{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TMDZLGQB3AZKSSONIJNB2QYVO6","short_pith_number":"pith:TMDZLGQB","schema_version":"1.0","canonical_sha256":"9b07959a01d832a949cd425a1d431577b1662447dc20a6420ec02d3188f89e6b","source":{"kind":"arxiv","id":"2302.05776","version":1},"attestation_state":"computed","paper":{"title":"Stochastic Surprisal: An inferential measurement of Free Energy in Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Ghassan AlRegib, Mohit Prabhushankar","submitted_at":"2023-02-11T20:41:05Z","abstract_excerpt":"This paper conjectures and validates a framework that allows for action during inference in supervised neural networks. Supervised neural networks are constructed with the objective to maximize their performance metric in any given task. This is done by reducing free energy and its associated surprisal during training. However, the bottom-up inference nature of supervised networks is a passive process that renders them fallible to noise. In this paper, we provide a thorough background of supervised neural networks, both generative and discriminative, and discuss their functionality from the pe"},"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":"2302.05776","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-11T20:41:05Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"267118a0450d4ff49bc97cb539613e5058b3d535bd6b970d5eab61a9b7098db1","abstract_canon_sha256":"7db615e048d9cf141a2870d0e007e0a0186713d2be8ab6c85839b907dac065eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:40:58.114139Z","signature_b64":"Iv2A6Yv7E8qQLRGLodq+spzNERv7DQ8MwalXFCksCeR9OcvNvNI1C7Pjtao8OQFLv1YcS3qrH6HNYfhn6+LEDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b07959a01d832a949cd425a1d431577b1662447dc20a6420ec02d3188f89e6b","last_reissued_at":"2026-07-05T05:40:58.113758Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:40:58.113758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic Surprisal: An inferential measurement of Free Energy in Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Ghassan AlRegib, Mohit Prabhushankar","submitted_at":"2023-02-11T20:41:05Z","abstract_excerpt":"This paper conjectures and validates a framework that allows for action during inference in supervised neural networks. Supervised neural networks are constructed with the objective to maximize their performance metric in any given task. This is done by reducing free energy and its associated surprisal during training. However, the bottom-up inference nature of supervised networks is a passive process that renders them fallible to noise. In this paper, we provide a thorough background of supervised neural networks, both generative and discriminative, and discuss their functionality from the pe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.05776","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/2302.05776/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":"2302.05776","created_at":"2026-07-05T05:40:58.113816+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.05776v1","created_at":"2026-07-05T05:40:58.113816+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.05776","created_at":"2026-07-05T05:40:58.113816+00:00"},{"alias_kind":"pith_short_12","alias_value":"TMDZLGQB3AZK","created_at":"2026-07-05T05:40:58.113816+00:00"},{"alias_kind":"pith_short_16","alias_value":"TMDZLGQB3AZKSSON","created_at":"2026-07-05T05:40:58.113816+00:00"},{"alias_kind":"pith_short_8","alias_value":"TMDZLGQB","created_at":"2026-07-05T05:40:58.113816+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/TMDZLGQB3AZKSSONIJNB2QYVO6","json":"https://pith.science/pith/TMDZLGQB3AZKSSONIJNB2QYVO6.json","graph_json":"https://pith.science/api/pith-number/TMDZLGQB3AZKSSONIJNB2QYVO6/graph.json","events_json":"https://pith.science/api/pith-number/TMDZLGQB3AZKSSONIJNB2QYVO6/events.json","paper":"https://pith.science/paper/TMDZLGQB"},"agent_actions":{"view_html":"https://pith.science/pith/TMDZLGQB3AZKSSONIJNB2QYVO6","download_json":"https://pith.science/pith/TMDZLGQB3AZKSSONIJNB2QYVO6.json","view_paper":"https://pith.science/paper/TMDZLGQB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.05776&json=true","fetch_graph":"https://pith.science/api/pith-number/TMDZLGQB3AZKSSONIJNB2QYVO6/graph.json","fetch_events":"https://pith.science/api/pith-number/TMDZLGQB3AZKSSONIJNB2QYVO6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TMDZLGQB3AZKSSONIJNB2QYVO6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TMDZLGQB3AZKSSONIJNB2QYVO6/action/storage_attestation","attest_author":"https://pith.science/pith/TMDZLGQB3AZKSSONIJNB2QYVO6/action/author_attestation","sign_citation":"https://pith.science/pith/TMDZLGQB3AZKSSONIJNB2QYVO6/action/citation_signature","submit_replication":"https://pith.science/pith/TMDZLGQB3AZKSSONIJNB2QYVO6/action/replication_record"}},"created_at":"2026-07-05T05:40:58.113816+00:00","updated_at":"2026-07-05T05:40:58.113816+00:00"}