{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OKTPD3VLXOU2DWL5ZZSKD2GHRQ","short_pith_number":"pith:OKTPD3VL","schema_version":"1.0","canonical_sha256":"72a6f1eeabbba9a1d97dce64a1e8c78c247fe96e985799b43a2a0584beb47567","source":{"kind":"arxiv","id":"2606.09718","version":1},"attestation_state":"computed","paper":{"title":"Evaluating the Representation Space of Diffusion Models via Self-Supervised Principles","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Jinxin Zhou, Lianghe Shi, Liyue Shen, Qing Qu, Xiang Li, Xiao Li, Yixuan Jia, Zekai Zhang, Zhihui Zhu","submitted_at":"2026-06-08T16:44:18Z","abstract_excerpt":"Diffusion models have demonstrated remarkable generative capabilities and have also emerged as powerful self-supervised representation learners, yet the connection between these two abilities remains less explored. Drawing inspiration from self-supervised learning (SSL), we introduce a framework for jointly evaluating the representation and generation capabilities of diffusion models. Specifically, we decompose features into invariant and residual components and derive the Invariant Contamination Ratio (ICR), a Fisher-based metric that quantifies how residual variation contaminates invariant s"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.09718","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T16:44:18Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"fd89479c657a2e7b3bcacfc3e4f363bfb7a701a42fa43cef9b8f59d6ceb8b5e7","abstract_canon_sha256":"f18bfafa61929d86b2583ad98a9fe514120aaa4a556bbaa30a8ceadb09931630"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:09:05.551748Z","signature_b64":"9tHsm/hI9um1GoJ3da5kMzH8Kg1yXpwWK7o/UeH2P1xT8gi3XphBWKJNqkLMFbGF/c3vA6kCrP71ujzVzBRcDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72a6f1eeabbba9a1d97dce64a1e8c78c247fe96e985799b43a2a0584beb47567","last_reissued_at":"2026-06-09T02:09:05.550836Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:09:05.550836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating the Representation Space of Diffusion Models via Self-Supervised Principles","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Jinxin Zhou, Lianghe Shi, Liyue Shen, Qing Qu, Xiang Li, Xiao Li, Yixuan Jia, Zekai Zhang, Zhihui Zhu","submitted_at":"2026-06-08T16:44:18Z","abstract_excerpt":"Diffusion models have demonstrated remarkable generative capabilities and have also emerged as powerful self-supervised representation learners, yet the connection between these two abilities remains less explored. Drawing inspiration from self-supervised learning (SSL), we introduce a framework for jointly evaluating the representation and generation capabilities of diffusion models. Specifically, we decompose features into invariant and residual components and derive the Invariant Contamination Ratio (ICR), a Fisher-based metric that quantifies how residual variation contaminates invariant s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09718","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/2606.09718/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.09718","created_at":"2026-06-09T02:09:05.550967+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09718v1","created_at":"2026-06-09T02:09:05.550967+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09718","created_at":"2026-06-09T02:09:05.550967+00:00"},{"alias_kind":"pith_short_12","alias_value":"OKTPD3VLXOU2","created_at":"2026-06-09T02:09:05.550967+00:00"},{"alias_kind":"pith_short_16","alias_value":"OKTPD3VLXOU2DWL5","created_at":"2026-06-09T02:09:05.550967+00:00"},{"alias_kind":"pith_short_8","alias_value":"OKTPD3VL","created_at":"2026-06-09T02:09:05.550967+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OKTPD3VLXOU2DWL5ZZSKD2GHRQ","json":"https://pith.science/pith/OKTPD3VLXOU2DWL5ZZSKD2GHRQ.json","graph_json":"https://pith.science/api/pith-number/OKTPD3VLXOU2DWL5ZZSKD2GHRQ/graph.json","events_json":"https://pith.science/api/pith-number/OKTPD3VLXOU2DWL5ZZSKD2GHRQ/events.json","paper":"https://pith.science/paper/OKTPD3VL"},"agent_actions":{"view_html":"https://pith.science/pith/OKTPD3VLXOU2DWL5ZZSKD2GHRQ","download_json":"https://pith.science/pith/OKTPD3VLXOU2DWL5ZZSKD2GHRQ.json","view_paper":"https://pith.science/paper/OKTPD3VL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09718&json=true","fetch_graph":"https://pith.science/api/pith-number/OKTPD3VLXOU2DWL5ZZSKD2GHRQ/graph.json","fetch_events":"https://pith.science/api/pith-number/OKTPD3VLXOU2DWL5ZZSKD2GHRQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OKTPD3VLXOU2DWL5ZZSKD2GHRQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OKTPD3VLXOU2DWL5ZZSKD2GHRQ/action/storage_attestation","attest_author":"https://pith.science/pith/OKTPD3VLXOU2DWL5ZZSKD2GHRQ/action/author_attestation","sign_citation":"https://pith.science/pith/OKTPD3VLXOU2DWL5ZZSKD2GHRQ/action/citation_signature","submit_replication":"https://pith.science/pith/OKTPD3VLXOU2DWL5ZZSKD2GHRQ/action/replication_record"}},"created_at":"2026-06-09T02:09:05.550967+00:00","updated_at":"2026-06-09T02:09:05.550967+00:00"}