{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:DKKKPAEJXQQPS6BWYAN7QS7PL3","short_pith_number":"pith:DKKKPAEJ","canonical_record":{"source":{"id":"1511.04707","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-15T14:33:26Z","cross_cats_sorted":[],"title_canon_sha256":"08df6411b13f0b5b380456bcf476f9dc2d1288e7805fac12eb3224fbabe0c7b9","abstract_canon_sha256":"f0d5bae3d9ab39ffed44f09c86c4d818036d007b70484f5a1ba6520623510d55"},"schema_version":"1.0"},"canonical_sha256":"1a94a78089bc20f97836c01bf84bef5ed39319d1e17e99134f1995300aafcb10","source":{"kind":"arxiv","id":"1511.04707","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.04707","created_at":"2026-05-18T01:20:29Z"},{"alias_kind":"arxiv_version","alias_value":"1511.04707v5","created_at":"2026-05-18T01:20:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.04707","created_at":"2026-05-18T01:20:29Z"},{"alias_kind":"pith_short_12","alias_value":"DKKKPAEJXQQP","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_16","alias_value":"DKKKPAEJXQQPS6BW","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_8","alias_value":"DKKKPAEJ","created_at":"2026-05-18T12:29:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:DKKKPAEJXQQPS6BWYAN7QS7PL3","target":"record","payload":{"canonical_record":{"source":{"id":"1511.04707","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-15T14:33:26Z","cross_cats_sorted":[],"title_canon_sha256":"08df6411b13f0b5b380456bcf476f9dc2d1288e7805fac12eb3224fbabe0c7b9","abstract_canon_sha256":"f0d5bae3d9ab39ffed44f09c86c4d818036d007b70484f5a1ba6520623510d55"},"schema_version":"1.0"},"canonical_sha256":"1a94a78089bc20f97836c01bf84bef5ed39319d1e17e99134f1995300aafcb10","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:20:29.113333Z","signature_b64":"cKcDkXVKWm0OpbyJ3Pft32woDQdOs9dunOfm3O5QObPkp4VdGDf9Wl8wSyDZZ3vc1ziJtz6uG0DW7SZC3/5uAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a94a78089bc20f97836c01bf84bef5ed39319d1e17e99134f1995300aafcb10","last_reissued_at":"2026-05-18T01:20:29.112774Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:20:29.112774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1511.04707","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:20:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yw6HDFMceieTZhYMaTtDLNN/2JtBdjGAJVtzEQhF5+C+cBfKG1IZzRR3S/JAm3zxgr86M+6gPbfm14fmGbSxCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T02:57:01.008096Z"},"content_sha256":"52381089b6a8999ef881a2f2c9bee0f58961f453f7c333fa1fefaa10f7ffd5c1","schema_version":"1.0","event_id":"sha256:52381089b6a8999ef881a2f2c9bee0f58961f453f7c333fa1fefaa10f7ffd5c1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:DKKKPAEJXQQPS6BWYAN7QS7PL3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Linear Discriminant Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gerhard Widmer, Matthias Dorfer, Rainer Kelz","submitted_at":"2015-11-15T14:33:26Z","abstract_excerpt":"We introduce Deep Linear Discriminant Analysis (DeepLDA) which learns linearly separable latent representations in an end-to-end fashion. Classic LDA extracts features which preserve class separability and is used for dimensionality reduction for many classification problems. The central idea of this paper is to put LDA on top of a deep neural network. This can be seen as a non-linear extension of classic LDA. Instead of maximizing the likelihood of target labels for individual samples, we propose an objective function that pushes the network to produce feature distributions which: (a) have lo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.04707","kind":"arxiv","version":5},"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":"2026-05-18T01:20:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LT+8UrhcHaV2uTMJ8D3Ovm3COJa0PpgSEvm54KhfYI/Uv064Gytt2WXIrmdMJr+0RsROJiJitNAZY1f9xkyeCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T02:57:01.008662Z"},"content_sha256":"eef033e7f1ba79588946aaddfb54033bf76993ac58ad52e361b0505ffcb7cb28","schema_version":"1.0","event_id":"sha256:eef033e7f1ba79588946aaddfb54033bf76993ac58ad52e361b0505ffcb7cb28"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DKKKPAEJXQQPS6BWYAN7QS7PL3/bundle.json","state_url":"https://pith.science/pith/DKKKPAEJXQQPS6BWYAN7QS7PL3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DKKKPAEJXQQPS6BWYAN7QS7PL3/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":"2026-05-25T02:57:01Z","links":{"resolver":"https://pith.science/pith/DKKKPAEJXQQPS6BWYAN7QS7PL3","bundle":"https://pith.science/pith/DKKKPAEJXQQPS6BWYAN7QS7PL3/bundle.json","state":"https://pith.science/pith/DKKKPAEJXQQPS6BWYAN7QS7PL3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DKKKPAEJXQQPS6BWYAN7QS7PL3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:DKKKPAEJXQQPS6BWYAN7QS7PL3","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":"f0d5bae3d9ab39ffed44f09c86c4d818036d007b70484f5a1ba6520623510d55","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-15T14:33:26Z","title_canon_sha256":"08df6411b13f0b5b380456bcf476f9dc2d1288e7805fac12eb3224fbabe0c7b9"},"schema_version":"1.0","source":{"id":"1511.04707","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.04707","created_at":"2026-05-18T01:20:29Z"},{"alias_kind":"arxiv_version","alias_value":"1511.04707v5","created_at":"2026-05-18T01:20:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.04707","created_at":"2026-05-18T01:20:29Z"},{"alias_kind":"pith_short_12","alias_value":"DKKKPAEJXQQP","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_16","alias_value":"DKKKPAEJXQQPS6BW","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_8","alias_value":"DKKKPAEJ","created_at":"2026-05-18T12:29:17Z"}],"graph_snapshots":[{"event_id":"sha256:eef033e7f1ba79588946aaddfb54033bf76993ac58ad52e361b0505ffcb7cb28","target":"graph","created_at":"2026-05-18T01:20:29Z","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":"We introduce Deep Linear Discriminant Analysis (DeepLDA) which learns linearly separable latent representations in an end-to-end fashion. Classic LDA extracts features which preserve class separability and is used for dimensionality reduction for many classification problems. The central idea of this paper is to put LDA on top of a deep neural network. This can be seen as a non-linear extension of classic LDA. Instead of maximizing the likelihood of target labels for individual samples, we propose an objective function that pushes the network to produce feature distributions which: (a) have lo","authors_text":"Gerhard Widmer, Matthias Dorfer, Rainer Kelz","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-15T14:33:26Z","title":"Deep Linear Discriminant Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.04707","kind":"arxiv","version":5},"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":"sha256:52381089b6a8999ef881a2f2c9bee0f58961f453f7c333fa1fefaa10f7ffd5c1","target":"record","created_at":"2026-05-18T01:20:29Z","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":"f0d5bae3d9ab39ffed44f09c86c4d818036d007b70484f5a1ba6520623510d55","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-15T14:33:26Z","title_canon_sha256":"08df6411b13f0b5b380456bcf476f9dc2d1288e7805fac12eb3224fbabe0c7b9"},"schema_version":"1.0","source":{"id":"1511.04707","kind":"arxiv","version":5}},"canonical_sha256":"1a94a78089bc20f97836c01bf84bef5ed39319d1e17e99134f1995300aafcb10","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a94a78089bc20f97836c01bf84bef5ed39319d1e17e99134f1995300aafcb10","first_computed_at":"2026-05-18T01:20:29.112774Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:20:29.112774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cKcDkXVKWm0OpbyJ3Pft32woDQdOs9dunOfm3O5QObPkp4VdGDf9Wl8wSyDZZ3vc1ziJtz6uG0DW7SZC3/5uAg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:20:29.113333Z","signed_message":"canonical_sha256_bytes"},"source_id":"1511.04707","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:52381089b6a8999ef881a2f2c9bee0f58961f453f7c333fa1fefaa10f7ffd5c1","sha256:eef033e7f1ba79588946aaddfb54033bf76993ac58ad52e361b0505ffcb7cb28"],"state_sha256":"607d750c609b004453afdc46ff02ae83fc7a8316110be0460178af218e465a75"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ag4GdSBBQ3J9bpuBOCh+hci0K+DvRppeT1yY/8LusKn4jlT4VM16hIjVLpW1QLPjBo5lofOCpCVcBc2BxhGgAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T02:57:01.012061Z","bundle_sha256":"15fb1c9b65570ee1baaa80a29c206471e8e87d325c783bf2c26d2b8886a276eb"}}