{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RJLFBAIJALBDHPB4QC2LOPIHEO","short_pith_number":"pith:RJLFBAIJ","schema_version":"1.0","canonical_sha256":"8a5650810902c233bc3c80b4b73d07238c971ca7e700353df2d0dc87a3fcda39","source":{"kind":"arxiv","id":"2311.18727","version":2},"attestation_state":"computed","paper":{"title":"Automatic Functional Differentiation in JAX","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.PL","authors_text":"Min Lin","submitted_at":"2023-11-30T17:23:40Z","abstract_excerpt":"We extend JAX with the capability to automatically differentiate higher-order functions (functionals and operators). By representing functions as a generalization of arrays, we seamlessly use JAX's existing primitive system to implement higher-order functions. We present a set of primitive operators that serve as foundational building blocks for constructing several key types of functionals. For every introduced primitive operator, we derive and implement both linearization and transposition rules, aligning with JAX's internal protocols for forward and reverse mode automatic differentiation. T"},"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":"2311.18727","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.PL","submitted_at":"2023-11-30T17:23:40Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"b58e33720e58ddc71c2836b61c3fe79f271be63acd901940fd22e3a4f94f6551","abstract_canon_sha256":"fe49b0d934b48500c2643cef132c0f1972648c86ade022330907fc3b2920005b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:38:32.830129Z","signature_b64":"X1RMRWaOYZG0uyUZjrxC6yRaejCHYyvms0B+lh8L02u4+6OAPWjp/tTh7ZkrDrl/o9sTX5czzebd2X++YCMYDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a5650810902c233bc3c80b4b73d07238c971ca7e700353df2d0dc87a3fcda39","last_reissued_at":"2026-07-05T07:38:32.829663Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:38:32.829663Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automatic Functional Differentiation in JAX","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.PL","authors_text":"Min Lin","submitted_at":"2023-11-30T17:23:40Z","abstract_excerpt":"We extend JAX with the capability to automatically differentiate higher-order functions (functionals and operators). By representing functions as a generalization of arrays, we seamlessly use JAX's existing primitive system to implement higher-order functions. We present a set of primitive operators that serve as foundational building blocks for constructing several key types of functionals. For every introduced primitive operator, we derive and implement both linearization and transposition rules, aligning with JAX's internal protocols for forward and reverse mode automatic differentiation. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.18727","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/2311.18727/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":"2311.18727","created_at":"2026-07-05T07:38:32.829726+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.18727v2","created_at":"2026-07-05T07:38:32.829726+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.18727","created_at":"2026-07-05T07:38:32.829726+00:00"},{"alias_kind":"pith_short_12","alias_value":"RJLFBAIJALBD","created_at":"2026-07-05T07:38:32.829726+00:00"},{"alias_kind":"pith_short_16","alias_value":"RJLFBAIJALBDHPB4","created_at":"2026-07-05T07:38:32.829726+00:00"},{"alias_kind":"pith_short_8","alias_value":"RJLFBAIJ","created_at":"2026-07-05T07:38:32.829726+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.06135","citing_title":"Shot-based quantum encoding: a data-loading paradigm for quantum neural networks","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RJLFBAIJALBDHPB4QC2LOPIHEO","json":"https://pith.science/pith/RJLFBAIJALBDHPB4QC2LOPIHEO.json","graph_json":"https://pith.science/api/pith-number/RJLFBAIJALBDHPB4QC2LOPIHEO/graph.json","events_json":"https://pith.science/api/pith-number/RJLFBAIJALBDHPB4QC2LOPIHEO/events.json","paper":"https://pith.science/paper/RJLFBAIJ"},"agent_actions":{"view_html":"https://pith.science/pith/RJLFBAIJALBDHPB4QC2LOPIHEO","download_json":"https://pith.science/pith/RJLFBAIJALBDHPB4QC2LOPIHEO.json","view_paper":"https://pith.science/paper/RJLFBAIJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.18727&json=true","fetch_graph":"https://pith.science/api/pith-number/RJLFBAIJALBDHPB4QC2LOPIHEO/graph.json","fetch_events":"https://pith.science/api/pith-number/RJLFBAIJALBDHPB4QC2LOPIHEO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RJLFBAIJALBDHPB4QC2LOPIHEO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RJLFBAIJALBDHPB4QC2LOPIHEO/action/storage_attestation","attest_author":"https://pith.science/pith/RJLFBAIJALBDHPB4QC2LOPIHEO/action/author_attestation","sign_citation":"https://pith.science/pith/RJLFBAIJALBDHPB4QC2LOPIHEO/action/citation_signature","submit_replication":"https://pith.science/pith/RJLFBAIJALBDHPB4QC2LOPIHEO/action/replication_record"}},"created_at":"2026-07-05T07:38:32.829726+00:00","updated_at":"2026-07-05T07:38:32.829726+00:00"}