{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:S7332NQDDWVIUIJLLHONN5AT7N","short_pith_number":"pith:S7332NQD","schema_version":"1.0","canonical_sha256":"97f7bd36031daa8a212b59dcd6f413fb74098ae99c943aef599cf3b1da1b6dd2","source":{"kind":"arxiv","id":"2103.12329","version":1},"attestation_state":"computed","paper":{"title":"Contrastive Reasoning in Neural Networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Ghassan AlRegib, Mohit Prabhushankar","submitted_at":"2021-03-23T05:54:36Z","abstract_excerpt":"Neural networks represent data as projections on trained weights in a high dimensional manifold. The trained weights act as a knowledge base consisting of causal class dependencies. Inference built on features that identify these dependencies is termed as feed-forward inference. Such inference mechanisms are justified based on classical cause-to-effect inductive reasoning models. Inductive reasoning based feed-forward inference is widely used due to its mathematical simplicity and operational ease. Nevertheless, feed-forward models do not generalize well to untrained situations. To alleviate 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":"2103.12329","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-23T05:54:36Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"0d7020dfbd39b726adb4ab5c36b87ebb109f1c70167c21362a21b186b509ddbd","abstract_canon_sha256":"f0080dfa5d698c1ea911cbff07c331270e62744137e159d76fd8397f661bf531"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:25:45.483450Z","signature_b64":"FcLFmf4JqVH00XXoKKAVBBcb1QNaMxOWuqiYbkTIEzCbdMeJaz21dKE6755xEigpA39f/KlpFu8SFM3rLlRrCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97f7bd36031daa8a212b59dcd6f413fb74098ae99c943aef599cf3b1da1b6dd2","last_reissued_at":"2026-07-05T02:25:45.482770Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:25:45.482770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contrastive Reasoning in Neural Networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Ghassan AlRegib, Mohit Prabhushankar","submitted_at":"2021-03-23T05:54:36Z","abstract_excerpt":"Neural networks represent data as projections on trained weights in a high dimensional manifold. The trained weights act as a knowledge base consisting of causal class dependencies. Inference built on features that identify these dependencies is termed as feed-forward inference. Such inference mechanisms are justified based on classical cause-to-effect inductive reasoning models. Inductive reasoning based feed-forward inference is widely used due to its mathematical simplicity and operational ease. Nevertheless, feed-forward models do not generalize well to untrained situations. To alleviate t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.12329","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/2103.12329/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":"2103.12329","created_at":"2026-07-05T02:25:45.482845+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.12329v1","created_at":"2026-07-05T02:25:45.482845+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.12329","created_at":"2026-07-05T02:25:45.482845+00:00"},{"alias_kind":"pith_short_12","alias_value":"S7332NQDDWVI","created_at":"2026-07-05T02:25:45.482845+00:00"},{"alias_kind":"pith_short_16","alias_value":"S7332NQDDWVIUIJL","created_at":"2026-07-05T02:25:45.482845+00:00"},{"alias_kind":"pith_short_8","alias_value":"S7332NQD","created_at":"2026-07-05T02:25:45.482845+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/S7332NQDDWVIUIJLLHONN5AT7N","json":"https://pith.science/pith/S7332NQDDWVIUIJLLHONN5AT7N.json","graph_json":"https://pith.science/api/pith-number/S7332NQDDWVIUIJLLHONN5AT7N/graph.json","events_json":"https://pith.science/api/pith-number/S7332NQDDWVIUIJLLHONN5AT7N/events.json","paper":"https://pith.science/paper/S7332NQD"},"agent_actions":{"view_html":"https://pith.science/pith/S7332NQDDWVIUIJLLHONN5AT7N","download_json":"https://pith.science/pith/S7332NQDDWVIUIJLLHONN5AT7N.json","view_paper":"https://pith.science/paper/S7332NQD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.12329&json=true","fetch_graph":"https://pith.science/api/pith-number/S7332NQDDWVIUIJLLHONN5AT7N/graph.json","fetch_events":"https://pith.science/api/pith-number/S7332NQDDWVIUIJLLHONN5AT7N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S7332NQDDWVIUIJLLHONN5AT7N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S7332NQDDWVIUIJLLHONN5AT7N/action/storage_attestation","attest_author":"https://pith.science/pith/S7332NQDDWVIUIJLLHONN5AT7N/action/author_attestation","sign_citation":"https://pith.science/pith/S7332NQDDWVIUIJLLHONN5AT7N/action/citation_signature","submit_replication":"https://pith.science/pith/S7332NQDDWVIUIJLLHONN5AT7N/action/replication_record"}},"created_at":"2026-07-05T02:25:45.482845+00:00","updated_at":"2026-07-05T02:25:45.482845+00:00"}