{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5WMFE4JDSNJEGWYG4VVKMMQSSZ","short_pith_number":"pith:5WMFE4JD","schema_version":"1.0","canonical_sha256":"ed985271239352435b06e56aa63212967e48c5b8939ae321d17e3e249269d143","source":{"kind":"arxiv","id":"2512.24780","version":2},"attestation_state":"computed","paper":{"title":"Gradient Descent as Implicit EM in Distance-Based Neural Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alan Oursland","submitted_at":"2025-12-31T10:56:43Z","abstract_excerpt":"Neural networks trained with standard objectives exhibit behaviors characteristic of probabilistic inference: soft clustering, prototype specialization, and Bayesian uncertainty tracking. These phenomena appear across architectures -- in attention mechanisms, classification heads, and energy-based models -- yet existing explanations often rely on loose analogies to mixture models or post-hoc architectural interpretation. We provide a direct explanation. For any objective with log-sum-exp structure over distances or energies, the gradient with respect to each distance is exactly the negative po"},"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":"2512.24780","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-31T10:56:43Z","cross_cats_sorted":[],"title_canon_sha256":"bdf1ef1cfddbae21925419a2cb028484d4c9f7435415ef4c432c9675207d7368","abstract_canon_sha256":"797097fe89c68052ead94391e47c258defc6f081a04cb411775a0f91505c4123"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:18:32.413072Z","signature_b64":"z9RqG/3SZ9tgvm7dpNqxyP7Gk1EiB5oRGWi03AhHN4Rxjx/0zL+eIitUx05VvKCRaB20cGoAIrjNyvQgZzN4Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed985271239352435b06e56aa63212967e48c5b8939ae321d17e3e249269d143","last_reissued_at":"2026-07-07T02:18:32.412299Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:18:32.412299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gradient Descent as Implicit EM in Distance-Based Neural Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alan Oursland","submitted_at":"2025-12-31T10:56:43Z","abstract_excerpt":"Neural networks trained with standard objectives exhibit behaviors characteristic of probabilistic inference: soft clustering, prototype specialization, and Bayesian uncertainty tracking. These phenomena appear across architectures -- in attention mechanisms, classification heads, and energy-based models -- yet existing explanations often rely on loose analogies to mixture models or post-hoc architectural interpretation. We provide a direct explanation. For any objective with log-sum-exp structure over distances or energies, the gradient with respect to each distance is exactly the negative po"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.24780","kind":"arxiv","version":2},"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/2512.24780/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":"2512.24780","created_at":"2026-07-07T02:18:32.412421+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.24780v2","created_at":"2026-07-07T02:18:32.412421+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.24780","created_at":"2026-07-07T02:18:32.412421+00:00"},{"alias_kind":"pith_short_12","alias_value":"5WMFE4JDSNJE","created_at":"2026-07-07T02:18:32.412421+00:00"},{"alias_kind":"pith_short_16","alias_value":"5WMFE4JDSNJEGWYG","created_at":"2026-07-07T02:18:32.412421+00:00"},{"alias_kind":"pith_short_8","alias_value":"5WMFE4JD","created_at":"2026-07-07T02:18:32.412421+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/5WMFE4JDSNJEGWYG4VVKMMQSSZ","json":"https://pith.science/pith/5WMFE4JDSNJEGWYG4VVKMMQSSZ.json","graph_json":"https://pith.science/api/pith-number/5WMFE4JDSNJEGWYG4VVKMMQSSZ/graph.json","events_json":"https://pith.science/api/pith-number/5WMFE4JDSNJEGWYG4VVKMMQSSZ/events.json","paper":"https://pith.science/paper/5WMFE4JD"},"agent_actions":{"view_html":"https://pith.science/pith/5WMFE4JDSNJEGWYG4VVKMMQSSZ","download_json":"https://pith.science/pith/5WMFE4JDSNJEGWYG4VVKMMQSSZ.json","view_paper":"https://pith.science/paper/5WMFE4JD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.24780&json=true","fetch_graph":"https://pith.science/api/pith-number/5WMFE4JDSNJEGWYG4VVKMMQSSZ/graph.json","fetch_events":"https://pith.science/api/pith-number/5WMFE4JDSNJEGWYG4VVKMMQSSZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5WMFE4JDSNJEGWYG4VVKMMQSSZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5WMFE4JDSNJEGWYG4VVKMMQSSZ/action/storage_attestation","attest_author":"https://pith.science/pith/5WMFE4JDSNJEGWYG4VVKMMQSSZ/action/author_attestation","sign_citation":"https://pith.science/pith/5WMFE4JDSNJEGWYG4VVKMMQSSZ/action/citation_signature","submit_replication":"https://pith.science/pith/5WMFE4JDSNJEGWYG4VVKMMQSSZ/action/replication_record"}},"created_at":"2026-07-07T02:18:32.412421+00:00","updated_at":"2026-07-07T02:18:32.412421+00:00"}