{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:56W33Z4HGUIKI2ZGMQBMLFJGAE","short_pith_number":"pith:56W33Z4H","schema_version":"1.0","canonical_sha256":"efadbde7873510a46b266402c59526012a69d92340081b0a2b8b0a8f9f464594","source":{"kind":"arxiv","id":"2010.12873","version":3},"attestation_state":"computed","paper":{"title":"Learning Contextualized Knowledge Structures for Commonsense Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aaron Chan, Handong Zhao, Jun Yan, Mrigank Raman, Nedim Lipka, Ryan Rossi, Sungchul Kim, Tianyu Zhang, Xiang Ren","submitted_at":"2020-10-24T11:09:16Z","abstract_excerpt":"Recently, knowledge graph (KG) augmented models have achieved noteworthy success on various commonsense reasoning tasks. However, KG edge (fact) sparsity and noisy edge extraction/generation often hinder models from obtaining useful knowledge to reason over. To address these issues, we propose a new KG-augmented model: Hybrid Graph Network (HGN). Unlike prior methods, HGN learns to jointly contextualize extracted and generated knowledge by reasoning over both within a unified graph structure. Given the task input context and an extracted KG subgraph, HGN is trained to generate embeddings for 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":"2010.12873","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-24T11:09:16Z","cross_cats_sorted":[],"title_canon_sha256":"09f2b108d28fa3db71bfe265bbebac2bcb71c8bf84fc0a6f584403440de4231f","abstract_canon_sha256":"1326d4ee48f7264cf08c9b07a448d92fb98ca733362b507e22a85fe6d64cb7bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:46:10.638376Z","signature_b64":"ipzDyDwzIemxM+c6nL+W+fR5NqlUqsUYaW7wqYou6lNrhJdUBsrWx0nEREoDT8WGwA2QEEGXXvEsmW08zJ9pDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efadbde7873510a46b266402c59526012a69d92340081b0a2b8b0a8f9f464594","last_reissued_at":"2026-07-05T02:46:10.637826Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:46:10.637826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Contextualized Knowledge Structures for Commonsense Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aaron Chan, Handong Zhao, Jun Yan, Mrigank Raman, Nedim Lipka, Ryan Rossi, Sungchul Kim, Tianyu Zhang, Xiang Ren","submitted_at":"2020-10-24T11:09:16Z","abstract_excerpt":"Recently, knowledge graph (KG) augmented models have achieved noteworthy success on various commonsense reasoning tasks. However, KG edge (fact) sparsity and noisy edge extraction/generation often hinder models from obtaining useful knowledge to reason over. To address these issues, we propose a new KG-augmented model: Hybrid Graph Network (HGN). Unlike prior methods, HGN learns to jointly contextualize extracted and generated knowledge by reasoning over both within a unified graph structure. Given the task input context and an extracted KG subgraph, HGN is trained to generate embeddings for t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.12873","kind":"arxiv","version":3},"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/2010.12873/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":"2010.12873","created_at":"2026-07-05T02:46:10.637889+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.12873v3","created_at":"2026-07-05T02:46:10.637889+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.12873","created_at":"2026-07-05T02:46:10.637889+00:00"},{"alias_kind":"pith_short_12","alias_value":"56W33Z4HGUIK","created_at":"2026-07-05T02:46:10.637889+00:00"},{"alias_kind":"pith_short_16","alias_value":"56W33Z4HGUIKI2ZG","created_at":"2026-07-05T02:46:10.637889+00:00"},{"alias_kind":"pith_short_8","alias_value":"56W33Z4H","created_at":"2026-07-05T02:46:10.637889+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/56W33Z4HGUIKI2ZGMQBMLFJGAE","json":"https://pith.science/pith/56W33Z4HGUIKI2ZGMQBMLFJGAE.json","graph_json":"https://pith.science/api/pith-number/56W33Z4HGUIKI2ZGMQBMLFJGAE/graph.json","events_json":"https://pith.science/api/pith-number/56W33Z4HGUIKI2ZGMQBMLFJGAE/events.json","paper":"https://pith.science/paper/56W33Z4H"},"agent_actions":{"view_html":"https://pith.science/pith/56W33Z4HGUIKI2ZGMQBMLFJGAE","download_json":"https://pith.science/pith/56W33Z4HGUIKI2ZGMQBMLFJGAE.json","view_paper":"https://pith.science/paper/56W33Z4H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.12873&json=true","fetch_graph":"https://pith.science/api/pith-number/56W33Z4HGUIKI2ZGMQBMLFJGAE/graph.json","fetch_events":"https://pith.science/api/pith-number/56W33Z4HGUIKI2ZGMQBMLFJGAE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/56W33Z4HGUIKI2ZGMQBMLFJGAE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/56W33Z4HGUIKI2ZGMQBMLFJGAE/action/storage_attestation","attest_author":"https://pith.science/pith/56W33Z4HGUIKI2ZGMQBMLFJGAE/action/author_attestation","sign_citation":"https://pith.science/pith/56W33Z4HGUIKI2ZGMQBMLFJGAE/action/citation_signature","submit_replication":"https://pith.science/pith/56W33Z4HGUIKI2ZGMQBMLFJGAE/action/replication_record"}},"created_at":"2026-07-05T02:46:10.637889+00:00","updated_at":"2026-07-05T02:46:10.637889+00:00"}