{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:DJYFZP36S4MGLCFH72E7TDPVTA","short_pith_number":"pith:DJYFZP36","canonical_record":{"source":{"id":"2210.02192","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-04T00:36:45Z","cross_cats_sorted":["cs.AI","cs.IT","math.IT","math.OC","stat.ML"],"title_canon_sha256":"9b66d3f43bdcf23306cdee2d94cef0c7ce7c3f1bdd2620447af8d019076c8e68","abstract_canon_sha256":"d0d519f908975b2e8d8f4a72425cfad367caca5622f87571a48cf835464412ee"},"schema_version":"1.0"},"canonical_sha256":"1a705cbf7e97186588a7fe89f98df5982fa928bc0becbc9f00f919b2615ae04a","source":{"kind":"arxiv","id":"2210.02192","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.02192","created_at":"2026-07-05T05:04:31Z"},{"alias_kind":"arxiv_version","alias_value":"2210.02192v2","created_at":"2026-07-05T05:04:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.02192","created_at":"2026-07-05T05:04:31Z"},{"alias_kind":"pith_short_12","alias_value":"DJYFZP36S4MG","created_at":"2026-07-05T05:04:31Z"},{"alias_kind":"pith_short_16","alias_value":"DJYFZP36S4MGLCFH","created_at":"2026-07-05T05:04:31Z"},{"alias_kind":"pith_short_8","alias_value":"DJYFZP36","created_at":"2026-07-05T05:04:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:DJYFZP36S4MGLCFH72E7TDPVTA","target":"record","payload":{"canonical_record":{"source":{"id":"2210.02192","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-04T00:36:45Z","cross_cats_sorted":["cs.AI","cs.IT","math.IT","math.OC","stat.ML"],"title_canon_sha256":"9b66d3f43bdcf23306cdee2d94cef0c7ce7c3f1bdd2620447af8d019076c8e68","abstract_canon_sha256":"d0d519f908975b2e8d8f4a72425cfad367caca5622f87571a48cf835464412ee"},"schema_version":"1.0"},"canonical_sha256":"1a705cbf7e97186588a7fe89f98df5982fa928bc0becbc9f00f919b2615ae04a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:04:31.657113Z","signature_b64":"MJ6grCUo76/YUjC8logL6+klzDVIwuJG6uOebV6OsfVgcWFQpZcdA7bDACpzniy5CXLS6SHqKwL8krgjPlptAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a705cbf7e97186588a7fe89f98df5982fa928bc0becbc9f00f919b2615ae04a","last_reissued_at":"2026-07-05T05:04:31.656650Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:04:31.656650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.02192","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":"2026-07-05T05:04:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r+qHko6UAH4gHaC9EWHaMKiYuPWJvhxniCKUnESGeImqGi39NXxI6vHQ5hPtOgFPATK9MA/kG00UDoynRAHGBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T15:02:01.167044Z"},"content_sha256":"c8c77dce617be410e86938219072a12e87346eef5f4c1c480a2858658ee53b1e","schema_version":"1.0","event_id":"sha256:c8c77dce617be410e86938219072a12e87346eef5f4c1c480a2858658ee53b1e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:DJYFZP36S4MGLCFH72E7TDPVTA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Are All Losses Created Equal: A Neural Collapse Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IT","math.IT","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chong You, Jinxin Zhou, Kangning Liu, Qing Qu, Sheng Liu, Xiao Li, Zhihui Zhu","submitted_at":"2022-10-04T00:36:45Z","abstract_excerpt":"While cross entropy (CE) is the most commonly used loss to train deep neural networks for classification tasks, many alternative losses have been developed to obtain better empirical performance. Among them, which one is the best to use is still a mystery, because there seem to be multiple factors affecting the answer, such as properties of the dataset, the choice of network architecture, and so on. This paper studies the choice of loss function by examining the last-layer features of deep networks, drawing inspiration from a recent line work showing that the global optimal solution of CE and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.02192","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2210.02192/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T05:04:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zU0XwHQF4/PqvZUWgOZci6PXUxELoY78v1hidjuWL/kMcfQo/oIaZN0QvitGa5TgSDwyd0pn2yKxhIDZwthYCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T15:02:01.167837Z"},"content_sha256":"99c6323ce13abe8f8c0743dc60463f61dd6bfa3f137d52fc3fd4c6cd8f952bba","schema_version":"1.0","event_id":"sha256:99c6323ce13abe8f8c0743dc60463f61dd6bfa3f137d52fc3fd4c6cd8f952bba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DJYFZP36S4MGLCFH72E7TDPVTA/bundle.json","state_url":"https://pith.science/pith/DJYFZP36S4MGLCFH72E7TDPVTA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DJYFZP36S4MGLCFH72E7TDPVTA/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":"2026-07-05T15:02:01Z","links":{"resolver":"https://pith.science/pith/DJYFZP36S4MGLCFH72E7TDPVTA","bundle":"https://pith.science/pith/DJYFZP36S4MGLCFH72E7TDPVTA/bundle.json","state":"https://pith.science/pith/DJYFZP36S4MGLCFH72E7TDPVTA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DJYFZP36S4MGLCFH72E7TDPVTA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:DJYFZP36S4MGLCFH72E7TDPVTA","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":"d0d519f908975b2e8d8f4a72425cfad367caca5622f87571a48cf835464412ee","cross_cats_sorted":["cs.AI","cs.IT","math.IT","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-04T00:36:45Z","title_canon_sha256":"9b66d3f43bdcf23306cdee2d94cef0c7ce7c3f1bdd2620447af8d019076c8e68"},"schema_version":"1.0","source":{"id":"2210.02192","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.02192","created_at":"2026-07-05T05:04:31Z"},{"alias_kind":"arxiv_version","alias_value":"2210.02192v2","created_at":"2026-07-05T05:04:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.02192","created_at":"2026-07-05T05:04:31Z"},{"alias_kind":"pith_short_12","alias_value":"DJYFZP36S4MG","created_at":"2026-07-05T05:04:31Z"},{"alias_kind":"pith_short_16","alias_value":"DJYFZP36S4MGLCFH","created_at":"2026-07-05T05:04:31Z"},{"alias_kind":"pith_short_8","alias_value":"DJYFZP36","created_at":"2026-07-05T05:04:31Z"}],"graph_snapshots":[{"event_id":"sha256:99c6323ce13abe8f8c0743dc60463f61dd6bfa3f137d52fc3fd4c6cd8f952bba","target":"graph","created_at":"2026-07-05T05:04:31Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2210.02192/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While cross entropy (CE) is the most commonly used loss to train deep neural networks for classification tasks, many alternative losses have been developed to obtain better empirical performance. Among them, which one is the best to use is still a mystery, because there seem to be multiple factors affecting the answer, such as properties of the dataset, the choice of network architecture, and so on. This paper studies the choice of loss function by examining the last-layer features of deep networks, drawing inspiration from a recent line work showing that the global optimal solution of CE and ","authors_text":"Chong You, Jinxin Zhou, Kangning Liu, Qing Qu, Sheng Liu, Xiao Li, Zhihui Zhu","cross_cats":["cs.AI","cs.IT","math.IT","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-04T00:36:45Z","title":"Are All Losses Created Equal: A Neural Collapse Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.02192","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:c8c77dce617be410e86938219072a12e87346eef5f4c1c480a2858658ee53b1e","target":"record","created_at":"2026-07-05T05:04:31Z","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":"d0d519f908975b2e8d8f4a72425cfad367caca5622f87571a48cf835464412ee","cross_cats_sorted":["cs.AI","cs.IT","math.IT","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-04T00:36:45Z","title_canon_sha256":"9b66d3f43bdcf23306cdee2d94cef0c7ce7c3f1bdd2620447af8d019076c8e68"},"schema_version":"1.0","source":{"id":"2210.02192","kind":"arxiv","version":2}},"canonical_sha256":"1a705cbf7e97186588a7fe89f98df5982fa928bc0becbc9f00f919b2615ae04a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a705cbf7e97186588a7fe89f98df5982fa928bc0becbc9f00f919b2615ae04a","first_computed_at":"2026-07-05T05:04:31.656650Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:04:31.656650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MJ6grCUo76/YUjC8logL6+klzDVIwuJG6uOebV6OsfVgcWFQpZcdA7bDACpzniy5CXLS6SHqKwL8krgjPlptAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:04:31.657113Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.02192","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c8c77dce617be410e86938219072a12e87346eef5f4c1c480a2858658ee53b1e","sha256:99c6323ce13abe8f8c0743dc60463f61dd6bfa3f137d52fc3fd4c6cd8f952bba"],"state_sha256":"c1d1232df531268e6a47321512e5e4a59bd561e62b9cea27232980610ddd1441"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6dURHOLaex0HHTOY/2qkbIvLloDI5PDyiJioDMyMRaAzVcT62LyyadJQaXW5XD9RouVM5hw9XfORB305QopcAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T15:02:01.172266Z","bundle_sha256":"8883f2f2523652d4fc4b3a6282edb22f66ec2a67007dfefa501f5c41a5652a42"}}