value":"RHW45HHP","created_at":"2026-05-18T12:30:41.710351+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/RHW45HHPZRTVEEPZQAD5WXD6DH","json":"https://pith.science/pith/RHW45HHPZRTVEEPZQAD5WXD6DH.json","graph_json":"https://pith.science/api/pith-number/RHW45HHPZRTVEEPZQAD5WXD6DH/graph.json","events_json":"https://pith.science/api/pith-number/RHW45HHPZRTVEEPZQAD5WXD6DH/events.json","paper":"https://pith.science/paper/RHW45HHP"},"agent_actions":{"view_html":"https://pith.science/pith/RHW45HHPZRTVEEPZQAD5WXD6DH","download_json":"https://pith.science/pith/RHW45HHPZRTVEEPZQAD5WXD6DH.json","view_paper":"https://pith.science/paper/RHW45HHP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1609.04557&json=true","fetch_graph":"https://pith.science/api/pith-number/RHW45HHPZRTVEEPZQAD5WXD6DH/graph.json","fetch_events":"https://pith.science/api/pith-number/RHW45HHPZRTVEEPZQAD5WXD6DH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RHW45HHPZRTVEEPZQAD5WXD6DH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RHW45HHPZRTVEEPZQAD5WXD6DH/action/storage_attestation","attest_author":"https://pith.science/pith/RHW45HHPZRTVEEPZQAD5WXD6DH/action/author_attestation","sign_citation":"https://pith.science/pith/RHW45HHPZRTVEEPZQAD5WXD6DH/action/citation_signature","submit_replication":"https://pith.science/pith/RHW45HHPZRTVEEPZQAD5WXD6DH/action/replication_record"}},"created_at":"2026-05-18T00:31:45.382164+00:00","updated_at":"2026-05-18T00:31:45.382164+00:00"}