{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:SMXKV6AYB5FAJ4BXXVA7SOAEUE","short_pith_number":"pith:SMXKV6AY","schema_version":"1.0","canonical_sha256":"932eaaf8180f4a04f037bd41f93804a100aa55b045c322eacf3aac13d6ede1fb","source":{"kind":"arxiv","id":"1802.03676","version":2},"attestation_state":"computed","paper":{"title":"Differentiable Dynamic Programming for Structured Prediction and Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Arthur Mensch, Mathieu Blondel","submitted_at":"2018-02-11T01:36:06Z","abstract_excerpt":"Dynamic programming (DP) solves a variety of structured combinatorial problems by iteratively breaking them down into smaller subproblems. In spite of their versatility, DP algorithms are usually non-differentiable, which hampers their use as a layer in neural networks trained by backpropagation. To address this issue, we propose to smooth the max operator in the dynamic programming recursion, using a strongly convex regularizer. This allows to relax both the optimal value and solution of the original combinatorial problem, and turns a broad class of DP algorithms into differentiable operators"},"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":"1802.03676","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-11T01:36:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"912430c594170a6d2a01d282a84aaef062860ba99b7c1a66f0aab7fffbd9803f","abstract_canon_sha256":"2ac0e80921cf16cf71cf631dec8f99478c5f6d07f978cd8566c9e97782ed29e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:54.455768Z","signature_b64":"qExHx4ALERM97wJr4hQdi7ye4Yr9s/pqL7wkRN0wsK/HJldSES/s0L/vjeDKNAA3to4WZ80PTIC1oEE1HOIhBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"932eaaf8180f4a04f037bd41f93804a100aa55b045c322eacf3aac13d6ede1fb","last_reissued_at":"2026-05-18T00:22:54.455355Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:54.455355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Differentiable Dynamic Programming for Structured Prediction and Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Arthur Mensch, Mathieu Blondel","submitted_at":"2018-02-11T01:36:06Z","abstract_excerpt":"Dynamic programming (DP) solves a variety of structured combinatorial problems by iteratively breaking them down into smaller subproblems. In spite of their versatility, DP algorithms are usually non-differentiable, which hampers their use as a layer in neural networks trained by backpropagation. To address this issue, we propose to smooth the max operator in the dynamic programming recursion, using a strongly convex regularizer. This allows to relax both the optimal value and solution of the original combinatorial problem, and turns a broad class of DP algorithms into differentiable operators"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.03676","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":""},"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":"1802.03676","created_at":"2026-05-18T00:22:54.455413+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.03676v2","created_at":"2026-05-18T00:22:54.455413+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.03676","created_at":"2026-05-18T00:22:54.455413+00:00"},{"alias_kind":"pith_short_12","alias_value":"SMXKV6AYB5FA","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"SMXKV6AYB5FAJ4BX","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"SMXKV6AY","created_at":"2026-05-18T12:32:53.628368+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.02294","citing_title":"Regularized Large Neighborhood Search","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SMXKV6AYB5FAJ4BXXVA7SOAEUE","json":"https://pith.science/pith/SMXKV6AYB5FAJ4BXXVA7SOAEUE.json","graph_json":"https://pith.science/api/pith-number/SMXKV6AYB5FAJ4BXXVA7SOAEUE/graph.json","events_json":"https://pith.science/api/pith-number/SMXKV6AYB5FAJ4BXXVA7SOAEUE/events.json","paper":"https://pith.science/paper/SMXKV6AY"},"agent_actions":{"view_html":"https://pith.science/pith/SMXKV6AYB5FAJ4BXXVA7SOAEUE","download_json":"https://pith.science/pith/SMXKV6AYB5FAJ4BXXVA7SOAEUE.json","view_paper":"https://pith.science/paper/SMXKV6AY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.03676&json=true","fetch_graph":"https://pith.science/api/pith-number/SMXKV6AYB5FAJ4BXXVA7SOAEUE/graph.json","fetch_events":"https://pith.science/api/pith-number/SMXKV6AYB5FAJ4BXXVA7SOAEUE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SMXKV6AYB5FAJ4BXXVA7SOAEUE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SMXKV6AYB5FAJ4BXXVA7SOAEUE/action/storage_attestation","attest_author":"https://pith.science/pith/SMXKV6AYB5FAJ4BXXVA7SOAEUE/action/author_attestation","sign_citation":"https://pith.science/pith/SMXKV6AYB5FAJ4BXXVA7SOAEUE/action/citation_signature","submit_replication":"https://pith.science/pith/SMXKV6AYB5FAJ4BXXVA7SOAEUE/action/replication_record"}},"created_at":"2026-05-18T00:22:54.455413+00:00","updated_at":"2026-05-18T00:22:54.455413+00:00"}