{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:Q3WH3XYQU6BARAY6GRCZMWGFZ4","short_pith_number":"pith:Q3WH3XYQ","schema_version":"1.0","canonical_sha256":"86ec7ddf10a78208831e34459658c5cf316990e83df95cc289cc34fd5bc97bba","source":{"kind":"arxiv","id":"2210.09082","version":2},"attestation_state":"computed","paper":{"title":"A Solver-Free Framework for Scalable Learning in Neural ILP Architectures","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Mausam, Parag Singla, Rishabh Ranjan, Yatin Nandwani","submitted_at":"2022-10-17T13:31:20Z","abstract_excerpt":"There is a recent focus on designing architectures that have an Integer Linear Programming (ILP) layer within a neural model (referred to as Neural ILP in this paper). Neural ILP architectures are suitable for pure reasoning tasks that require data-driven constraint learning or for tasks requiring both perception (neural) and reasoning (ILP). A recent SOTA approach for end-to-end training of Neural ILP explicitly defines gradients through the ILP black box (Paulus et al. 2021) - this trains extremely slowly, owing to a call to the underlying ILP solver for every training data point in a miniba"},"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":"2210.09082","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-17T13:31:20Z","cross_cats_sorted":[],"title_canon_sha256":"9fd27dda8cd4f557615f15593ad1ec7303db49bdeebbc206d795fbfe212e3132","abstract_canon_sha256":"45f29c9927f8d1f894f2024f62d9724d39ddfdfa88acf0aba8a1076a09f972b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:32:48.826544Z","signature_b64":"bi6A833xoBWzqtue23ujr5paQj7mtDFl7aoDA//2pRl0XhCOps0BhNb//ylHLl0yPDSyLwwK5/u1X1IEQPWMAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86ec7ddf10a78208831e34459658c5cf316990e83df95cc289cc34fd5bc97bba","last_reissued_at":"2026-07-05T05:32:48.826132Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:32:48.826132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Solver-Free Framework for Scalable Learning in Neural ILP Architectures","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Mausam, Parag Singla, Rishabh Ranjan, Yatin Nandwani","submitted_at":"2022-10-17T13:31:20Z","abstract_excerpt":"There is a recent focus on designing architectures that have an Integer Linear Programming (ILP) layer within a neural model (referred to as Neural ILP in this paper). Neural ILP architectures are suitable for pure reasoning tasks that require data-driven constraint learning or for tasks requiring both perception (neural) and reasoning (ILP). A recent SOTA approach for end-to-end training of Neural ILP explicitly defines gradients through the ILP black box (Paulus et al. 2021) - this trains extremely slowly, owing to a call to the underlying ILP solver for every training data point in a miniba"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.09082","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/2210.09082/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":"2210.09082","created_at":"2026-07-05T05:32:48.826187+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.09082v2","created_at":"2026-07-05T05:32:48.826187+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.09082","created_at":"2026-07-05T05:32:48.826187+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q3WH3XYQU6BA","created_at":"2026-07-05T05:32:48.826187+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q3WH3XYQU6BARAY6","created_at":"2026-07-05T05:32:48.826187+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q3WH3XYQ","created_at":"2026-07-05T05:32:48.826187+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/Q3WH3XYQU6BARAY6GRCZMWGFZ4","json":"https://pith.science/pith/Q3WH3XYQU6BARAY6GRCZMWGFZ4.json","graph_json":"https://pith.science/api/pith-number/Q3WH3XYQU6BARAY6GRCZMWGFZ4/graph.json","events_json":"https://pith.science/api/pith-number/Q3WH3XYQU6BARAY6GRCZMWGFZ4/events.json","paper":"https://pith.science/paper/Q3WH3XYQ"},"agent_actions":{"view_html":"https://pith.science/pith/Q3WH3XYQU6BARAY6GRCZMWGFZ4","download_json":"https://pith.science/pith/Q3WH3XYQU6BARAY6GRCZMWGFZ4.json","view_paper":"https://pith.science/paper/Q3WH3XYQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.09082&json=true","fetch_graph":"https://pith.science/api/pith-number/Q3WH3XYQU6BARAY6GRCZMWGFZ4/graph.json","fetch_events":"https://pith.science/api/pith-number/Q3WH3XYQU6BARAY6GRCZMWGFZ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q3WH3XYQU6BARAY6GRCZMWGFZ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q3WH3XYQU6BARAY6GRCZMWGFZ4/action/storage_attestation","attest_author":"https://pith.science/pith/Q3WH3XYQU6BARAY6GRCZMWGFZ4/action/author_attestation","sign_citation":"https://pith.science/pith/Q3WH3XYQU6BARAY6GRCZMWGFZ4/action/citation_signature","submit_replication":"https://pith.science/pith/Q3WH3XYQU6BARAY6GRCZMWGFZ4/action/replication_record"}},"created_at":"2026-07-05T05:32:48.826187+00:00","updated_at":"2026-07-05T05:32:48.826187+00:00"}