{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RDEGSIAT42WLSMORMHD5LI5O7G","short_pith_number":"pith:RDEGSIAT","schema_version":"1.0","canonical_sha256":"88c8692013e6acb931d161c7d5a3aef9808ac5f73db91a2f2510d7ab921255c3","source":{"kind":"arxiv","id":"2407.14504","version":3},"attestation_state":"computed","paper":{"title":"Physical Data Embedding for Memory Efficient AI","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bahram Jalali, Callen MacPhee, Yiming Zhou","submitted_at":"2024-07-19T17:58:00Z","abstract_excerpt":"Deep neural networks (DNNs) have achieved exceptional performance across various fields by learning complex, nonlinear mappings from large-scale datasets. However, they face challenges such as high memory requirements and computational costs with limited interpretability. This paper introduces an approach where master equations of physics are converted into multilayered networks that are trained via backpropagation. The resulting general-purpose model effectively encodes data in the properties of the underlying physical system. In contrast to existing methods wherein a trained neural network i"},"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":"2407.14504","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-19T17:58:00Z","cross_cats_sorted":[],"title_canon_sha256":"c129b3051ce10db164f55869d84f867712fa39220de0d1a4eb3948ba90ea4792","abstract_canon_sha256":"14048f5e0e09dad4bfa13195f2fd4cc13366a6f4be1927640000f8b76bc02b8e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:42.972266Z","signature_b64":"T5d9Bu/AtnhORHE9uZDAfAdiwjaqWKmuMvxZX9Pg5vOmPqk0/xy0soAI6dTZPwfNroM+9+qOvivXP0wfy5YDBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88c8692013e6acb931d161c7d5a3aef9808ac5f73db91a2f2510d7ab921255c3","last_reissued_at":"2026-07-05T10:50:42.971751Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:42.971751Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Physical Data Embedding for Memory Efficient AI","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bahram Jalali, Callen MacPhee, Yiming Zhou","submitted_at":"2024-07-19T17:58:00Z","abstract_excerpt":"Deep neural networks (DNNs) have achieved exceptional performance across various fields by learning complex, nonlinear mappings from large-scale datasets. However, they face challenges such as high memory requirements and computational costs with limited interpretability. This paper introduces an approach where master equations of physics are converted into multilayered networks that are trained via backpropagation. The resulting general-purpose model effectively encodes data in the properties of the underlying physical system. In contrast to existing methods wherein a trained neural network i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.14504","kind":"arxiv","version":3},"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/2407.14504/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":"2407.14504","created_at":"2026-07-05T10:50:42.971809+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.14504v3","created_at":"2026-07-05T10:50:42.971809+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.14504","created_at":"2026-07-05T10:50:42.971809+00:00"},{"alias_kind":"pith_short_12","alias_value":"RDEGSIAT42WL","created_at":"2026-07-05T10:50:42.971809+00:00"},{"alias_kind":"pith_short_16","alias_value":"RDEGSIAT42WLSMOR","created_at":"2026-07-05T10:50:42.971809+00:00"},{"alias_kind":"pith_short_8","alias_value":"RDEGSIAT","created_at":"2026-07-05T10:50:42.971809+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/RDEGSIAT42WLSMORMHD5LI5O7G","json":"https://pith.science/pith/RDEGSIAT42WLSMORMHD5LI5O7G.json","graph_json":"https://pith.science/api/pith-number/RDEGSIAT42WLSMORMHD5LI5O7G/graph.json","events_json":"https://pith.science/api/pith-number/RDEGSIAT42WLSMORMHD5LI5O7G/events.json","paper":"https://pith.science/paper/RDEGSIAT"},"agent_actions":{"view_html":"https://pith.science/pith/RDEGSIAT42WLSMORMHD5LI5O7G","download_json":"https://pith.science/pith/RDEGSIAT42WLSMORMHD5LI5O7G.json","view_paper":"https://pith.science/paper/RDEGSIAT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.14504&json=true","fetch_graph":"https://pith.science/api/pith-number/RDEGSIAT42WLSMORMHD5LI5O7G/graph.json","fetch_events":"https://pith.science/api/pith-number/RDEGSIAT42WLSMORMHD5LI5O7G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RDEGSIAT42WLSMORMHD5LI5O7G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RDEGSIAT42WLSMORMHD5LI5O7G/action/storage_attestation","attest_author":"https://pith.science/pith/RDEGSIAT42WLSMORMHD5LI5O7G/action/author_attestation","sign_citation":"https://pith.science/pith/RDEGSIAT42WLSMORMHD5LI5O7G/action/citation_signature","submit_replication":"https://pith.science/pith/RDEGSIAT42WLSMORMHD5LI5O7G/action/replication_record"}},"created_at":"2026-07-05T10:50:42.971809+00:00","updated_at":"2026-07-05T10:50:42.971809+00:00"}