{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PYMT7PNXFQROWDOVJODPACRJQR","short_pith_number":"pith:PYMT7PNX","schema_version":"1.0","canonical_sha256":"7e193fbdb72c22eb0dd54b86f00a298444aaff3872063212abf1d8382b20f02e","source":{"kind":"arxiv","id":"2607.06887","version":1},"attestation_state":"computed","paper":{"title":"Converge to Surprise: Evolutionary Self-supervised Image Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Canlin Zhang, Xiuwen Liu","submitted_at":"2026-07-08T01:09:21Z","abstract_excerpt":"Most self-supervised image clustering models, actually almost all deep learning approaches, are based on gradient descent: In order to calculate the loss, every optimization step requires a clearly defined target, whether a contrastive split, a masked patch or entity, an EMA-teacher output, a pseudo-label, or a differentiable information-theoretic functional. We propose a self-supervised framework that drops this requirement for image clustering. Without any prior knowledge, we have to assume that each pixel is i.i.d. according to the Principle of Maximum Entropy. Taking this as our null hypot"},"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":"2607.06887","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-08T01:09:21Z","cross_cats_sorted":[],"title_canon_sha256":"2b1b891ce2869e670091f0d4fe55cb97bdf0e8d54e4748dcaed967b51dcf5b2d","abstract_canon_sha256":"bc687c6ace988bce7f9816eb3bdd13a5f6a6520684d88635dbfff9aae101f050"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-09T00:19:38.653499Z","signature_b64":"41vN6IdMYh4iCpmV0b6Ke3DBEqwSf5XXE2Azk+F2AIbH0MnCPToIekmlJR0ZOJQ2DECKU3XktJfagtHcRbNoBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e193fbdb72c22eb0dd54b86f00a298444aaff3872063212abf1d8382b20f02e","last_reissued_at":"2026-07-09T00:19:38.652997Z","signature_status":"signed_v1","first_computed_at":"2026-07-09T00:19:38.652997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Converge to Surprise: Evolutionary Self-supervised Image Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Canlin Zhang, Xiuwen Liu","submitted_at":"2026-07-08T01:09:21Z","abstract_excerpt":"Most self-supervised image clustering models, actually almost all deep learning approaches, are based on gradient descent: In order to calculate the loss, every optimization step requires a clearly defined target, whether a contrastive split, a masked patch or entity, an EMA-teacher output, a pseudo-label, or a differentiable information-theoretic functional. We propose a self-supervised framework that drops this requirement for image clustering. Without any prior knowledge, we have to assume that each pixel is i.i.d. according to the Principle of Maximum Entropy. Taking this as our null hypot"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.06887","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/2607.06887/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":"2607.06887","created_at":"2026-07-09T00:19:38.653057+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.06887v1","created_at":"2026-07-09T00:19:38.653057+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.06887","created_at":"2026-07-09T00:19:38.653057+00:00"},{"alias_kind":"pith_short_12","alias_value":"PYMT7PNXFQRO","created_at":"2026-07-09T00:19:38.653057+00:00"},{"alias_kind":"pith_short_16","alias_value":"PYMT7PNXFQROWDOV","created_at":"2026-07-09T00:19:38.653057+00:00"},{"alias_kind":"pith_short_8","alias_value":"PYMT7PNX","created_at":"2026-07-09T00:19:38.653057+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/PYMT7PNXFQROWDOVJODPACRJQR","json":"https://pith.science/pith/PYMT7PNXFQROWDOVJODPACRJQR.json","graph_json":"https://pith.science/api/pith-number/PYMT7PNXFQROWDOVJODPACRJQR/graph.json","events_json":"https://pith.science/api/pith-number/PYMT7PNXFQROWDOVJODPACRJQR/events.json","paper":"https://pith.science/paper/PYMT7PNX"},"agent_actions":{"view_html":"https://pith.science/pith/PYMT7PNXFQROWDOVJODPACRJQR","download_json":"https://pith.science/pith/PYMT7PNXFQROWDOVJODPACRJQR.json","view_paper":"https://pith.science/paper/PYMT7PNX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.06887&json=true","fetch_graph":"https://pith.science/api/pith-number/PYMT7PNXFQROWDOVJODPACRJQR/graph.json","fetch_events":"https://pith.science/api/pith-number/PYMT7PNXFQROWDOVJODPACRJQR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PYMT7PNXFQROWDOVJODPACRJQR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PYMT7PNXFQROWDOVJODPACRJQR/action/storage_attestation","attest_author":"https://pith.science/pith/PYMT7PNXFQROWDOVJODPACRJQR/action/author_attestation","sign_citation":"https://pith.science/pith/PYMT7PNXFQROWDOVJODPACRJQR/action/citation_signature","submit_replication":"https://pith.science/pith/PYMT7PNXFQROWDOVJODPACRJQR/action/replication_record"}},"created_at":"2026-07-09T00:19:38.653057+00:00","updated_at":"2026-07-09T00:19:38.653057+00:00"}