{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:CMKDWE6QPVZRQTHFGT5KUDDUR6","short_pith_number":"pith:CMKDWE6Q","canonical_record":{"source":{"id":"1812.09916","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-24T13:23:18Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"5e585c8bf758b12b17e7961035781a079460e965c6297d4acbb7295517e77efa","abstract_canon_sha256":"9271665a04e6802a44b634b3b2f2edda6d2fb598adbdfe968aefdb51354c5026"},"schema_version":"1.0"},"canonical_sha256":"13143b13d07d73184ce534faaa0c748fae106cef78b31d62ab9416fde25fce32","source":{"kind":"arxiv","id":"1812.09916","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.09916","created_at":"2026-05-17T23:54:31Z"},{"alias_kind":"arxiv_version","alias_value":"1812.09916v4","created_at":"2026-05-17T23:54:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.09916","created_at":"2026-05-17T23:54:31Z"},{"alias_kind":"pith_short_12","alias_value":"CMKDWE6QPVZR","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"CMKDWE6QPVZRQTHF","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"CMKDWE6Q","created_at":"2026-05-18T12:32:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:CMKDWE6QPVZRQTHFGT5KUDDUR6","target":"record","payload":{"canonical_record":{"source":{"id":"1812.09916","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-24T13:23:18Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"5e585c8bf758b12b17e7961035781a079460e965c6297d4acbb7295517e77efa","abstract_canon_sha256":"9271665a04e6802a44b634b3b2f2edda6d2fb598adbdfe968aefdb51354c5026"},"schema_version":"1.0"},"canonical_sha256":"13143b13d07d73184ce534faaa0c748fae106cef78b31d62ab9416fde25fce32","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:31.393632Z","signature_b64":"6VgFDEJcnoPIXblhCFHqqLxkmDSiTIdML9oHzxz15aN5uDhT3BlbH9xGPM/HsW9TfaviOrBG65/TgcUzdza0CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13143b13d07d73184ce534faaa0c748fae106cef78b31d62ab9416fde25fce32","last_reissued_at":"2026-05-17T23:54:31.393004Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:31.393004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.09916","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:54:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T2seIwpUMmkBsEDEwPlIz6ljOmbOE1w8fy2i22hKWxKnju1mF9SD+yM5ZlXOlgnQOxT67USKzZzie2HmEqXvAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T22:36:39.414755Z"},"content_sha256":"4e62f80ab691e95f675c46ca852ad1e7a6d16e58e4f9ef56bbb4ec18698aeb3d","schema_version":"1.0","event_id":"sha256:4e62f80ab691e95f675c46ca852ad1e7a6d16e58e4f9ef56bbb4ec18698aeb3d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:CMKDWE6QPVZRQTHFGT5KUDDUR6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving MMD-GAN Training with Repulsive Loss Function","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Saman Halgamuge, Wei Wang, Yuan Sun","submitted_at":"2018-12-24T13:23:18Z","abstract_excerpt":"Generative adversarial nets (GANs) are widely used to learn the data sampling process and their performance may heavily depend on the loss functions, given a limited computational budget. This study revisits MMD-GAN that uses the maximum mean discrepancy (MMD) as the loss function for GAN and makes two contributions. First, we argue that the existing MMD loss function may discourage the learning of fine details in data as it attempts to contract the discriminator outputs of real data. To address this issue, we propose a repulsive loss function to actively learn the difference among the real da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.09916","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":""},"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":"2026-05-17T23:54:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6SE/uHQSYDDWzU3EDJOA0LJzQOa9nwc8lTqOtEIiE40QIq1AfhUXyvR3F+2Cq89ZrrOj67I16nEwsXE1F7VQAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T22:36:39.415105Z"},"content_sha256":"f7da95b58abf9ffda05691b6db8690dfdabb946a6278eeecb476e86cee8cd032","schema_version":"1.0","event_id":"sha256:f7da95b58abf9ffda05691b6db8690dfdabb946a6278eeecb476e86cee8cd032"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CMKDWE6QPVZRQTHFGT5KUDDUR6/bundle.json","state_url":"https://pith.science/pith/CMKDWE6QPVZRQTHFGT5KUDDUR6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CMKDWE6QPVZRQTHFGT5KUDDUR6/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":"2026-06-08T22:36:39Z","links":{"resolver":"https://pith.science/pith/CMKDWE6QPVZRQTHFGT5KUDDUR6","bundle":"https://pith.science/pith/CMKDWE6QPVZRQTHFGT5KUDDUR6/bundle.json","state":"https://pith.science/pith/CMKDWE6QPVZRQTHFGT5KUDDUR6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CMKDWE6QPVZRQTHFGT5KUDDUR6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:CMKDWE6QPVZRQTHFGT5KUDDUR6","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":"9271665a04e6802a44b634b3b2f2edda6d2fb598adbdfe968aefdb51354c5026","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-24T13:23:18Z","title_canon_sha256":"5e585c8bf758b12b17e7961035781a079460e965c6297d4acbb7295517e77efa"},"schema_version":"1.0","source":{"id":"1812.09916","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.09916","created_at":"2026-05-17T23:54:31Z"},{"alias_kind":"arxiv_version","alias_value":"1812.09916v4","created_at":"2026-05-17T23:54:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.09916","created_at":"2026-05-17T23:54:31Z"},{"alias_kind":"pith_short_12","alias_value":"CMKDWE6QPVZR","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"CMKDWE6QPVZRQTHF","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"CMKDWE6Q","created_at":"2026-05-18T12:32:16Z"}],"graph_snapshots":[{"event_id":"sha256:f7da95b58abf9ffda05691b6db8690dfdabb946a6278eeecb476e86cee8cd032","target":"graph","created_at":"2026-05-17T23:54:31Z","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":"Generative adversarial nets (GANs) are widely used to learn the data sampling process and their performance may heavily depend on the loss functions, given a limited computational budget. This study revisits MMD-GAN that uses the maximum mean discrepancy (MMD) as the loss function for GAN and makes two contributions. First, we argue that the existing MMD loss function may discourage the learning of fine details in data as it attempts to contract the discriminator outputs of real data. To address this issue, we propose a repulsive loss function to actively learn the difference among the real da","authors_text":"Saman Halgamuge, Wei Wang, Yuan Sun","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-24T13:23:18Z","title":"Improving MMD-GAN Training with Repulsive Loss Function"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.09916","kind":"arxiv","version":4},"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":"sha256:4e62f80ab691e95f675c46ca852ad1e7a6d16e58e4f9ef56bbb4ec18698aeb3d","target":"record","created_at":"2026-05-17T23:54:31Z","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":"9271665a04e6802a44b634b3b2f2edda6d2fb598adbdfe968aefdb51354c5026","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-24T13:23:18Z","title_canon_sha256":"5e585c8bf758b12b17e7961035781a079460e965c6297d4acbb7295517e77efa"},"schema_version":"1.0","source":{"id":"1812.09916","kind":"arxiv","version":4}},"canonical_sha256":"13143b13d07d73184ce534faaa0c748fae106cef78b31d62ab9416fde25fce32","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"13143b13d07d73184ce534faaa0c748fae106cef78b31d62ab9416fde25fce32","first_computed_at":"2026-05-17T23:54:31.393004Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:54:31.393004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6VgFDEJcnoPIXblhCFHqqLxkmDSiTIdML9oHzxz15aN5uDhT3BlbH9xGPM/HsW9TfaviOrBG65/TgcUzdza0CA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:54:31.393632Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.09916","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4e62f80ab691e95f675c46ca852ad1e7a6d16e58e4f9ef56bbb4ec18698aeb3d","sha256:f7da95b58abf9ffda05691b6db8690dfdabb946a6278eeecb476e86cee8cd032"],"state_sha256":"941b6de8f416f5df3b092b0f79d5f69cace9f1adf1e4cdf156bf4679d5c95eb0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6JROGzTyz0mQ+ViYvIVtC40qIj/tTMA8SEbzmgG5wmeYuYJOqIoOIOMy6VqWnAyWKoQGHZbew+Z8wbzOnmp/Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T22:36:39.416983Z","bundle_sha256":"2aae25798e397485af7100ca4d8c54a2dae8e115ca2b33d713f3a9599bbe4d50"}}