{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:NHPWD5QZV5YK53QHB3VHFXO7FM","short_pith_number":"pith:NHPWD5QZ","canonical_record":{"source":{"id":"1809.02322","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-07T06:41:17Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9f6b2acd2496c160965ac6b1556b21345b036909137082e3f74ba98cbb4a208d","abstract_canon_sha256":"dc356f7ba2ab1d4b060a7194746f11b39cb8423d1c4f154ea5cb14129fbae33e"},"schema_version":"1.0"},"canonical_sha256":"69df61f619af70aeee070eea72dddf2b085b350814d72e7d3b1edc7d1f2672f2","source":{"kind":"arxiv","id":"1809.02322","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.02322","created_at":"2026-05-17T23:47:36Z"},{"alias_kind":"arxiv_version","alias_value":"1809.02322v2","created_at":"2026-05-17T23:47:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.02322","created_at":"2026-05-17T23:47:36Z"},{"alias_kind":"pith_short_12","alias_value":"NHPWD5QZV5YK","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"NHPWD5QZV5YK53QH","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"NHPWD5QZ","created_at":"2026-05-18T12:32:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:NHPWD5QZV5YK53QHB3VHFXO7FM","target":"record","payload":{"canonical_record":{"source":{"id":"1809.02322","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-07T06:41:17Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9f6b2acd2496c160965ac6b1556b21345b036909137082e3f74ba98cbb4a208d","abstract_canon_sha256":"dc356f7ba2ab1d4b060a7194746f11b39cb8423d1c4f154ea5cb14129fbae33e"},"schema_version":"1.0"},"canonical_sha256":"69df61f619af70aeee070eea72dddf2b085b350814d72e7d3b1edc7d1f2672f2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:36.099058Z","signature_b64":"smzVLZfTmp7Tyvd32wFozed6rhUpYLzADQTsjF06GBkYb+MY7yLP0R9jBbmdRjsN/z3CsG0eo3h0KIGn7RcwBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69df61f619af70aeee070eea72dddf2b085b350814d72e7d3b1edc7d1f2672f2","last_reissued_at":"2026-05-17T23:47:36.098652Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:36.098652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.02322","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":"2026-05-17T23:47:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QgD5sNT3pcIaBvHmdIhOQnSwpCgS3fQdZ383vPaLRM7SaqlJ6clzzwViOLNGPwh0c8JVx4H0e++4AdynPnmlDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T23:20:11.160086Z"},"content_sha256":"f6bb9775f9d5cf9600ed30c906864f52999d30a909643a6d506ed036c88b0967","schema_version":"1.0","event_id":"sha256:f6bb9775f9d5cf9600ed30c906864f52999d30a909643a6d506ed036c88b0967"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:NHPWD5QZV5YK53QHB3VHFXO7FM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Gradient Descent for Regularized Segmentation Losses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dmitrii Marin, Ismail Ben Ayed, Meng Tang, Yuri Boykov","submitted_at":"2018-09-07T06:41:17Z","abstract_excerpt":"The simplicity of gradient descent (GD) made it the default method for training ever-deeper and complex neural networks. Both loss functions and architectures are often explicitly tuned to be amenable to this basic local optimization. In the context of weakly-supervised CNN segmentation, we demonstrate a well-motivated loss function where an alternative optimizer (ADM) achieves the state-of-the-art while GD performs poorly. Interestingly, GD obtains its best result for a \"smoother\" tuning of the loss function. The results are consistent across different network architectures. Our loss is motiv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.02322","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:47:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"853NAH2OAbGnuhUHqtnKDpo6PlP7s08wtLKPpqs66GBUffRA2AHNj3d3p44I1Ro7YdQKVwZwI5OSVALhhH65DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T23:20:11.160437Z"},"content_sha256":"501badf0c549cb483eb8313c78274021e27393b17f519feb83f6ebea120132c2","schema_version":"1.0","event_id":"sha256:501badf0c549cb483eb8313c78274021e27393b17f519feb83f6ebea120132c2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NHPWD5QZV5YK53QHB3VHFXO7FM/bundle.json","state_url":"https://pith.science/pith/NHPWD5QZV5YK53QHB3VHFXO7FM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NHPWD5QZV5YK53QHB3VHFXO7FM/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":"2026-06-08T23:20:11Z","links":{"resolver":"https://pith.science/pith/NHPWD5QZV5YK53QHB3VHFXO7FM","bundle":"https://pith.science/pith/NHPWD5QZV5YK53QHB3VHFXO7FM/bundle.json","state":"https://pith.science/pith/NHPWD5QZV5YK53QHB3VHFXO7FM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NHPWD5QZV5YK53QHB3VHFXO7FM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:NHPWD5QZV5YK53QHB3VHFXO7FM","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":"dc356f7ba2ab1d4b060a7194746f11b39cb8423d1c4f154ea5cb14129fbae33e","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-07T06:41:17Z","title_canon_sha256":"9f6b2acd2496c160965ac6b1556b21345b036909137082e3f74ba98cbb4a208d"},"schema_version":"1.0","source":{"id":"1809.02322","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.02322","created_at":"2026-05-17T23:47:36Z"},{"alias_kind":"arxiv_version","alias_value":"1809.02322v2","created_at":"2026-05-17T23:47:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.02322","created_at":"2026-05-17T23:47:36Z"},{"alias_kind":"pith_short_12","alias_value":"NHPWD5QZV5YK","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"NHPWD5QZV5YK53QH","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"NHPWD5QZ","created_at":"2026-05-18T12:32:40Z"}],"graph_snapshots":[{"event_id":"sha256:501badf0c549cb483eb8313c78274021e27393b17f519feb83f6ebea120132c2","target":"graph","created_at":"2026-05-17T23:47:36Z","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":"The simplicity of gradient descent (GD) made it the default method for training ever-deeper and complex neural networks. Both loss functions and architectures are often explicitly tuned to be amenable to this basic local optimization. In the context of weakly-supervised CNN segmentation, we demonstrate a well-motivated loss function where an alternative optimizer (ADM) achieves the state-of-the-art while GD performs poorly. Interestingly, GD obtains its best result for a \"smoother\" tuning of the loss function. The results are consistent across different network architectures. Our loss is motiv","authors_text":"Dmitrii Marin, Ismail Ben Ayed, Meng Tang, Yuri Boykov","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-07T06:41:17Z","title":"Beyond Gradient Descent for Regularized Segmentation Losses"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.02322","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:f6bb9775f9d5cf9600ed30c906864f52999d30a909643a6d506ed036c88b0967","target":"record","created_at":"2026-05-17T23:47:36Z","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":"dc356f7ba2ab1d4b060a7194746f11b39cb8423d1c4f154ea5cb14129fbae33e","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-07T06:41:17Z","title_canon_sha256":"9f6b2acd2496c160965ac6b1556b21345b036909137082e3f74ba98cbb4a208d"},"schema_version":"1.0","source":{"id":"1809.02322","kind":"arxiv","version":2}},"canonical_sha256":"69df61f619af70aeee070eea72dddf2b085b350814d72e7d3b1edc7d1f2672f2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"69df61f619af70aeee070eea72dddf2b085b350814d72e7d3b1edc7d1f2672f2","first_computed_at":"2026-05-17T23:47:36.098652Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:47:36.098652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"smzVLZfTmp7Tyvd32wFozed6rhUpYLzADQTsjF06GBkYb+MY7yLP0R9jBbmdRjsN/z3CsG0eo3h0KIGn7RcwBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:47:36.099058Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.02322","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6bb9775f9d5cf9600ed30c906864f52999d30a909643a6d506ed036c88b0967","sha256:501badf0c549cb483eb8313c78274021e27393b17f519feb83f6ebea120132c2"],"state_sha256":"4660818a5ca7c63ba5c8c3b3bcb556241f5862ce80397666e438ebebcf64711c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oZS9+vZumJRu7ku3bwHsBhw5N1udXv2JFQCFtSynvyfQWKelk0xLDvv0oMrpBn37q4umA3tEdFsB5TXHotK/Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T23:20:11.162235Z","bundle_sha256":"affa47472cb054442023b5f3606884525c22db5a4a117facf1173a0e74ff63f7"}}