{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VTYFA6XCPDW5RZD5PHGTS4N7CX","short_pith_number":"pith:VTYFA6XC","canonical_record":{"source":{"id":"2403.13808","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-20T17:59:58Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"73a8537f068c5815ac2143d2dc6a8b2425d0b8aa7ef99eb5530dbb20fc093468","abstract_canon_sha256":"123887ed1967420cea05b69359b4afb7bf8de4ade8776410a45f245e973e7c94"},"schema_version":"1.0"},"canonical_sha256":"acf0507ae278edd8e47d79cd3971bf15c3acf63ae8d08be8da699819f289deed","source":{"kind":"arxiv","id":"2403.13808","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.13808","created_at":"2026-07-05T08:45:26Z"},{"alias_kind":"arxiv_version","alias_value":"2403.13808v3","created_at":"2026-07-05T08:45:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.13808","created_at":"2026-07-05T08:45:26Z"},{"alias_kind":"pith_short_12","alias_value":"VTYFA6XCPDW5","created_at":"2026-07-05T08:45:26Z"},{"alias_kind":"pith_short_16","alias_value":"VTYFA6XCPDW5RZD5","created_at":"2026-07-05T08:45:26Z"},{"alias_kind":"pith_short_8","alias_value":"VTYFA6XC","created_at":"2026-07-05T08:45:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VTYFA6XCPDW5RZD5PHGTS4N7CX","target":"record","payload":{"canonical_record":{"source":{"id":"2403.13808","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-20T17:59:58Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"73a8537f068c5815ac2143d2dc6a8b2425d0b8aa7ef99eb5530dbb20fc093468","abstract_canon_sha256":"123887ed1967420cea05b69359b4afb7bf8de4ade8776410a45f245e973e7c94"},"schema_version":"1.0"},"canonical_sha256":"acf0507ae278edd8e47d79cd3971bf15c3acf63ae8d08be8da699819f289deed","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:26.514838Z","signature_b64":"RXDwK0HOWyX4gOjzhOLon2jyLbKzsYfgOEo6W60DJRA7vSt9KgEG2YWjPFxyC1bKDhhlR4nYFf8bJt33TchoDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acf0507ae278edd8e47d79cd3971bf15c3acf63ae8d08be8da699819f289deed","last_reissued_at":"2026-07-05T08:45:26.514424Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:26.514424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.13808","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:45:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TgxlGJFvtDpiuV2NIy63rUTB9eJpvfYKQzx9J8a1OawBwU22jGwS+wMrrI4a2KsvkirBvrBjgLpUuU7ZYSyFCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:41:23.867983Z"},"content_sha256":"aaddfbe786bb86250ee6ce36d360c2e251762f4ef5a1438677646ee34e9365d4","schema_version":"1.0","event_id":"sha256:aaddfbe786bb86250ee6ce36d360c2e251762f4ef5a1438677646ee34e9365d4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VTYFA6XCPDW5RZD5PHGTS4N7CX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On Pretraining Data Diversity for Self-Supervised Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Adel Bibi, Bernard Ghanem, Fabio Pizzati, Hasan Abed Al Kader Hammoud, Philip Torr, Tuhin Das","submitted_at":"2024-03-20T17:59:58Z","abstract_excerpt":"We explore the impact of training with more diverse datasets, characterized by the number of unique samples, on the performance of self-supervised learning (SSL) under a fixed computational budget. Our findings consistently demonstrate that increasing pretraining data diversity enhances SSL performance, albeit only when the distribution distance to the downstream data is minimal. Notably, even with an exceptionally large pretraining data diversity achieved through methods like web crawling or diffusion-generated data, among other ways, the distribution shift remains a challenge. Our experiment"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.13808","kind":"arxiv","version":3},"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/2403.13808/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":"2026-07-05T08:45:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qkOxKl618BktGCpmtI+ItHHgHyxTOjRi1v9wW958w8dxURkjoDxvk4UO3UJDSSyM2AyzcakEo9MaLMVU9umRDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:41:23.868484Z"},"content_sha256":"7139dc12136e07b38d4783697728c65a903d501243a5848b274bf6e40b004ecf","schema_version":"1.0","event_id":"sha256:7139dc12136e07b38d4783697728c65a903d501243a5848b274bf6e40b004ecf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VTYFA6XCPDW5RZD5PHGTS4N7CX/bundle.json","state_url":"https://pith.science/pith/VTYFA6XCPDW5RZD5PHGTS4N7CX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VTYFA6XCPDW5RZD5PHGTS4N7CX/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":"2026-08-07T22:41:23Z","links":{"resolver":"https://pith.science/pith/VTYFA6XCPDW5RZD5PHGTS4N7CX","bundle":"https://pith.science/pith/VTYFA6XCPDW5RZD5PHGTS4N7CX/bundle.json","state":"https://pith.science/pith/VTYFA6XCPDW5RZD5PHGTS4N7CX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VTYFA6XCPDW5RZD5PHGTS4N7CX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VTYFA6XCPDW5RZD5PHGTS4N7CX","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":"123887ed1967420cea05b69359b4afb7bf8de4ade8776410a45f245e973e7c94","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-20T17:59:58Z","title_canon_sha256":"73a8537f068c5815ac2143d2dc6a8b2425d0b8aa7ef99eb5530dbb20fc093468"},"schema_version":"1.0","source":{"id":"2403.13808","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.13808","created_at":"2026-07-05T08:45:26Z"},{"alias_kind":"arxiv_version","alias_value":"2403.13808v3","created_at":"2026-07-05T08:45:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.13808","created_at":"2026-07-05T08:45:26Z"},{"alias_kind":"pith_short_12","alias_value":"VTYFA6XCPDW5","created_at":"2026-07-05T08:45:26Z"},{"alias_kind":"pith_short_16","alias_value":"VTYFA6XCPDW5RZD5","created_at":"2026-07-05T08:45:26Z"},{"alias_kind":"pith_short_8","alias_value":"VTYFA6XC","created_at":"2026-07-05T08:45:26Z"}],"graph_snapshots":[{"event_id":"sha256:7139dc12136e07b38d4783697728c65a903d501243a5848b274bf6e40b004ecf","target":"graph","created_at":"2026-07-05T08:45:26Z","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/2403.13808/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We explore the impact of training with more diverse datasets, characterized by the number of unique samples, on the performance of self-supervised learning (SSL) under a fixed computational budget. Our findings consistently demonstrate that increasing pretraining data diversity enhances SSL performance, albeit only when the distribution distance to the downstream data is minimal. Notably, even with an exceptionally large pretraining data diversity achieved through methods like web crawling or diffusion-generated data, among other ways, the distribution shift remains a challenge. Our experiment","authors_text":"Adel Bibi, Bernard Ghanem, Fabio Pizzati, Hasan Abed Al Kader Hammoud, Philip Torr, Tuhin Das","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-20T17:59:58Z","title":"On Pretraining Data Diversity for Self-Supervised Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.13808","kind":"arxiv","version":3},"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:aaddfbe786bb86250ee6ce36d360c2e251762f4ef5a1438677646ee34e9365d4","target":"record","created_at":"2026-07-05T08:45:26Z","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":"123887ed1967420cea05b69359b4afb7bf8de4ade8776410a45f245e973e7c94","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-20T17:59:58Z","title_canon_sha256":"73a8537f068c5815ac2143d2dc6a8b2425d0b8aa7ef99eb5530dbb20fc093468"},"schema_version":"1.0","source":{"id":"2403.13808","kind":"arxiv","version":3}},"canonical_sha256":"acf0507ae278edd8e47d79cd3971bf15c3acf63ae8d08be8da699819f289deed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"acf0507ae278edd8e47d79cd3971bf15c3acf63ae8d08be8da699819f289deed","first_computed_at":"2026-07-05T08:45:26.514424Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:45:26.514424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RXDwK0HOWyX4gOjzhOLon2jyLbKzsYfgOEo6W60DJRA7vSt9KgEG2YWjPFxyC1bKDhhlR4nYFf8bJt33TchoDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:45:26.514838Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.13808","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aaddfbe786bb86250ee6ce36d360c2e251762f4ef5a1438677646ee34e9365d4","sha256:7139dc12136e07b38d4783697728c65a903d501243a5848b274bf6e40b004ecf"],"state_sha256":"4c19094968591a0e83d32d72caa0ee767899353d5d64f43aa4fdfb5f7b9563b6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Db1QqO6tQGlEBQduo2MI23BtXqYK1WoxPBlM731E/hithwi0NxlZDqPwVc5C/G+qZLuWyRA0Lm6Qz3U6mduSAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T22:41:23.872532Z","bundle_sha256":"5eda6679281a56180b75ae4d80d4957e72f53ec93ed410534ccd816bcefe4b2d"}}