{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OK7SNXVWEMTE7DLZLM7JKXXMTL","short_pith_number":"pith:OK7SNXVW","schema_version":"1.0","canonical_sha256":"72bf26deb623264f8d795b3e955eec9acc87a81a01ef0ac4d0e2e091be7ba2c0","source":{"kind":"arxiv","id":"2201.11137","version":2},"attestation_state":"computed","paper":{"title":"Born-Infeld (BI) for AI: Energy-Conserving Descent (ECD) for Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["astro-ph.CO","hep-th","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Eva Silverstein, G. Bruno De Luca","submitted_at":"2022-01-26T19:00:05Z","abstract_excerpt":"We introduce a novel framework for optimization based on energy-conserving Hamiltonian dynamics in a strongly mixing (chaotic) regime and establish its key properties analytically and numerically. The prototype is a discretization of Born-Infeld dynamics, with a squared relativistic speed limit depending on the objective function. This class of frictionless, energy-conserving optimizers proceeds unobstructed until slowing naturally near the minimal loss, which dominates the phase space volume of the system. Building from studies of chaotic systems such as dynamical billiards, we formulate a sp"},"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":"2201.11137","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-26T19:00:05Z","cross_cats_sorted":["astro-ph.CO","hep-th","math.OC","stat.ML"],"title_canon_sha256":"d7fcf9dd9da365ed68c6b5c50519412576694b4495acd419bc977a54838ad0e5","abstract_canon_sha256":"b39a95002dc1e88d72d515bfb69b5702e696e01b816974446fa7cced8d1d6731"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:09:42.045146Z","signature_b64":"MieE2M6exOUOR6NFhv9T7vbe/6iulq18DLUZ+9E+rA/C7A6Y1KVW/JXourAWQH7+v0D/hi1IPmeh6zI2yI9wAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72bf26deb623264f8d795b3e955eec9acc87a81a01ef0ac4d0e2e091be7ba2c0","last_reissued_at":"2026-07-05T06:09:42.044607Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:09:42.044607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Born-Infeld (BI) for AI: Energy-Conserving Descent (ECD) for Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["astro-ph.CO","hep-th","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Eva Silverstein, G. Bruno De Luca","submitted_at":"2022-01-26T19:00:05Z","abstract_excerpt":"We introduce a novel framework for optimization based on energy-conserving Hamiltonian dynamics in a strongly mixing (chaotic) regime and establish its key properties analytically and numerically. The prototype is a discretization of Born-Infeld dynamics, with a squared relativistic speed limit depending on the objective function. This class of frictionless, energy-conserving optimizers proceeds unobstructed until slowing naturally near the minimal loss, which dominates the phase space volume of the system. Building from studies of chaotic systems such as dynamical billiards, we formulate a sp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.11137","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/2201.11137/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":"2201.11137","created_at":"2026-07-05T06:09:42.044669+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.11137v2","created_at":"2026-07-05T06:09:42.044669+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.11137","created_at":"2026-07-05T06:09:42.044669+00:00"},{"alias_kind":"pith_short_12","alias_value":"OK7SNXVWEMTE","created_at":"2026-07-05T06:09:42.044669+00:00"},{"alias_kind":"pith_short_16","alias_value":"OK7SNXVWEMTE7DLZ","created_at":"2026-07-05T06:09:42.044669+00:00"},{"alias_kind":"pith_short_8","alias_value":"OK7SNXVW","created_at":"2026-07-05T06:09:42.044669+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20299","citing_title":"Statistical Properties of Training & Generalization","ref_index":164,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20299","citing_title":"Statistical Properties of Training & Generalization","ref_index":164,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OK7SNXVWEMTE7DLZLM7JKXXMTL","json":"https://pith.science/pith/OK7SNXVWEMTE7DLZLM7JKXXMTL.json","graph_json":"https://pith.science/api/pith-number/OK7SNXVWEMTE7DLZLM7JKXXMTL/graph.json","events_json":"https://pith.science/api/pith-number/OK7SNXVWEMTE7DLZLM7JKXXMTL/events.json","paper":"https://pith.science/paper/OK7SNXVW"},"agent_actions":{"view_html":"https://pith.science/pith/OK7SNXVWEMTE7DLZLM7JKXXMTL","download_json":"https://pith.science/pith/OK7SNXVWEMTE7DLZLM7JKXXMTL.json","view_paper":"https://pith.science/paper/OK7SNXVW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.11137&json=true","fetch_graph":"https://pith.science/api/pith-number/OK7SNXVWEMTE7DLZLM7JKXXMTL/graph.json","fetch_events":"https://pith.science/api/pith-number/OK7SNXVWEMTE7DLZLM7JKXXMTL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OK7SNXVWEMTE7DLZLM7JKXXMTL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OK7SNXVWEMTE7DLZLM7JKXXMTL/action/storage_attestation","attest_author":"https://pith.science/pith/OK7SNXVWEMTE7DLZLM7JKXXMTL/action/author_attestation","sign_citation":"https://pith.science/pith/OK7SNXVWEMTE7DLZLM7JKXXMTL/action/citation_signature","submit_replication":"https://pith.science/pith/OK7SNXVWEMTE7DLZLM7JKXXMTL/action/replication_record"}},"created_at":"2026-07-05T06:09:42.044669+00:00","updated_at":"2026-07-05T06:09:42.044669+00:00"}