{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:D7DWUI5JPMRCTJEMIVPUHTLNJO","short_pith_number":"pith:D7DWUI5J","canonical_record":{"source":{"id":"2605.14609","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T09:25:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8b12fce1a60d43dc963b15cbf7c64ef90026d74fb1ce16892e72c914f4deb8e7","abstract_canon_sha256":"fca97bee5d8b4c4cc85c25f8b881ccf926981f032b3e70933097ac5b901b7193"},"schema_version":"1.0"},"canonical_sha256":"1fc76a23a97b2229a48c455f43cd6d4b92595ab491a0cf829a7890fa054d45f9","source":{"kind":"arxiv","id":"2605.14609","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14609","created_at":"2026-05-17T23:39:04Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14609v1","created_at":"2026-05-17T23:39:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14609","created_at":"2026-05-17T23:39:04Z"},{"alias_kind":"pith_short_12","alias_value":"D7DWUI5JPMRC","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"D7DWUI5JPMRCTJEM","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"D7DWUI5J","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:D7DWUI5JPMRCTJEMIVPUHTLNJO","target":"record","payload":{"canonical_record":{"source":{"id":"2605.14609","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T09:25:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8b12fce1a60d43dc963b15cbf7c64ef90026d74fb1ce16892e72c914f4deb8e7","abstract_canon_sha256":"fca97bee5d8b4c4cc85c25f8b881ccf926981f032b3e70933097ac5b901b7193"},"schema_version":"1.0"},"canonical_sha256":"1fc76a23a97b2229a48c455f43cd6d4b92595ab491a0cf829a7890fa054d45f9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:04.180826Z","signature_b64":"l/7b1QDbnmXRe4c55s1tgdPSkasPE6Q8p14qEIw5tpfehgQOZ1Fdyb/uOXPn+EVYypKK14jQYDySK8hMpOIKBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1fc76a23a97b2229a48c455f43cd6d4b92595ab491a0cf829a7890fa054d45f9","last_reissued_at":"2026-05-17T23:39:04.180103Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:04.180103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.14609","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1dexRxEIuJDbJBC0l8CkBFF+ytRseMKxYysJzWzCmB/2IcrmNLKQp4XflYeVkzWnrs9ok3fD5FHftUo3oMmWCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T02:42:19.375263Z"},"content_sha256":"81e23130d9a087a49cb317c3aa91473b1c7359bcc7ff77e090c3795c74b24e70","schema_version":"1.0","event_id":"sha256:81e23130d9a087a49cb317c3aa91473b1c7359bcc7ff77e090c3795c74b24e70"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:D7DWUI5JPMRCTJEMIVPUHTLNJO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Image Segmentation via Discriminant Feature Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A new loss based on classical discriminant analysis sharpens segmentation boundaries by making features more separable.","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Adam Dawid Sztamborski, Antonio Agudo, Ra\\\"ul P\\'erez-Gonzalo","submitted_at":"2026-05-14T09:25:36Z","abstract_excerpt":"Accurate image segmentation remains challenging, particularly in generating sharp, confident boundaries. While modern architectures have advanced the field, many of them still rely on standard loss functions like Cross-Entropy and Dice, which often neglect the discriminative structure of learned features, leading to inaccurate boundaries. This work introduces Deep Discriminant Analysis (DDA), a differentiable, architecture-agnostic loss function that embeds classical discriminant principles for network training. DDA explicitly maximizes between-class variance while minimizing within-class one,"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"DDA explicitly maximizes between-class variance while minimizing within-class one, promoting compact and separable feature distributions without increasing inference cost.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the observed improvements on the DIS5K benchmark are caused by the discriminant properties of the loss rather than by differences in training schedule, hyper-parameters, or implementation details not described in the abstract.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Deep Discriminant Analysis (DDA) is a new loss that maximizes between-class variance and minimizes within-class variance to produce more compact and separable features for image segmentation.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A new loss based on classical discriminant analysis sharpens segmentation boundaries by making features more separable.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"e23f9a70586ba0cce06424f4016eb1e8fa3420bdb088fe922db95270f44f316b"},"source":{"id":"2605.14609","kind":"arxiv","version":1},"verdict":{"id":"b4f2888d-16ba-4c34-a88b-acbe4286d426","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T06:02:18.083261Z","strongest_claim":"DDA explicitly maximizes between-class variance while minimizing within-class one, promoting compact and separable feature distributions without increasing inference cost.","one_line_summary":"Deep Discriminant Analysis (DDA) is a new loss that maximizes between-class variance and minimizes within-class variance to produce more compact and separable features for image segmentation.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the observed improvements on the DIS5K benchmark are caused by the discriminant properties of the loss rather than by differences in training schedule, hyper-parameters, or implementation details not described in the abstract.","pith_extraction_headline":"A new loss based on classical discriminant analysis sharpens segmentation boundaries by making features more separable."},"references":{"count":38,"sample":[{"doi":"10.13039/501100011033","year":2026,"title":"Deep Image Segmentation via Discriminant Feature Learning","work_id":"65b3d757-cd63-4d82-92c8-70be0f6a295e","ref_index":1,"cited_arxiv_id":"2605.14609","is_internal_anchor":true},{"doi":"","year":null,"title":"It can lead to over- lapping foreground and background activations and uncertain or blurred boundaries","work_id":"c27c832d-9f33-47df-bc3b-285b2ad30f82","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"A largerS B indicates better class separability","work_id":"eda37088-e888-43b2-ba58-d68c313ba534","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Smaller values indicate more compact, discriminable classes","work_id":"bd527b60-15e7-44ef-ad78-03ec8e61147f","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"This desirable general separability criterion should take larger values when the within-class scatter is smaller and when the between-class scatter is larger","work_id":"fa2da256-ad58-4b90-9999-68cdff036769","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":38,"snapshot_sha256":"03b081cec002f78189b73181451db3eb3788471a303e3e6c9743280d2aa672f3","internal_anchors":2},"formal_canon":{"evidence_count":2,"snapshot_sha256":"1ba84952438072f731be2d919b5cc4668817913fde996c6498e1507925035a09"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"b4f2888d-16ba-4c34-a88b-acbe4286d426"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dIqTf6VHCH7Om4YKGaEJg8J6yZJ1zdQfBOUes/6t0GWSA2p83YEJMrlfkRE8nH29LnXZySWkk9KJlhuV55rBBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T02:42:19.376213Z"},"content_sha256":"2b9922943ad27d143806c7eead0f03f85f17a6b73be87b613de9ec18ee732c8b","schema_version":"1.0","event_id":"sha256:2b9922943ad27d143806c7eead0f03f85f17a6b73be87b613de9ec18ee732c8b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D7DWUI5JPMRCTJEMIVPUHTLNJO/bundle.json","state_url":"https://pith.science/pith/D7DWUI5JPMRCTJEMIVPUHTLNJO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D7DWUI5JPMRCTJEMIVPUHTLNJO/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":"2026-06-06T02:42:19Z","links":{"resolver":"https://pith.science/pith/D7DWUI5JPMRCTJEMIVPUHTLNJO","bundle":"https://pith.science/pith/D7DWUI5JPMRCTJEMIVPUHTLNJO/bundle.json","state":"https://pith.science/pith/D7DWUI5JPMRCTJEMIVPUHTLNJO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D7DWUI5JPMRCTJEMIVPUHTLNJO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:D7DWUI5JPMRCTJEMIVPUHTLNJO","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":"fca97bee5d8b4c4cc85c25f8b881ccf926981f032b3e70933097ac5b901b7193","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T09:25:36Z","title_canon_sha256":"8b12fce1a60d43dc963b15cbf7c64ef90026d74fb1ce16892e72c914f4deb8e7"},"schema_version":"1.0","source":{"id":"2605.14609","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14609","created_at":"2026-05-17T23:39:04Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14609v1","created_at":"2026-05-17T23:39:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14609","created_at":"2026-05-17T23:39:04Z"},{"alias_kind":"pith_short_12","alias_value":"D7DWUI5JPMRC","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"D7DWUI5JPMRCTJEM","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"D7DWUI5J","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:2b9922943ad27d143806c7eead0f03f85f17a6b73be87b613de9ec18ee732c8b","target":"graph","created_at":"2026-05-17T23:39:04Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"DDA explicitly maximizes between-class variance while minimizing within-class one, promoting compact and separable feature distributions without increasing inference cost."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the observed improvements on the DIS5K benchmark are caused by the discriminant properties of the loss rather than by differences in training schedule, hyper-parameters, or implementation details not described in the abstract."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Deep Discriminant Analysis (DDA) is a new loss that maximizes between-class variance and minimizes within-class variance to produce more compact and separable features for image segmentation."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A new loss based on classical discriminant analysis sharpens segmentation boundaries by making features more separable."}],"snapshot_sha256":"e23f9a70586ba0cce06424f4016eb1e8fa3420bdb088fe922db95270f44f316b"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"1ba84952438072f731be2d919b5cc4668817913fde996c6498e1507925035a09"},"paper":{"abstract_excerpt":"Accurate image segmentation remains challenging, particularly in generating sharp, confident boundaries. While modern architectures have advanced the field, many of them still rely on standard loss functions like Cross-Entropy and Dice, which often neglect the discriminative structure of learned features, leading to inaccurate boundaries. This work introduces Deep Discriminant Analysis (DDA), a differentiable, architecture-agnostic loss function that embeds classical discriminant principles for network training. DDA explicitly maximizes between-class variance while minimizing within-class one,","authors_text":"Adam Dawid Sztamborski, Antonio Agudo, Ra\\\"ul P\\'erez-Gonzalo","cross_cats":["cs.LG"],"headline":"A new loss based on classical discriminant analysis sharpens segmentation boundaries by making features more separable.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T09:25:36Z","title":"Deep Image Segmentation via Discriminant Feature Learning"},"references":{"count":38,"internal_anchors":2,"resolved_work":38,"sample":[{"cited_arxiv_id":"2605.14609","doi":"10.13039/501100011033","is_internal_anchor":true,"ref_index":1,"title":"Deep Image Segmentation via Discriminant Feature Learning","work_id":"65b3d757-cd63-4d82-92c8-70be0f6a295e","year":2026},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"It can lead to over- lapping foreground and background activations and uncertain or blurred boundaries","work_id":"c27c832d-9f33-47df-bc3b-285b2ad30f82","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"A largerS B indicates better class separability","work_id":"eda37088-e888-43b2-ba58-d68c313ba534","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Smaller values indicate more compact, discriminable classes","work_id":"bd527b60-15e7-44ef-ad78-03ec8e61147f","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"This desirable general separability criterion should take larger values when the within-class scatter is smaller and when the between-class scatter is larger","work_id":"fa2da256-ad58-4b90-9999-68cdff036769","year":null}],"snapshot_sha256":"03b081cec002f78189b73181451db3eb3788471a303e3e6c9743280d2aa672f3"},"source":{"id":"2605.14609","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T06:02:18.083261Z","id":"b4f2888d-16ba-4c34-a88b-acbe4286d426","model_set":{"reader":"grok-4.3"},"one_line_summary":"Deep Discriminant Analysis (DDA) is a new loss that maximizes between-class variance and minimizes within-class variance to produce more compact and separable features for image segmentation.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A new loss based on classical discriminant analysis sharpens segmentation boundaries by making features more separable.","strongest_claim":"DDA explicitly maximizes between-class variance while minimizing within-class one, promoting compact and separable feature distributions without increasing inference cost.","weakest_assumption":"That the observed improvements on the DIS5K benchmark are caused by the discriminant properties of the loss rather than by differences in training schedule, hyper-parameters, or implementation details not described in the abstract."}},"verdict_id":"b4f2888d-16ba-4c34-a88b-acbe4286d426"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:81e23130d9a087a49cb317c3aa91473b1c7359bcc7ff77e090c3795c74b24e70","target":"record","created_at":"2026-05-17T23:39:04Z","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":"fca97bee5d8b4c4cc85c25f8b881ccf926981f032b3e70933097ac5b901b7193","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T09:25:36Z","title_canon_sha256":"8b12fce1a60d43dc963b15cbf7c64ef90026d74fb1ce16892e72c914f4deb8e7"},"schema_version":"1.0","source":{"id":"2605.14609","kind":"arxiv","version":1}},"canonical_sha256":"1fc76a23a97b2229a48c455f43cd6d4b92595ab491a0cf829a7890fa054d45f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1fc76a23a97b2229a48c455f43cd6d4b92595ab491a0cf829a7890fa054d45f9","first_computed_at":"2026-05-17T23:39:04.180103Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:04.180103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l/7b1QDbnmXRe4c55s1tgdPSkasPE6Q8p14qEIw5tpfehgQOZ1Fdyb/uOXPn+EVYypKK14jQYDySK8hMpOIKBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:04.180826Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14609","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:81e23130d9a087a49cb317c3aa91473b1c7359bcc7ff77e090c3795c74b24e70","sha256:2b9922943ad27d143806c7eead0f03f85f17a6b73be87b613de9ec18ee732c8b"],"state_sha256":"73a683f94c41f5950bc88ffca54717774192d87a54d5f6e374ecba19f056e4c6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q8HrCr2lzA6EQSkKvdF//ClGvG4BjLTxEQX0t5Fb6rWg4XJtcL2lqpDkp9HtLMV/SrT2d6l1IEvZtaRx7OEuDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T02:42:19.385521Z","bundle_sha256":"661e4b2ac77805c3b4165eaa912943b0ae0d2ee6485dc7bc8043ea014cd2c175"}}