{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:MG7JV33K2WLP5E7BJSTUFOMSVB","short_pith_number":"pith:MG7JV33K","schema_version":"1.0","canonical_sha256":"61be9aef6ad596fe93e14ca742b992a87e40a68afc7fae6c352bbefcecdbc7c4","source":{"kind":"arxiv","id":"1910.08243","version":1},"attestation_state":"computed","paper":{"title":"Reflecting After Learning for Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Gaoyuan Zhang, Lee Martie, Mohammad Arif Ul Alam, Ryan R. Anderson","submitted_at":"2019-10-18T03:37:30Z","abstract_excerpt":"Today, image classification is a common way for systems to process visual content. Although neural network approaches to classification have seen great progress in reducing error rates, it is not clear what this means for a cognitive system that needs to make sense of the multiple and competing predictions from its own classifiers. As a step to address this, we present a novel framework that uses meta-reasoning and meta-operations to unify predictions into abstractions, properties, or relationships. Using the framework on images from ImageNet, we demonstrate systems that unify 41% to 46% of pr"},"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":"1910.08243","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-10-18T03:37:30Z","cross_cats_sorted":[],"title_canon_sha256":"3ce43adaa6504665fd6e338afc810d1a6281355fdbe26f4e6ff7fa6af12317fe","abstract_canon_sha256":"9563e7c30be9fb168ae7307329640d91fb33b3b7835ae859bfe1aa9060d6f055"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:39:14.829561Z","signature_b64":"MCMHupZ2mYkzubUOm4kmxaU+jpbFiyPXiatGAdZX50CpssL6k/16Ba4MmJVuXhl03OCzbWK29tBvYCEMPPJVAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61be9aef6ad596fe93e14ca742b992a87e40a68afc7fae6c352bbefcecdbc7c4","last_reissued_at":"2026-07-05T00:39:14.829086Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:39:14.829086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reflecting After Learning for Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Gaoyuan Zhang, Lee Martie, Mohammad Arif Ul Alam, Ryan R. Anderson","submitted_at":"2019-10-18T03:37:30Z","abstract_excerpt":"Today, image classification is a common way for systems to process visual content. Although neural network approaches to classification have seen great progress in reducing error rates, it is not clear what this means for a cognitive system that needs to make sense of the multiple and competing predictions from its own classifiers. As a step to address this, we present a novel framework that uses meta-reasoning and meta-operations to unify predictions into abstractions, properties, or relationships. Using the framework on images from ImageNet, we demonstrate systems that unify 41% to 46% of pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.08243","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/1910.08243/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":"1910.08243","created_at":"2026-07-05T00:39:14.829153+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.08243v1","created_at":"2026-07-05T00:39:14.829153+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.08243","created_at":"2026-07-05T00:39:14.829153+00:00"},{"alias_kind":"pith_short_12","alias_value":"MG7JV33K2WLP","created_at":"2026-07-05T00:39:14.829153+00:00"},{"alias_kind":"pith_short_16","alias_value":"MG7JV33K2WLP5E7B","created_at":"2026-07-05T00:39:14.829153+00:00"},{"alias_kind":"pith_short_8","alias_value":"MG7JV33K","created_at":"2026-07-05T00:39:14.829153+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/MG7JV33K2WLP5E7BJSTUFOMSVB","json":"https://pith.science/pith/MG7JV33K2WLP5E7BJSTUFOMSVB.json","graph_json":"https://pith.science/api/pith-number/MG7JV33K2WLP5E7BJSTUFOMSVB/graph.json","events_json":"https://pith.science/api/pith-number/MG7JV33K2WLP5E7BJSTUFOMSVB/events.json","paper":"https://pith.science/paper/MG7JV33K"},"agent_actions":{"view_html":"https://pith.science/pith/MG7JV33K2WLP5E7BJSTUFOMSVB","download_json":"https://pith.science/pith/MG7JV33K2WLP5E7BJSTUFOMSVB.json","view_paper":"https://pith.science/paper/MG7JV33K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.08243&json=true","fetch_graph":"https://pith.science/api/pith-number/MG7JV33K2WLP5E7BJSTUFOMSVB/graph.json","fetch_events":"https://pith.science/api/pith-number/MG7JV33K2WLP5E7BJSTUFOMSVB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MG7JV33K2WLP5E7BJSTUFOMSVB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MG7JV33K2WLP5E7BJSTUFOMSVB/action/storage_attestation","attest_author":"https://pith.science/pith/MG7JV33K2WLP5E7BJSTUFOMSVB/action/author_attestation","sign_citation":"https://pith.science/pith/MG7JV33K2WLP5E7BJSTUFOMSVB/action/citation_signature","submit_replication":"https://pith.science/pith/MG7JV33K2WLP5E7BJSTUFOMSVB/action/replication_record"}},"created_at":"2026-07-05T00:39:14.829153+00:00","updated_at":"2026-07-05T00:39:14.829153+00:00"}