{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XH3DCGDAGW4SZS26O76HK5E2QB","short_pith_number":"pith:XH3DCGDA","canonical_record":{"source":{"id":"2406.16468","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-24T09:16:59Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c5cd85349943d034e50cb863cd6c246ca72aa1e166c61d361c3c5eb480d4f6b2","abstract_canon_sha256":"6f605844a55370ff88a147294f5a846cd3b8d6a1fab309b4d6864cb17a78afea"},"schema_version":"1.0"},"canonical_sha256":"b9f631186035b92ccb5e77fc75749a8045f70b93116e9feaafdc07ab1b74f985","source":{"kind":"arxiv","id":"2406.16468","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.16468","created_at":"2026-07-05T08:35:59Z"},{"alias_kind":"arxiv_version","alias_value":"2406.16468v1","created_at":"2026-07-05T08:35:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.16468","created_at":"2026-07-05T08:35:59Z"},{"alias_kind":"pith_short_12","alias_value":"XH3DCGDAGW4S","created_at":"2026-07-05T08:35:59Z"},{"alias_kind":"pith_short_16","alias_value":"XH3DCGDAGW4SZS26","created_at":"2026-07-05T08:35:59Z"},{"alias_kind":"pith_short_8","alias_value":"XH3DCGDA","created_at":"2026-07-05T08:35:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XH3DCGDAGW4SZS26O76HK5E2QB","target":"record","payload":{"canonical_record":{"source":{"id":"2406.16468","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-24T09:16:59Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c5cd85349943d034e50cb863cd6c246ca72aa1e166c61d361c3c5eb480d4f6b2","abstract_canon_sha256":"6f605844a55370ff88a147294f5a846cd3b8d6a1fab309b4d6864cb17a78afea"},"schema_version":"1.0"},"canonical_sha256":"b9f631186035b92ccb5e77fc75749a8045f70b93116e9feaafdc07ab1b74f985","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:59.149218Z","signature_b64":"UUIDo0KPUVdh/L1zr6VkCnZWtCHTi9OZInJrc+6tkY1W7ojm/uSaWl6pT2sixNTV39R59009cN/vnyIAxLwTAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9f631186035b92ccb5e77fc75749a8045f70b93116e9feaafdc07ab1b74f985","last_reissued_at":"2026-07-05T08:35:59.148763Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:59.148763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.16468","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":"2026-07-05T08:35:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g0iKAqk6xmD6TKqdjcKqSYTuXayJQtEhq/xbKiaKkcNt/87jnDiAEHUDqzES9fK9RP6rMomZmI59zP7sm6FvCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:50:33.535998Z"},"content_sha256":"6b1b4fe23dc1c8357be4da8308dcd5a6b85681199c75342a6fe18c22ae899c45","schema_version":"1.0","event_id":"sha256:6b1b4fe23dc1c8357be4da8308dcd5a6b85681199c75342a6fe18c22ae899c45"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XH3DCGDAGW4SZS26O76HK5E2QB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Hidden Pitfalls of the Cosine Similarity Loss","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew Draganov, Erik J. Bekkers, Sharvaree Vadgama","submitted_at":"2024-06-24T09:16:59Z","abstract_excerpt":"We show that the gradient of the cosine similarity between two points goes to zero in two under-explored settings: (1) if a point has large magnitude or (2) if the points are on opposite ends of the latent space. Counterintuitively, we prove that optimizing the cosine similarity between points forces them to grow in magnitude. Thus, (1) is unavoidable in practice. We then observe that these derivations are extremely general -- they hold across deep learning architectures and for many of the standard self-supervised learning (SSL) loss functions. This leads us to propose cut-initialization: a s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.16468","kind":"arxiv","version":1},"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/2406.16468/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":"2026-07-05T08:35:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yky6zE6eglqSmmz4Twe2dy8x2Z9Iwnt5lWguhTZQv7a53xVovW+4Imw+e/R/nlEhVhhiXRPG13MFf8jJTxxRAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:50:33.536428Z"},"content_sha256":"7a16e984c4a05df940a2a283c62468c328d97dadea64bacbfe0e41c37044b560","schema_version":"1.0","event_id":"sha256:7a16e984c4a05df940a2a283c62468c328d97dadea64bacbfe0e41c37044b560"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XH3DCGDAGW4SZS26O76HK5E2QB/bundle.json","state_url":"https://pith.science/pith/XH3DCGDAGW4SZS26O76HK5E2QB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XH3DCGDAGW4SZS26O76HK5E2QB/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":"2026-07-06T20:50:33Z","links":{"resolver":"https://pith.science/pith/XH3DCGDAGW4SZS26O76HK5E2QB","bundle":"https://pith.science/pith/XH3DCGDAGW4SZS26O76HK5E2QB/bundle.json","state":"https://pith.science/pith/XH3DCGDAGW4SZS26O76HK5E2QB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XH3DCGDAGW4SZS26O76HK5E2QB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XH3DCGDAGW4SZS26O76HK5E2QB","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":"6f605844a55370ff88a147294f5a846cd3b8d6a1fab309b4d6864cb17a78afea","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-24T09:16:59Z","title_canon_sha256":"c5cd85349943d034e50cb863cd6c246ca72aa1e166c61d361c3c5eb480d4f6b2"},"schema_version":"1.0","source":{"id":"2406.16468","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.16468","created_at":"2026-07-05T08:35:59Z"},{"alias_kind":"arxiv_version","alias_value":"2406.16468v1","created_at":"2026-07-05T08:35:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.16468","created_at":"2026-07-05T08:35:59Z"},{"alias_kind":"pith_short_12","alias_value":"XH3DCGDAGW4S","created_at":"2026-07-05T08:35:59Z"},{"alias_kind":"pith_short_16","alias_value":"XH3DCGDAGW4SZS26","created_at":"2026-07-05T08:35:59Z"},{"alias_kind":"pith_short_8","alias_value":"XH3DCGDA","created_at":"2026-07-05T08:35:59Z"}],"graph_snapshots":[{"event_id":"sha256:7a16e984c4a05df940a2a283c62468c328d97dadea64bacbfe0e41c37044b560","target":"graph","created_at":"2026-07-05T08:35:59Z","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/2406.16468/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We show that the gradient of the cosine similarity between two points goes to zero in two under-explored settings: (1) if a point has large magnitude or (2) if the points are on opposite ends of the latent space. Counterintuitively, we prove that optimizing the cosine similarity between points forces them to grow in magnitude. Thus, (1) is unavoidable in practice. We then observe that these derivations are extremely general -- they hold across deep learning architectures and for many of the standard self-supervised learning (SSL) loss functions. This leads us to propose cut-initialization: a s","authors_text":"Andrew Draganov, Erik J. Bekkers, Sharvaree Vadgama","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-24T09:16:59Z","title":"The Hidden Pitfalls of the Cosine Similarity Loss"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.16468","kind":"arxiv","version":1},"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":"sha256:6b1b4fe23dc1c8357be4da8308dcd5a6b85681199c75342a6fe18c22ae899c45","target":"record","created_at":"2026-07-05T08:35:59Z","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":"6f605844a55370ff88a147294f5a846cd3b8d6a1fab309b4d6864cb17a78afea","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-24T09:16:59Z","title_canon_sha256":"c5cd85349943d034e50cb863cd6c246ca72aa1e166c61d361c3c5eb480d4f6b2"},"schema_version":"1.0","source":{"id":"2406.16468","kind":"arxiv","version":1}},"canonical_sha256":"b9f631186035b92ccb5e77fc75749a8045f70b93116e9feaafdc07ab1b74f985","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b9f631186035b92ccb5e77fc75749a8045f70b93116e9feaafdc07ab1b74f985","first_computed_at":"2026-07-05T08:35:59.148763Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:35:59.148763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UUIDo0KPUVdh/L1zr6VkCnZWtCHTi9OZInJrc+6tkY1W7ojm/uSaWl6pT2sixNTV39R59009cN/vnyIAxLwTAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:35:59.149218Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.16468","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6b1b4fe23dc1c8357be4da8308dcd5a6b85681199c75342a6fe18c22ae899c45","sha256:7a16e984c4a05df940a2a283c62468c328d97dadea64bacbfe0e41c37044b560"],"state_sha256":"70cd32846c7095679be7f9fdc74a57c03c1726202f097419345c98784244e4ba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bWkRd5nd9m0Vl9q8iv5MfoG4dy+uqmzjFM0sNekc+zwOJwAlyVLOVrJ7JjacBJuifrR+Ga6LwPBbhsPO3nPxBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T20:50:33.538451Z","bundle_sha256":"35f28149bbc232139192f3372c848dd6b14166e0219166c0f4f86db857da1629"}}