{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PHP2TDATRLSCNRAJOFIREWCP6G","short_pith_number":"pith:PHP2TDAT","schema_version":"1.0","canonical_sha256":"79dfa98c138ae426c409715112584ff19b4d62b26e7dcaef6c485eafec118622","source":{"kind":"arxiv","id":"2403.03190","version":14},"attestation_state":"computed","paper":{"title":"Triple-CFN: Separating Concepts and Features Enhances Machine Abstract Reasoning Ability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Beiming Yuan, Ruizhuo Song","submitted_at":"2024-03-05T18:29:17Z","abstract_excerpt":"This paper introduces innovative frameworks for visual abstract reasoning, aiming to boost deep learning model performance. It emphasizes the importance of separating abstract concept and reasoning feature extraction processes. The effectiveness of the Cross-Feature Network (CFN) and its enhanced version, Triple-CFN, validates this approach. Challenges in visual abstract reasoning arise from complex pattern induction and conflicts in low-dimensional representations. To address these, a dual Expectation-Maximization (EM) process is introduced during CFN training, optimizing module parameters to"},"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":"2403.03190","kind":"arxiv","version":14},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-05T18:29:17Z","cross_cats_sorted":[],"title_canon_sha256":"ed428fb2d0fc02536906bd04b83654cbed0914c89f1d15377702fe2c61c12bfd","abstract_canon_sha256":"f248323b8a6a776bcddf154791e85f121a9b6645372d90bda3b1bf94bbcbaf49"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:32.266441Z","signature_b64":"9OEM4/EmUqI6ddy8s3YUUKqU48VZrvrFdfl6lip9NcBak4TnLoBBca9F0He+XiACddacXyg4/H0Cjs36cRbrDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79dfa98c138ae426c409715112584ff19b4d62b26e7dcaef6c485eafec118622","last_reissued_at":"2026-07-05T10:38:32.266059Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:32.266059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Triple-CFN: Separating Concepts and Features Enhances Machine Abstract Reasoning Ability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Beiming Yuan, Ruizhuo Song","submitted_at":"2024-03-05T18:29:17Z","abstract_excerpt":"This paper introduces innovative frameworks for visual abstract reasoning, aiming to boost deep learning model performance. It emphasizes the importance of separating abstract concept and reasoning feature extraction processes. The effectiveness of the Cross-Feature Network (CFN) and its enhanced version, Triple-CFN, validates this approach. Challenges in visual abstract reasoning arise from complex pattern induction and conflicts in low-dimensional representations. To address these, a dual Expectation-Maximization (EM) process is introduced during CFN training, optimizing module parameters to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.03190","kind":"arxiv","version":14},"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/2403.03190/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":"2403.03190","created_at":"2026-07-05T10:38:32.266115+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.03190v14","created_at":"2026-07-05T10:38:32.266115+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03190","created_at":"2026-07-05T10:38:32.266115+00:00"},{"alias_kind":"pith_short_12","alias_value":"PHP2TDATRLSC","created_at":"2026-07-05T10:38:32.266115+00:00"},{"alias_kind":"pith_short_16","alias_value":"PHP2TDATRLSCNRAJ","created_at":"2026-07-05T10:38:32.266115+00:00"},{"alias_kind":"pith_short_8","alias_value":"PHP2TDAT","created_at":"2026-07-05T10:38:32.266115+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.01970","citing_title":"Johnny: Structuring Representation Space to Enhance Machine Abstract Reasoning Ability","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PHP2TDATRLSCNRAJOFIREWCP6G","json":"https://pith.science/pith/PHP2TDATRLSCNRAJOFIREWCP6G.json","graph_json":"https://pith.science/api/pith-number/PHP2TDATRLSCNRAJOFIREWCP6G/graph.json","events_json":"https://pith.science/api/pith-number/PHP2TDATRLSCNRAJOFIREWCP6G/events.json","paper":"https://pith.science/paper/PHP2TDAT"},"agent_actions":{"view_html":"https://pith.science/pith/PHP2TDATRLSCNRAJOFIREWCP6G","download_json":"https://pith.science/pith/PHP2TDATRLSCNRAJOFIREWCP6G.json","view_paper":"https://pith.science/paper/PHP2TDAT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.03190&json=true","fetch_graph":"https://pith.science/api/pith-number/PHP2TDATRLSCNRAJOFIREWCP6G/graph.json","fetch_events":"https://pith.science/api/pith-number/PHP2TDATRLSCNRAJOFIREWCP6G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PHP2TDATRLSCNRAJOFIREWCP6G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PHP2TDATRLSCNRAJOFIREWCP6G/action/storage_attestation","attest_author":"https://pith.science/pith/PHP2TDATRLSCNRAJOFIREWCP6G/action/author_attestation","sign_citation":"https://pith.science/pith/PHP2TDATRLSCNRAJOFIREWCP6G/action/citation_signature","submit_replication":"https://pith.science/pith/PHP2TDATRLSCNRAJOFIREWCP6G/action/replication_record"}},"created_at":"2026-07-05T10:38:32.266115+00:00","updated_at":"2026-07-05T10:38:32.266115+00:00"}