{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:IWJQXAQT5BQSMDSSXVPORCQAUS","short_pith_number":"pith:IWJQXAQT","schema_version":"1.0","canonical_sha256":"45930b8213e861260e52bd5ee88a00a480cbc65b36bcab0c0aafc9d0df10c20f","source":{"kind":"arxiv","id":"1802.04721","version":1},"attestation_state":"computed","paper":{"title":"Predict and Constrain: Modeling Cardinality in Deep Structured Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Amir Globerson, Nataly Brukhim","submitted_at":"2018-02-13T16:40:08Z","abstract_excerpt":"Many machine learning problems require the prediction of multi-dimensional labels. Such structured prediction models can benefit from modeling dependencies between labels. Recently, several deep learning approaches to structured prediction have been proposed. Here we focus on capturing cardinality constraints in such models. Namely, constraining the number of non-zero labels that the model outputs. Such constraints have proven very useful in previous structured prediction approaches, but it is a challenge to introduce them into a deep learning framework. Here we show how to do this via a novel"},"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":"1802.04721","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-13T16:40:08Z","cross_cats_sorted":[],"title_canon_sha256":"bd078438411ff7684e84b0ff7b75d15b3bcd15f7945457949b4474659c645a34","abstract_canon_sha256":"7903ee4dcafa60911f018b6d743f06b65338390e4f2f769087d4518e342b6705"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:23:41.592289Z","signature_b64":"bumQX3YOhdVIzWIWg8GNKXMiFYGutEs+HFMRyL8xLTLbRzLs8HCyIiDtnRRkjyI1WCBWWYNWpOhAqUTHI50fBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45930b8213e861260e52bd5ee88a00a480cbc65b36bcab0c0aafc9d0df10c20f","last_reissued_at":"2026-05-18T00:23:41.591809Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:23:41.591809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Predict and Constrain: Modeling Cardinality in Deep Structured Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Amir Globerson, Nataly Brukhim","submitted_at":"2018-02-13T16:40:08Z","abstract_excerpt":"Many machine learning problems require the prediction of multi-dimensional labels. Such structured prediction models can benefit from modeling dependencies between labels. Recently, several deep learning approaches to structured prediction have been proposed. Here we focus on capturing cardinality constraints in such models. Namely, constraining the number of non-zero labels that the model outputs. Such constraints have proven very useful in previous structured prediction approaches, but it is a challenge to introduce them into a deep learning framework. Here we show how to do this via a novel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.04721","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":""},"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":"1802.04721","created_at":"2026-05-18T00:23:41.591883+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.04721v1","created_at":"2026-05-18T00:23:41.591883+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.04721","created_at":"2026-05-18T00:23:41.591883+00:00"},{"alias_kind":"pith_short_12","alias_value":"IWJQXAQT5BQS","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"IWJQXAQT5BQSMDSS","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"IWJQXAQT","created_at":"2026-05-18T12:32:31.084164+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/IWJQXAQT5BQSMDSSXVPORCQAUS","json":"https://pith.science/pith/IWJQXAQT5BQSMDSSXVPORCQAUS.json","graph_json":"https://pith.science/api/pith-number/IWJQXAQT5BQSMDSSXVPORCQAUS/graph.json","events_json":"https://pith.science/api/pith-number/IWJQXAQT5BQSMDSSXVPORCQAUS/events.json","paper":"https://pith.science/paper/IWJQXAQT"},"agent_actions":{"view_html":"https://pith.science/pith/IWJQXAQT5BQSMDSSXVPORCQAUS","download_json":"https://pith.science/pith/IWJQXAQT5BQSMDSSXVPORCQAUS.json","view_paper":"https://pith.science/paper/IWJQXAQT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.04721&json=true","fetch_graph":"https://pith.science/api/pith-number/IWJQXAQT5BQSMDSSXVPORCQAUS/graph.json","fetch_events":"https://pith.science/api/pith-number/IWJQXAQT5BQSMDSSXVPORCQAUS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IWJQXAQT5BQSMDSSXVPORCQAUS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IWJQXAQT5BQSMDSSXVPORCQAUS/action/storage_attestation","attest_author":"https://pith.science/pith/IWJQXAQT5BQSMDSSXVPORCQAUS/action/author_attestation","sign_citation":"https://pith.science/pith/IWJQXAQT5BQSMDSSXVPORCQAUS/action/citation_signature","submit_replication":"https://pith.science/pith/IWJQXAQT5BQSMDSSXVPORCQAUS/action/replication_record"}},"created_at":"2026-05-18T00:23:41.591883+00:00","updated_at":"2026-05-18T00:23:41.591883+00:00"}