{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:D7DOJLGPTAHUQTTIJ4A4UJQSAC","short_pith_number":"pith:D7DOJLGP","schema_version":"1.0","canonical_sha256":"1fc6e4accf980f484e684f01ca2612008934f3c2db7db8e45c9586fe33530653","source":{"kind":"arxiv","id":"2605.28983","version":1},"attestation_state":"computed","paper":{"title":"The Hamilton-Jacobi Theory of Deep Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","math.DS","math.RT","physics.comp-ph"],"primary_cat":"cs.LG","authors_text":"Christopher P. Monterola, Erika Fille T. Legara, Jose Marie Antonio Mi\\~noza","submitted_at":"2026-05-27T18:38:23Z","abstract_excerpt":"In this paper, training a neural network is identified, exactly, as a search through Hamilton--Jacobi initial-value problems: each gradient step selects the initial data of a viscous Hamilton--Jacobi equation whose Hopf--Cole propagator best fits the observations; at inference, the input is the spatial point at which that solution is evaluated and the initial condition is already encoded in the weights. The correspondence is exact for log-sum-exp layers and structural for broader architectures: residual networks, transformers, and recurrent architectures (RNNs, LSTMs, SSMs) each discretize the"},"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":"2605.28983","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T18:38:23Z","cross_cats_sorted":["cs.AI","math.DS","math.RT","physics.comp-ph"],"title_canon_sha256":"fc31415dd6dd8a7921ce034dd2dee536fec381177b3169726cd3298c8a965a45","abstract_canon_sha256":"ee7be0c8198cf9f7926dc1ec1f4736a1b1f0c667e90fb1bc15aa2e588564c784"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:04:42.389952Z","signature_b64":"fq8DmNqEiPP7G8oVvrue6WaQgXNuoGRptqoePu5xNTAFvpOUIH7gk7a9w/5GzGc5cuZrxBjk3FCaMy2cQzm+Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1fc6e4accf980f484e684f01ca2612008934f3c2db7db8e45c9586fe33530653","last_reissued_at":"2026-05-29T01:04:42.389489Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:04:42.389489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Hamilton-Jacobi Theory of Deep Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","math.DS","math.RT","physics.comp-ph"],"primary_cat":"cs.LG","authors_text":"Christopher P. Monterola, Erika Fille T. Legara, Jose Marie Antonio Mi\\~noza","submitted_at":"2026-05-27T18:38:23Z","abstract_excerpt":"In this paper, training a neural network is identified, exactly, as a search through Hamilton--Jacobi initial-value problems: each gradient step selects the initial data of a viscous Hamilton--Jacobi equation whose Hopf--Cole propagator best fits the observations; at inference, the input is the spatial point at which that solution is evaluated and the initial condition is already encoded in the weights. The correspondence is exact for log-sum-exp layers and structural for broader architectures: residual networks, transformers, and recurrent architectures (RNNs, LSTMs, SSMs) each discretize the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28983","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/2605.28983/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":"2605.28983","created_at":"2026-05-29T01:04:42.389562+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28983v1","created_at":"2026-05-29T01:04:42.389562+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28983","created_at":"2026-05-29T01:04:42.389562+00:00"},{"alias_kind":"pith_short_12","alias_value":"D7DOJLGPTAHU","created_at":"2026-05-29T01:04:42.389562+00:00"},{"alias_kind":"pith_short_16","alias_value":"D7DOJLGPTAHUQTTI","created_at":"2026-05-29T01:04:42.389562+00:00"},{"alias_kind":"pith_short_8","alias_value":"D7DOJLGP","created_at":"2026-05-29T01:04:42.389562+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/D7DOJLGPTAHUQTTIJ4A4UJQSAC","json":"https://pith.science/pith/D7DOJLGPTAHUQTTIJ4A4UJQSAC.json","graph_json":"https://pith.science/api/pith-number/D7DOJLGPTAHUQTTIJ4A4UJQSAC/graph.json","events_json":"https://pith.science/api/pith-number/D7DOJLGPTAHUQTTIJ4A4UJQSAC/events.json","paper":"https://pith.science/paper/D7DOJLGP"},"agent_actions":{"view_html":"https://pith.science/pith/D7DOJLGPTAHUQTTIJ4A4UJQSAC","download_json":"https://pith.science/pith/D7DOJLGPTAHUQTTIJ4A4UJQSAC.json","view_paper":"https://pith.science/paper/D7DOJLGP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28983&json=true","fetch_graph":"https://pith.science/api/pith-number/D7DOJLGPTAHUQTTIJ4A4UJQSAC/graph.json","fetch_events":"https://pith.science/api/pith-number/D7DOJLGPTAHUQTTIJ4A4UJQSAC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D7DOJLGPTAHUQTTIJ4A4UJQSAC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D7DOJLGPTAHUQTTIJ4A4UJQSAC/action/storage_attestation","attest_author":"https://pith.science/pith/D7DOJLGPTAHUQTTIJ4A4UJQSAC/action/author_attestation","sign_citation":"https://pith.science/pith/D7DOJLGPTAHUQTTIJ4A4UJQSAC/action/citation_signature","submit_replication":"https://pith.science/pith/D7DOJLGPTAHUQTTIJ4A4UJQSAC/action/replication_record"}},"created_at":"2026-05-29T01:04:42.389562+00:00","updated_at":"2026-05-29T01:04:42.389562+00:00"}