{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UNIRQA77ZH2EPXQBUO2OX4S5JV","short_pith_number":"pith:UNIRQA77","schema_version":"1.0","canonical_sha256":"a3511803ffc9f447de01a3b4ebf25d4d5bb0893d9d567c1bf7267dc4fffeb441","source":{"kind":"arxiv","id":"2606.06624","version":1},"attestation_state":"computed","paper":{"title":"Principles and Practice of Deep Representation Learning: or a Mathematical Theory of Memory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Druv Pai, Peng Wang, San Buchanan, Yi Ma","submitted_at":"2026-06-04T18:21:03Z","abstract_excerpt":"In the current era of deep learning and especially generative models, there is significant investment in training very large generative models. Thus far, such models have been \"black boxes\" that are difficult to understand in the sense that they have opaque internal mechanisms, leading to difficulties in interpretability, reliability, and control. Naturally, this lack of understanding has led to both hype and fear.\n  This book is an attempt to \"open the black box\" and understand the mechanisms of large deep networks, through the perspective of representation learning, which is a major factor -"},"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":"2606.06624","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T18:21:03Z","cross_cats_sorted":[],"title_canon_sha256":"286cd08d079be630a7973d9543e15b6f26b5cd9757428194cae51756765fa612","abstract_canon_sha256":"fe87ce896eb90ddf7aa6a3e9ed234a96d531f715e839198c6ac8ee5e43dbf548"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:04:19.617987Z","signature_b64":"NtNWEw5zhEdpllj0JjVoJPN59R+ulCZEashv851tolL3otg8N5DFqfxlojQJoAwvO39uf5YXQtvzMnqSepQmCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3511803ffc9f447de01a3b4ebf25d4d5bb0893d9d567c1bf7267dc4fffeb441","last_reissued_at":"2026-06-08T01:04:19.617279Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:04:19.617279Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Principles and Practice of Deep Representation Learning: or a Mathematical Theory of Memory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Druv Pai, Peng Wang, San Buchanan, Yi Ma","submitted_at":"2026-06-04T18:21:03Z","abstract_excerpt":"In the current era of deep learning and especially generative models, there is significant investment in training very large generative models. Thus far, such models have been \"black boxes\" that are difficult to understand in the sense that they have opaque internal mechanisms, leading to difficulties in interpretability, reliability, and control. Naturally, this lack of understanding has led to both hype and fear.\n  This book is an attempt to \"open the black box\" and understand the mechanisms of large deep networks, through the perspective of representation learning, which is a major factor -"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06624","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/2606.06624/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":"2606.06624","created_at":"2026-06-08T01:04:19.617383+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.06624v1","created_at":"2026-06-08T01:04:19.617383+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06624","created_at":"2026-06-08T01:04:19.617383+00:00"},{"alias_kind":"pith_short_12","alias_value":"UNIRQA77ZH2E","created_at":"2026-06-08T01:04:19.617383+00:00"},{"alias_kind":"pith_short_16","alias_value":"UNIRQA77ZH2EPXQB","created_at":"2026-06-08T01:04:19.617383+00:00"},{"alias_kind":"pith_short_8","alias_value":"UNIRQA77","created_at":"2026-06-08T01:04:19.617383+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/UNIRQA77ZH2EPXQBUO2OX4S5JV","json":"https://pith.science/pith/UNIRQA77ZH2EPXQBUO2OX4S5JV.json","graph_json":"https://pith.science/api/pith-number/UNIRQA77ZH2EPXQBUO2OX4S5JV/graph.json","events_json":"https://pith.science/api/pith-number/UNIRQA77ZH2EPXQBUO2OX4S5JV/events.json","paper":"https://pith.science/paper/UNIRQA77"},"agent_actions":{"view_html":"https://pith.science/pith/UNIRQA77ZH2EPXQBUO2OX4S5JV","download_json":"https://pith.science/pith/UNIRQA77ZH2EPXQBUO2OX4S5JV.json","view_paper":"https://pith.science/paper/UNIRQA77","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.06624&json=true","fetch_graph":"https://pith.science/api/pith-number/UNIRQA77ZH2EPXQBUO2OX4S5JV/graph.json","fetch_events":"https://pith.science/api/pith-number/UNIRQA77ZH2EPXQBUO2OX4S5JV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UNIRQA77ZH2EPXQBUO2OX4S5JV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UNIRQA77ZH2EPXQBUO2OX4S5JV/action/storage_attestation","attest_author":"https://pith.science/pith/UNIRQA77ZH2EPXQBUO2OX4S5JV/action/author_attestation","sign_citation":"https://pith.science/pith/UNIRQA77ZH2EPXQBUO2OX4S5JV/action/citation_signature","submit_replication":"https://pith.science/pith/UNIRQA77ZH2EPXQBUO2OX4S5JV/action/replication_record"}},"created_at":"2026-06-08T01:04:19.617383+00:00","updated_at":"2026-06-08T01:04:19.617383+00:00"}