{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:75ARSMLEIPA5N2TTRGROR4HIRE","short_pith_number":"pith:75ARSMLE","canonical_record":{"source":{"id":"2605.03517","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-05T08:53:00Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"22e38605503f4afc6f2631c9c4851a56388e9d647616cd20ef2234670bf7595d","abstract_canon_sha256":"a7ce7975143800a7b5b8c6c81fc1a0663a8ffce46868a898538ad651689c5e33"},"schema_version":"1.0"},"canonical_sha256":"ff4119316443c1d6ea7389a2e8f0e889210b655147fbe85974e0bbcd6fd76fb2","source":{"kind":"arxiv","id":"2605.03517","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.03517","created_at":"2026-05-20T00:05:45Z"},{"alias_kind":"arxiv_version","alias_value":"2605.03517v2","created_at":"2026-05-20T00:05:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.03517","created_at":"2026-05-20T00:05:45Z"},{"alias_kind":"pith_short_12","alias_value":"75ARSMLEIPA5","created_at":"2026-05-20T00:05:45Z"},{"alias_kind":"pith_short_16","alias_value":"75ARSMLEIPA5N2TT","created_at":"2026-05-20T00:05:45Z"},{"alias_kind":"pith_short_8","alias_value":"75ARSMLE","created_at":"2026-05-20T00:05:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:75ARSMLEIPA5N2TTRGROR4HIRE","target":"record","payload":{"canonical_record":{"source":{"id":"2605.03517","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-05T08:53:00Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"22e38605503f4afc6f2631c9c4851a56388e9d647616cd20ef2234670bf7595d","abstract_canon_sha256":"a7ce7975143800a7b5b8c6c81fc1a0663a8ffce46868a898538ad651689c5e33"},"schema_version":"1.0"},"canonical_sha256":"ff4119316443c1d6ea7389a2e8f0e889210b655147fbe85974e0bbcd6fd76fb2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:45.908400Z","signature_b64":"jJvHd+YlVBJjpgYxQGCvPYtIDeiL2Uv6P13rGpQ9E4tUEA5MfSAvVk6g+7iJH1MItw+ezoOzuBVYjEQyL3CtAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff4119316443c1d6ea7389a2e8f0e889210b655147fbe85974e0bbcd6fd76fb2","last_reissued_at":"2026-05-20T00:05:45.907367Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:45.907367Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.03517","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":"2026-05-20T00:05:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"smPiG9xMTfwiVG1w4BjaAjDj2yRP554n2eo1ZofbojCuploOTnnTRDOlPj+dOyrzDpKTEqdPjkIY2kWrz1XUCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T20:27:24.836118Z"},"content_sha256":"21279b75d89449ddce037034dce4b9cdddac430e8ef1dcb11296112a5dba91f7","schema_version":"1.0","event_id":"sha256:21279b75d89449ddce037034dce4b9cdddac430e8ef1dcb11296112a5dba91f7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:75ARSMLEIPA5N2TTRGROR4HIRE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Understanding Self-Supervised Learning via Latent Distribution Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Self-supervised learning works by matching representations to an assumed latent model while maximizing their entropy to avoid collapse.","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Fabian A Mikulasch, Friedemann Zenke","submitted_at":"2026-05-05T08:53:00Z","abstract_excerpt":"Self-supervised learning (SSL) excels at finding general-purpose latent representations from complex data, yet lacks a unifying theoretical framework that explains the diverse existing methods and guides the design of new ones. We cast SSL as latent distribution matching (LDM): learning representations that maximize their log-probability under an assumed latent model (alignment), while maximizing latent entropy to prevent collapse (uniformity). This view unifies independent component analysis with contrastive, non-contrastive, and predictive SSL methods, including stop gradient approaches. Lev"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We cast SSL as latent distribution matching (LDM): learning representations that maximize their log-probability under an assumed latent model (alignment), while maximizing latent entropy to prevent collapse (uniformity). This view unifies independent component analysis with contrastive, non-contrastive, and predictive SSL methods... We further prove that predictive LDM yields identifiable latent representations under mild assumptions, even with nonlinear predictors.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The existence and suitability of an 'assumed latent model' whose log-probability can be maximized, plus the 'mild assumptions' required for the identifiability proof; without the full derivations it is unclear how restrictive these are or whether they are satisfied by standard SSL objectives.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Self-supervised learning is cast as latent distribution matching that aligns representations to a model while enforcing uniformity, unifying multiple SSL families and proving identifiability for predictive variants even with nonlinear predictors.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Self-supervised learning works by matching representations to an assumed latent model while maximizing their entropy to avoid collapse.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"8fe166fd534e11c99720fd0706c74064776e466c19b0884a8817d5b9a30556c6"},"source":{"id":"2605.03517","kind":"arxiv","version":2},"verdict":{"id":"d023f27d-c001-4bf8-99d5-ca81ec816512","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-07T17:02:00.033134Z","strongest_claim":"We cast SSL as latent distribution matching (LDM): learning representations that maximize their log-probability under an assumed latent model (alignment), while maximizing latent entropy to prevent collapse (uniformity). This view unifies independent component analysis with contrastive, non-contrastive, and predictive SSL methods... We further prove that predictive LDM yields identifiable latent representations under mild assumptions, even with nonlinear predictors.","one_line_summary":"Self-supervised learning is cast as latent distribution matching that aligns representations to a model while enforcing uniformity, unifying multiple SSL families and proving identifiability for predictive variants even with nonlinear predictors.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The existence and suitability of an 'assumed latent model' whose log-probability can be maximized, plus the 'mild assumptions' required for the identifiability proof; without the full derivations it is unclear how restrictive these are or whether they are satisfied by standard SSL objectives.","pith_extraction_headline":"Self-supervised learning works by matching representations to an assumed latent model while maximizing their entropy to avoid collapse."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.03517/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_compliance","ran_at":"2026-05-19T15:17:23.808536Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"5fb48a1f1cf553c13e95a29491e3e38f9c40780c37e7e09d9fdac09dfdb1f713"},"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":"d023f27d-c001-4bf8-99d5-ca81ec816512"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:05:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7Ii9kDgMYfiYlq4AAY4wVuPfxlRH4D+wXmLTSrPvHvwu1yuLfW8Ea+IZ1HC/0c0FmuK/b0l3+5uib/wwQzQUCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T20:27:24.836672Z"},"content_sha256":"cb77841c73c5f99081a1e46459218e31daf412c9e0cf43e77fac88ea29e0984f","schema_version":"1.0","event_id":"sha256:cb77841c73c5f99081a1e46459218e31daf412c9e0cf43e77fac88ea29e0984f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/75ARSMLEIPA5N2TTRGROR4HIRE/bundle.json","state_url":"https://pith.science/pith/75ARSMLEIPA5N2TTRGROR4HIRE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/75ARSMLEIPA5N2TTRGROR4HIRE/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":"2026-06-04T20:27:24Z","links":{"resolver":"https://pith.science/pith/75ARSMLEIPA5N2TTRGROR4HIRE","bundle":"https://pith.science/pith/75ARSMLEIPA5N2TTRGROR4HIRE/bundle.json","state":"https://pith.science/pith/75ARSMLEIPA5N2TTRGROR4HIRE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/75ARSMLEIPA5N2TTRGROR4HIRE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:75ARSMLEIPA5N2TTRGROR4HIRE","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":"a7ce7975143800a7b5b8c6c81fc1a0663a8ffce46868a898538ad651689c5e33","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-05T08:53:00Z","title_canon_sha256":"22e38605503f4afc6f2631c9c4851a56388e9d647616cd20ef2234670bf7595d"},"schema_version":"1.0","source":{"id":"2605.03517","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.03517","created_at":"2026-05-20T00:05:45Z"},{"alias_kind":"arxiv_version","alias_value":"2605.03517v2","created_at":"2026-05-20T00:05:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.03517","created_at":"2026-05-20T00:05:45Z"},{"alias_kind":"pith_short_12","alias_value":"75ARSMLEIPA5","created_at":"2026-05-20T00:05:45Z"},{"alias_kind":"pith_short_16","alias_value":"75ARSMLEIPA5N2TT","created_at":"2026-05-20T00:05:45Z"},{"alias_kind":"pith_short_8","alias_value":"75ARSMLE","created_at":"2026-05-20T00:05:45Z"}],"graph_snapshots":[{"event_id":"sha256:cb77841c73c5f99081a1e46459218e31daf412c9e0cf43e77fac88ea29e0984f","target":"graph","created_at":"2026-05-20T00:05:45Z","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":"We cast SSL as latent distribution matching (LDM): learning representations that maximize their log-probability under an assumed latent model (alignment), while maximizing latent entropy to prevent collapse (uniformity). This view unifies independent component analysis with contrastive, non-contrastive, and predictive SSL methods... We further prove that predictive LDM yields identifiable latent representations under mild assumptions, even with nonlinear predictors."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The existence and suitability of an 'assumed latent model' whose log-probability can be maximized, plus the 'mild assumptions' required for the identifiability proof; without the full derivations it is unclear how restrictive these are or whether they are satisfied by standard SSL objectives."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Self-supervised learning is cast as latent distribution matching that aligns representations to a model while enforcing uniformity, unifying multiple SSL families and proving identifiability for predictive variants even with nonlinear predictors."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Self-supervised learning works by matching representations to an assumed latent model while maximizing their entropy to avoid collapse."}],"snapshot_sha256":"8fe166fd534e11c99720fd0706c74064776e466c19b0884a8817d5b9a30556c6"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T15:17:23.808536Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.03517/integrity.json","findings":[],"snapshot_sha256":"5fb48a1f1cf553c13e95a29491e3e38f9c40780c37e7e09d9fdac09dfdb1f713","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-supervised learning (SSL) excels at finding general-purpose latent representations from complex data, yet lacks a unifying theoretical framework that explains the diverse existing methods and guides the design of new ones. We cast SSL as latent distribution matching (LDM): learning representations that maximize their log-probability under an assumed latent model (alignment), while maximizing latent entropy to prevent collapse (uniformity). This view unifies independent component analysis with contrastive, non-contrastive, and predictive SSL methods, including stop gradient approaches. Lev","authors_text":"Fabian A Mikulasch, Friedemann Zenke","cross_cats":["stat.ML"],"headline":"Self-supervised learning works by matching representations to an assumed latent model while maximizing their entropy to avoid collapse.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-05T08:53:00Z","title":"Understanding Self-Supervised Learning via Latent Distribution Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.03517","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-07T17:02:00.033134Z","id":"d023f27d-c001-4bf8-99d5-ca81ec816512","model_set":{"reader":"grok-4.3"},"one_line_summary":"Self-supervised learning is cast as latent distribution matching that aligns representations to a model while enforcing uniformity, unifying multiple SSL families and proving identifiability for predictive variants even with nonlinear predictors.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Self-supervised learning works by matching representations to an assumed latent model while maximizing their entropy to avoid collapse.","strongest_claim":"We cast SSL as latent distribution matching (LDM): learning representations that maximize their log-probability under an assumed latent model (alignment), while maximizing latent entropy to prevent collapse (uniformity). This view unifies independent component analysis with contrastive, non-contrastive, and predictive SSL methods... We further prove that predictive LDM yields identifiable latent representations under mild assumptions, even with nonlinear predictors.","weakest_assumption":"The existence and suitability of an 'assumed latent model' whose log-probability can be maximized, plus the 'mild assumptions' required for the identifiability proof; without the full derivations it is unclear how restrictive these are or whether they are satisfied by standard SSL objectives."}},"verdict_id":"d023f27d-c001-4bf8-99d5-ca81ec816512"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:21279b75d89449ddce037034dce4b9cdddac430e8ef1dcb11296112a5dba91f7","target":"record","created_at":"2026-05-20T00:05:45Z","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":"a7ce7975143800a7b5b8c6c81fc1a0663a8ffce46868a898538ad651689c5e33","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-05T08:53:00Z","title_canon_sha256":"22e38605503f4afc6f2631c9c4851a56388e9d647616cd20ef2234670bf7595d"},"schema_version":"1.0","source":{"id":"2605.03517","kind":"arxiv","version":2}},"canonical_sha256":"ff4119316443c1d6ea7389a2e8f0e889210b655147fbe85974e0bbcd6fd76fb2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff4119316443c1d6ea7389a2e8f0e889210b655147fbe85974e0bbcd6fd76fb2","first_computed_at":"2026-05-20T00:05:45.907367Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:05:45.907367Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jJvHd+YlVBJjpgYxQGCvPYtIDeiL2Uv6P13rGpQ9E4tUEA5MfSAvVk6g+7iJH1MItw+ezoOzuBVYjEQyL3CtAw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:05:45.908400Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.03517","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:21279b75d89449ddce037034dce4b9cdddac430e8ef1dcb11296112a5dba91f7","sha256:cb77841c73c5f99081a1e46459218e31daf412c9e0cf43e77fac88ea29e0984f"],"state_sha256":"c02a7d273337c111ea1e10d0b5b53cb7682d52104d82033f495c67e1420a8f98"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jf/6K1tL3GMmfA8H2/Ju0Lz0dB5H+lsl8pYHr5ndFXlDOvnXkWYFCeWcylrFhvHUcO9+FnZwisszMYLPfLJcBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T20:27:24.841532Z","bundle_sha256":"a0cef83a072a0a3f8299d9656254bcd073c39dbba0ecd55886161dc26194cce5"}}