{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:P4XQTLMRVFAGUG4AHQDJEL5CB4","short_pith_number":"pith:P4XQTLMR","canonical_record":{"source":{"id":"2502.08231","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-12T09:20:08Z","cross_cats_sorted":[],"title_canon_sha256":"dd33eb89d5d9d41deb6ee5e21b9af67f0010d61fdf1ded9f2f65428607424dbc","abstract_canon_sha256":"8b67a0704fbcd1c0a6f8d761d7fc12db497a2e14a593017d4462425a40b5d4bb"},"schema_version":"1.0"},"canonical_sha256":"7f2f09ad91a9406a1b803c06922fa20f234ef976e11584d9b53445c10490ded6","source":{"kind":"arxiv","id":"2502.08231","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.08231","created_at":"2026-07-05T11:59:10Z"},{"alias_kind":"arxiv_version","alias_value":"2502.08231v4","created_at":"2026-07-05T11:59:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08231","created_at":"2026-07-05T11:59:10Z"},{"alias_kind":"pith_short_12","alias_value":"P4XQTLMRVFAG","created_at":"2026-07-05T11:59:10Z"},{"alias_kind":"pith_short_16","alias_value":"P4XQTLMRVFAGUG4A","created_at":"2026-07-05T11:59:10Z"},{"alias_kind":"pith_short_8","alias_value":"P4XQTLMR","created_at":"2026-07-05T11:59:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:P4XQTLMRVFAGUG4AHQDJEL5CB4","target":"record","payload":{"canonical_record":{"source":{"id":"2502.08231","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-12T09:20:08Z","cross_cats_sorted":[],"title_canon_sha256":"dd33eb89d5d9d41deb6ee5e21b9af67f0010d61fdf1ded9f2f65428607424dbc","abstract_canon_sha256":"8b67a0704fbcd1c0a6f8d761d7fc12db497a2e14a593017d4462425a40b5d4bb"},"schema_version":"1.0"},"canonical_sha256":"7f2f09ad91a9406a1b803c06922fa20f234ef976e11584d9b53445c10490ded6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:10.750756Z","signature_b64":"p5DAKMgyhlfaZmyP9YoZ6U+UrEpm+T0gjwcQ/7uzEX7Lhmymlzxs1H/2bU+yF36nCwbuwqiW0924jsfEtSMtCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f2f09ad91a9406a1b803c06922fa20f234ef976e11584d9b53445c10490ded6","last_reissued_at":"2026-07-05T11:59:10.750349Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:10.750349Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.08231","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":"2026-07-05T11:59:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YIONcHbKUL2jYxUWjWZgZshHqpCxmP5GlP4+zMT8fsGVoas0DzSm8sI64gUAtxRniI6SII1Z0552g7lsUlzTDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:32:43.103190Z"},"content_sha256":"43780ab37718bb6103271e279506f6595cef028a7b7e71487fab7dee2dce756b","schema_version":"1.0","event_id":"sha256:43780ab37718bb6103271e279506f6595cef028a7b7e71487fab7dee2dce756b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:P4XQTLMRVFAGUG4AHQDJEL5CB4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Keep your distance: learning dispersed embeddings on $\\mathbb{S}_m$","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Evgeniia Tokarchuk, Hua Chang Bakker, Vlad Niculae","submitted_at":"2025-02-12T09:20:08Z","abstract_excerpt":"Learning well-separated features in high-dimensional spaces, such as text or image embeddings, is crucial for many machine learning applications. Achieving such separation can be effectively accomplished through the dispersion of embeddings, where unrelated vectors are pushed apart as much as possible. By constraining features to be on a hypersphere, we can connect dispersion to well-studied problems in mathematics and physics, where optimal solutions are known for limited low-dimensional cases. However, in representation learning we typically deal with a large number of features in high-dimen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08231","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2502.08231/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":"2026-07-05T11:59:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uMpavgesKokup0CDPB3/w+ikqAtCHCaiA6uoNqhEqM/tEWtUU3wRHo/dnoH6HNpTOWspDcUbGSFFrsO99ssgCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:32:43.104243Z"},"content_sha256":"01fa8a0a6a372f47bb8e10c91cc1435092758de2ad712d54db418426173c61cf","schema_version":"1.0","event_id":"sha256:01fa8a0a6a372f47bb8e10c91cc1435092758de2ad712d54db418426173c61cf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P4XQTLMRVFAGUG4AHQDJEL5CB4/bundle.json","state_url":"https://pith.science/pith/P4XQTLMRVFAGUG4AHQDJEL5CB4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P4XQTLMRVFAGUG4AHQDJEL5CB4/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":"2026-08-03T15:32:43Z","links":{"resolver":"https://pith.science/pith/P4XQTLMRVFAGUG4AHQDJEL5CB4","bundle":"https://pith.science/pith/P4XQTLMRVFAGUG4AHQDJEL5CB4/bundle.json","state":"https://pith.science/pith/P4XQTLMRVFAGUG4AHQDJEL5CB4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P4XQTLMRVFAGUG4AHQDJEL5CB4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:P4XQTLMRVFAGUG4AHQDJEL5CB4","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":"8b67a0704fbcd1c0a6f8d761d7fc12db497a2e14a593017d4462425a40b5d4bb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-12T09:20:08Z","title_canon_sha256":"dd33eb89d5d9d41deb6ee5e21b9af67f0010d61fdf1ded9f2f65428607424dbc"},"schema_version":"1.0","source":{"id":"2502.08231","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.08231","created_at":"2026-07-05T11:59:10Z"},{"alias_kind":"arxiv_version","alias_value":"2502.08231v4","created_at":"2026-07-05T11:59:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08231","created_at":"2026-07-05T11:59:10Z"},{"alias_kind":"pith_short_12","alias_value":"P4XQTLMRVFAG","created_at":"2026-07-05T11:59:10Z"},{"alias_kind":"pith_short_16","alias_value":"P4XQTLMRVFAGUG4A","created_at":"2026-07-05T11:59:10Z"},{"alias_kind":"pith_short_8","alias_value":"P4XQTLMR","created_at":"2026-07-05T11:59:10Z"}],"graph_snapshots":[{"event_id":"sha256:01fa8a0a6a372f47bb8e10c91cc1435092758de2ad712d54db418426173c61cf","target":"graph","created_at":"2026-07-05T11:59:10Z","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/2502.08231/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning well-separated features in high-dimensional spaces, such as text or image embeddings, is crucial for many machine learning applications. Achieving such separation can be effectively accomplished through the dispersion of embeddings, where unrelated vectors are pushed apart as much as possible. By constraining features to be on a hypersphere, we can connect dispersion to well-studied problems in mathematics and physics, where optimal solutions are known for limited low-dimensional cases. However, in representation learning we typically deal with a large number of features in high-dimen","authors_text":"Evgeniia Tokarchuk, Hua Chang Bakker, Vlad Niculae","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-12T09:20:08Z","title":"Keep your distance: learning dispersed embeddings on $\\mathbb{S}_m$"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08231","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":"sha256:43780ab37718bb6103271e279506f6595cef028a7b7e71487fab7dee2dce756b","target":"record","created_at":"2026-07-05T11:59:10Z","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":"8b67a0704fbcd1c0a6f8d761d7fc12db497a2e14a593017d4462425a40b5d4bb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-12T09:20:08Z","title_canon_sha256":"dd33eb89d5d9d41deb6ee5e21b9af67f0010d61fdf1ded9f2f65428607424dbc"},"schema_version":"1.0","source":{"id":"2502.08231","kind":"arxiv","version":4}},"canonical_sha256":"7f2f09ad91a9406a1b803c06922fa20f234ef976e11584d9b53445c10490ded6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7f2f09ad91a9406a1b803c06922fa20f234ef976e11584d9b53445c10490ded6","first_computed_at":"2026-07-05T11:59:10.750349Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:59:10.750349Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p5DAKMgyhlfaZmyP9YoZ6U+UrEpm+T0gjwcQ/7uzEX7Lhmymlzxs1H/2bU+yF36nCwbuwqiW0924jsfEtSMtCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:59:10.750756Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.08231","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:43780ab37718bb6103271e279506f6595cef028a7b7e71487fab7dee2dce756b","sha256:01fa8a0a6a372f47bb8e10c91cc1435092758de2ad712d54db418426173c61cf"],"state_sha256":"18ba975dcce7be10acd1c93254e558786b1ac0521e36a8f0902bcacea5e7d39d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oesQFFb5L2xQOjZO1NzyCoQ0WQnEbqEILnX7/kU0PczEuJL4gLqD7eTK9kpaczvRzUjtlUa7TtgeuG+IZguIDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T15:32:43.115397Z","bundle_sha256":"e7b2b73ec2423232fd1258f0acc3f04b7e154f9f046de1aa9549dd3a39db3616"}}