{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:K5IQ6SSBMQBSLVDMCUA5I5BHSU","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":"2a37cf7a6f59ae9397750abff65877b157a55d1d017d2d49c3602c2fd441512b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-01-31T22:14:09Z","title_canon_sha256":"fcdb43b0e6bf0dffdb6b6b0dbbd96cb6462916ce4a53b05fbdb3a02a81212c92"},"schema_version":"1.0","source":{"id":"1802.00086","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.00086","created_at":"2026-07-05T03:15:49Z"},{"alias_kind":"arxiv_version","alias_value":"1802.00086v1","created_at":"2026-07-05T03:15:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.00086","created_at":"2026-07-05T03:15:49Z"},{"alias_kind":"pith_short_12","alias_value":"K5IQ6SSBMQBS","created_at":"2026-07-05T03:15:49Z"},{"alias_kind":"pith_short_16","alias_value":"K5IQ6SSBMQBSLVDM","created_at":"2026-07-05T03:15:49Z"},{"alias_kind":"pith_short_8","alias_value":"K5IQ6SSB","created_at":"2026-07-05T03:15:49Z"}],"graph_snapshots":[{"event_id":"sha256:cef481923f73ce584bc6dd7bd4e7514686832dbd0c350cc549ccc3607d8c6354","target":"graph","created_at":"2026-07-05T03:15:49Z","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/1802.00086/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a class of algorithms capable of directly training deep neural networks with respect to large families of task-specific performance measures such as the F-measure and the Kullback-Leibler divergence that are structured and non-decomposable. This presents a departure from standard deep learning techniques that typically use squared or cross-entropy loss functions (that are decomposable) to train neural networks. We demonstrate that directly training with task-specific loss functions yields much faster and more stable convergence across problems and datasets. Our proposed algorithms a","authors_text":"Amartya Sanyal, Fabrizio Sebastiani, Pawan Kumar, Purushottam Kar, Sanjay Chawla","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-01-31T22:14:09Z","title":"Optimizing Non-decomposable Measures with Deep Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.00086","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:b42f7218b17812ffcd9cbc9e58655f1e3134fdc15680a3f0a32ea6aa4d12459c","target":"record","created_at":"2026-07-05T03:15:49Z","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":"2a37cf7a6f59ae9397750abff65877b157a55d1d017d2d49c3602c2fd441512b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-01-31T22:14:09Z","title_canon_sha256":"fcdb43b0e6bf0dffdb6b6b0dbbd96cb6462916ce4a53b05fbdb3a02a81212c92"},"schema_version":"1.0","source":{"id":"1802.00086","kind":"arxiv","version":1}},"canonical_sha256":"57510f4a41640325d46c1501d474279517660357d30368b3b3dfa2029686bd9a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"57510f4a41640325d46c1501d474279517660357d30368b3b3dfa2029686bd9a","first_computed_at":"2026-07-05T03:15:49.499785Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:15:49.499785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FijGx3ka2TFZ5VCJ9w+WjGDacsc+ssOkgzIJC2ui1wfF5hvQVhBOjrDxGMfxVzleJAaBvGPYpl4hXNlxriiACA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:15:49.500244Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.00086","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b42f7218b17812ffcd9cbc9e58655f1e3134fdc15680a3f0a32ea6aa4d12459c","sha256:cef481923f73ce584bc6dd7bd4e7514686832dbd0c350cc549ccc3607d8c6354"],"state_sha256":"8e24230e4a5e1fba9bfb6a36b8c98fb2480a0c8ce5aca3e8084cac826abb6fc3"}