{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GD443R526NTNSNV6IWAHL2FZYA","short_pith_number":"pith:GD443R52","schema_version":"1.0","canonical_sha256":"30f9cdc7baf366d936be458075e8b9c001d9b2e9e3a26be5d609178dffa77afa","source":{"kind":"arxiv","id":"2403.14606","version":3},"attestation_state":"computed","paper":{"title":"The Elements of Differentiable Programming","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.PL"],"primary_cat":"cs.LG","authors_text":"Mathieu Blondel, Vincent Roulet","submitted_at":"2024-03-21T17:55:16Z","abstract_excerpt":"Artificial intelligence has recently experienced remarkable advances, fueled by large models, vast datasets, accelerated hardware, and, last but not least, the transformative power of differentiable programming. This new programming paradigm enables end-to-end differentiation of complex computer programs (including those with control flows and data structures), making gradient-based optimization of program parameters possible. As an emerging paradigm, differentiable programming builds upon several areas of computer science and applied mathematics, including automatic differentiation, graphical"},"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":"2403.14606","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-21T17:55:16Z","cross_cats_sorted":["cs.AI","cs.PL"],"title_canon_sha256":"a608f74ed9b44fc550300f89d0439548414a2c00c4f0872aeeefe57e377b10e2","abstract_canon_sha256":"a4eb65dee4534e48bc7c42a12f3c697aedc533e29bd95cd39e65361985c0d0ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:59.307485Z","signature_b64":"fFyxkg05X2sUIect4OfFmGyvCIJfoIgCxGLokpkchZypxdzlbdmyfWp/Lxt4LEik6XH567pTLvlIdHvEp+FeDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30f9cdc7baf366d936be458075e8b9c001d9b2e9e3a26be5d609178dffa77afa","last_reissued_at":"2026-07-05T11:25:59.307053Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:59.307053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Elements of Differentiable Programming","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.PL"],"primary_cat":"cs.LG","authors_text":"Mathieu Blondel, Vincent Roulet","submitted_at":"2024-03-21T17:55:16Z","abstract_excerpt":"Artificial intelligence has recently experienced remarkable advances, fueled by large models, vast datasets, accelerated hardware, and, last but not least, the transformative power of differentiable programming. This new programming paradigm enables end-to-end differentiation of complex computer programs (including those with control flows and data structures), making gradient-based optimization of program parameters possible. As an emerging paradigm, differentiable programming builds upon several areas of computer science and applied mathematics, including automatic differentiation, graphical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.14606","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/2403.14606/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":"2403.14606","created_at":"2026-07-05T11:25:59.307106+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.14606v3","created_at":"2026-07-05T11:25:59.307106+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.14606","created_at":"2026-07-05T11:25:59.307106+00:00"},{"alias_kind":"pith_short_12","alias_value":"GD443R526NTN","created_at":"2026-07-05T11:25:59.307106+00:00"},{"alias_kind":"pith_short_16","alias_value":"GD443R526NTNSNV6","created_at":"2026-07-05T11:25:59.307106+00:00"},{"alias_kind":"pith_short_8","alias_value":"GD443R52","created_at":"2026-07-05T11:25:59.307106+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":9,"sample":[{"citing_arxiv_id":"2607.02498","citing_title":"Alleviating prior dependencies for DESI DR1 clustering fits through reparameterization","ref_index":127,"is_internal_anchor":true},{"citing_arxiv_id":"2606.07114","citing_title":"DIFFRACT: Neuralized Utility Maximization for Wireless Networks by Differentiable Programming","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2607.00141","citing_title":"AD-MPCC: Adaptive Differentiable Model Predictive Contouring Control for Autonomous Racing","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2606.06313","citing_title":"Wall Shear Stress Reconstruction from Concentration: Differentiable Physics and Physics-Informed Neural Networks","ref_index":59,"is_internal_anchor":true},{"citing_arxiv_id":"2606.06094","citing_title":"Integrating Mechanistic and Data-Driven Models for Neurological Disorders through Differentiable Programming","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2606.02294","citing_title":"Regularized Large Neighborhood Search","ref_index":58,"is_internal_anchor":true},{"citing_arxiv_id":"2511.08734","citing_title":"Hierarchical Strategic Decision-Making in Layered Mobility Systems","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2512.15605","citing_title":"Autoregressive Language Models are Secretly Energy-Based Models: Insights into the Lookahead Capabilities of Next-Token Prediction","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09307","citing_title":"Constitutive Priors for Inverse Design","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GD443R526NTNSNV6IWAHL2FZYA","json":"https://pith.science/pith/GD443R526NTNSNV6IWAHL2FZYA.json","graph_json":"https://pith.science/api/pith-number/GD443R526NTNSNV6IWAHL2FZYA/graph.json","events_json":"https://pith.science/api/pith-number/GD443R526NTNSNV6IWAHL2FZYA/events.json","paper":"https://pith.science/paper/GD443R52"},"agent_actions":{"view_html":"https://pith.science/pith/GD443R526NTNSNV6IWAHL2FZYA","download_json":"https://pith.science/pith/GD443R526NTNSNV6IWAHL2FZYA.json","view_paper":"https://pith.science/paper/GD443R52","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.14606&json=true","fetch_graph":"https://pith.science/api/pith-number/GD443R526NTNSNV6IWAHL2FZYA/graph.json","fetch_events":"https://pith.science/api/pith-number/GD443R526NTNSNV6IWAHL2FZYA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GD443R526NTNSNV6IWAHL2FZYA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GD443R526NTNSNV6IWAHL2FZYA/action/storage_attestation","attest_author":"https://pith.science/pith/GD443R526NTNSNV6IWAHL2FZYA/action/author_attestation","sign_citation":"https://pith.science/pith/GD443R526NTNSNV6IWAHL2FZYA/action/citation_signature","submit_replication":"https://pith.science/pith/GD443R526NTNSNV6IWAHL2FZYA/action/replication_record"}},"created_at":"2026-07-05T11:25:59.307106+00:00","updated_at":"2026-07-05T11:25:59.307106+00:00"}