{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IMZV233TDOOVXH54P6JQ5LEFJX","short_pith_number":"pith:IMZV233T","schema_version":"1.0","canonical_sha256":"43335d6f731b9d5b9fbc7f930eac854deb4663877d396525bef504a2bdff5a7e","source":{"kind":"arxiv","id":"2202.03229","version":1},"attestation_state":"computed","paper":{"title":"Neural Models for Output-Space Invariance in Combinatorial Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Mausam, Parag Singla, Vidit Jain, Yatin Nandwani","submitted_at":"2022-02-07T14:34:53Z","abstract_excerpt":"Recently many neural models have been proposed to solve combinatorial puzzles by implicitly learning underlying constraints using their solved instances, such as sudoku or graph coloring (GCP). One drawback of the proposed architectures, which are often based on Graph Neural Networks (GNN), is that they cannot generalize across the size of the output space from which variables are assigned a value, for example, set of colors in a GCP, or board-size in sudoku. We call the output space for the variables as 'value-set'. While many works have demonstrated generalization of GNNs across graph size, "},"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":"2202.03229","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-07T14:34:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0879671a257c5d13219adfac76bf9abd0ce7953e2f4ef12a2b4c53f4b403f9e9","abstract_canon_sha256":"5a25d80be07954f5031623401a5361a84de24fce3f888dc927365dc698d51ea7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:54:36.837827Z","signature_b64":"MaS3v3UVQkF+gijyTeXjMsX6g9fM8SPflJuI7AEc4Povm8CYHmE/JorFNWitmwRpyuLyP8qCs+eGbKiC0ERXAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43335d6f731b9d5b9fbc7f930eac854deb4663877d396525bef504a2bdff5a7e","last_reissued_at":"2026-07-05T03:54:36.837399Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:54:36.837399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Models for Output-Space Invariance in Combinatorial Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Mausam, Parag Singla, Vidit Jain, Yatin Nandwani","submitted_at":"2022-02-07T14:34:53Z","abstract_excerpt":"Recently many neural models have been proposed to solve combinatorial puzzles by implicitly learning underlying constraints using their solved instances, such as sudoku or graph coloring (GCP). One drawback of the proposed architectures, which are often based on Graph Neural Networks (GNN), is that they cannot generalize across the size of the output space from which variables are assigned a value, for example, set of colors in a GCP, or board-size in sudoku. We call the output space for the variables as 'value-set'. While many works have demonstrated generalization of GNNs across graph size, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.03229","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2202.03229/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":"2202.03229","created_at":"2026-07-05T03:54:36.837460+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.03229v1","created_at":"2026-07-05T03:54:36.837460+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.03229","created_at":"2026-07-05T03:54:36.837460+00:00"},{"alias_kind":"pith_short_12","alias_value":"IMZV233TDOOV","created_at":"2026-07-05T03:54:36.837460+00:00"},{"alias_kind":"pith_short_16","alias_value":"IMZV233TDOOVXH54","created_at":"2026-07-05T03:54:36.837460+00:00"},{"alias_kind":"pith_short_8","alias_value":"IMZV233T","created_at":"2026-07-05T03:54:36.837460+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/IMZV233TDOOVXH54P6JQ5LEFJX","json":"https://pith.science/pith/IMZV233TDOOVXH54P6JQ5LEFJX.json","graph_json":"https://pith.science/api/pith-number/IMZV233TDOOVXH54P6JQ5LEFJX/graph.json","events_json":"https://pith.science/api/pith-number/IMZV233TDOOVXH54P6JQ5LEFJX/events.json","paper":"https://pith.science/paper/IMZV233T"},"agent_actions":{"view_html":"https://pith.science/pith/IMZV233TDOOVXH54P6JQ5LEFJX","download_json":"https://pith.science/pith/IMZV233TDOOVXH54P6JQ5LEFJX.json","view_paper":"https://pith.science/paper/IMZV233T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.03229&json=true","fetch_graph":"https://pith.science/api/pith-number/IMZV233TDOOVXH54P6JQ5LEFJX/graph.json","fetch_events":"https://pith.science/api/pith-number/IMZV233TDOOVXH54P6JQ5LEFJX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IMZV233TDOOVXH54P6JQ5LEFJX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IMZV233TDOOVXH54P6JQ5LEFJX/action/storage_attestation","attest_author":"https://pith.science/pith/IMZV233TDOOVXH54P6JQ5LEFJX/action/author_attestation","sign_citation":"https://pith.science/pith/IMZV233TDOOVXH54P6JQ5LEFJX/action/citation_signature","submit_replication":"https://pith.science/pith/IMZV233TDOOVXH54P6JQ5LEFJX/action/replication_record"}},"created_at":"2026-07-05T03:54:36.837460+00:00","updated_at":"2026-07-05T03:54:36.837460+00:00"}