{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:ENVCGEEBRS75BLCW2RFIR4DD5A","short_pith_number":"pith:ENVCGEEB","schema_version":"1.0","canonical_sha256":"236a2310818cbfd0ac56d44a88f063e810b1a7bde594afe90c78af0fa6c1cced","source":{"kind":"arxiv","id":"1703.00810","version":3},"attestation_state":"computed","paper":{"title":"Opening the Black Box of Deep Neural Networks via Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Naftali Tishby, Ravid Shwartz-Ziv","submitted_at":"2017-03-02T14:53:14Z","abstract_excerpt":"Despite their great success, there is still no comprehensive theoretical understanding of learning with Deep Neural Networks (DNNs) or their inner organization. Previous work proposed to analyze DNNs in the \\textit{Information Plane}; i.e., the plane of the Mutual Information values that each layer preserves on the input and output variables. They suggested that the goal of the network is to optimize the Information Bottleneck (IB) tradeoff between compression and prediction, successively, for each layer.\n  In this work we follow up on this idea and demonstrate the effectiveness of the Informa"},"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":"1703.00810","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-02T14:53:14Z","cross_cats_sorted":[],"title_canon_sha256":"4e43eeba7ab96d9ee9b39a4f986138defb4d327eb30403fac2e3882035484dc8","abstract_canon_sha256":"4fb9e211951eb4aec9c932285130e78236aca1fa68a26df7dea29837085b9879"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:45:21.943101Z","signature_b64":"xl1E1RQU+sBlgyUIrTVz9OyeiqQQX4haW1FF5c0TPBQI0L/3rcFkrLuBujufUVeXQ59/oTYJsV4MxyLTO9OsDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"236a2310818cbfd0ac56d44a88f063e810b1a7bde594afe90c78af0fa6c1cced","last_reissued_at":"2026-05-18T00:45:21.942504Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:45:21.942504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Opening the Black Box of Deep Neural Networks via Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Naftali Tishby, Ravid Shwartz-Ziv","submitted_at":"2017-03-02T14:53:14Z","abstract_excerpt":"Despite their great success, there is still no comprehensive theoretical understanding of learning with Deep Neural Networks (DNNs) or their inner organization. Previous work proposed to analyze DNNs in the \\textit{Information Plane}; i.e., the plane of the Mutual Information values that each layer preserves on the input and output variables. They suggested that the goal of the network is to optimize the Information Bottleneck (IB) tradeoff between compression and prediction, successively, for each layer.\n  In this work we follow up on this idea and demonstrate the effectiveness of the Informa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.00810","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":""},"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":"1703.00810","created_at":"2026-05-18T00:45:21.942585+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.00810v3","created_at":"2026-05-18T00:45:21.942585+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.00810","created_at":"2026-05-18T00:45:21.942585+00:00"},{"alias_kind":"pith_short_12","alias_value":"ENVCGEEBRS75","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_16","alias_value":"ENVCGEEBRS75BLCW","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_8","alias_value":"ENVCGEEB","created_at":"2026-05-18T12:31:12.930513+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":44,"internal_anchor_count":31,"sample":[{"citing_arxiv_id":"2607.08377","citing_title":"Eigenvalue Calibration for Semantic Embeddings of Large Language Models","ref_index":171,"is_internal_anchor":true},{"citing_arxiv_id":"2607.06392","citing_title":"InsideSSL: Understanding Self-Supervised Speech Representations using a Model-Centric Perspective","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2607.05175","citing_title":"Platonic Projection Structures: Operator-Induced Observability in Representation Learning","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2607.05319","citing_title":"Steering Optimisation Trajectories in Diffusion Representation Learning","ref_index":74,"is_internal_anchor":true},{"citing_arxiv_id":"2606.24861","citing_title":"First-Order Recoverability Collapse in Self-Referential Information Decoders","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22901","citing_title":"Explainable AI in Speaker Recognition -- Attention Map Visualisation and Evaluation","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2606.21593","citing_title":"Geometric and Information Compression of Representations in Deep Learning","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2606.17352","citing_title":"MM++: Unsupervised Scale-Invariant Multilayer OOD Detection via Top-K Gated Feature Fusion","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2606.10669","citing_title":"In Defense of Information Leakage in Concept-based Models","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2606.09411","citing_title":"Now You (Still) See Me: Detecting Evasive Steganographic Payloads in LLMs","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2606.08067","citing_title":"Beyond Homophily: Towards Generalized Graph Reconstruction Attack and Defense","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2606.06539","citing_title":"Synthetic Benchmarks Overstate Forward-Forward Scaling: Real-Data Limits of Layer-Local Training","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2606.27729","citing_title":"Learning 1-Bit LiDAR-based Localization with Auxiliary Objective","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"2606.00241","citing_title":"InfoAtlas: A Foundation Model for Zero-Shot Statistical Dependence Estimate","ref_index":216,"is_internal_anchor":true},{"citing_arxiv_id":"1907.00348","citing_title":"Learning to Find Correlated Features by Maximizing Information Flow in Convolutional Neural Networks","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22940","citing_title":"Human-Centered Learning Mechanics: A Dynamical Framework for Entropy-Regulated Representation Learning","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.23901","citing_title":"LLMs as Noisy Channels: A Shannon Perspective on Model Capacity and Scaling Laws","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2411.05183","citing_title":"Why CNN Features Are not Gaussian: A Statistical Anatomy of Deep Representations","ref_index":63,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14738","citing_title":"TAPIOCA: Why Task- Aware Pruning Improves OOD model Capability","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21776","citing_title":"PromptNCE: Pointwise Mutual Information Predictions Using Only LLMs and Contrastive Estimation Prompts","ref_index":59,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20276","citing_title":"OmniISR: A Unified Framework for Centralized and Federated Learning via Intermediate Supervision and Regularization","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21391","citing_title":"Post-Hoc Understanding of Metaphor Processing in Decoder-Only Language Models via Conditional Scale Entropy","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17084","citing_title":"Scale Determines Whether Language Models Organize Representation Geometry for Prediction","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18598","citing_title":"Pointwise Generalization in Deep Neural Networks","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2507.05387","citing_title":"The Generalization Ridge: Information Flow in Natural Language Generation","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ENVCGEEBRS75BLCW2RFIR4DD5A","json":"https://pith.science/pith/ENVCGEEBRS75BLCW2RFIR4DD5A.json","graph_json":"https://pith.science/api/pith-number/ENVCGEEBRS75BLCW2RFIR4DD5A/graph.json","events_json":"https://pith.science/api/pith-number/ENVCGEEBRS75BLCW2RFIR4DD5A/events.json","paper":"https://pith.science/paper/ENVCGEEB"},"agent_actions":{"view_html":"https://pith.science/pith/ENVCGEEBRS75BLCW2RFIR4DD5A","download_json":"https://pith.science/pith/ENVCGEEBRS75BLCW2RFIR4DD5A.json","view_paper":"https://pith.science/paper/ENVCGEEB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.00810&json=true","fetch_graph":"https://pith.science/api/pith-number/ENVCGEEBRS75BLCW2RFIR4DD5A/graph.json","fetch_events":"https://pith.science/api/pith-number/ENVCGEEBRS75BLCW2RFIR4DD5A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ENVCGEEBRS75BLCW2RFIR4DD5A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ENVCGEEBRS75BLCW2RFIR4DD5A/action/storage_attestation","attest_author":"https://pith.science/pith/ENVCGEEBRS75BLCW2RFIR4DD5A/action/author_attestation","sign_citation":"https://pith.science/pith/ENVCGEEBRS75BLCW2RFIR4DD5A/action/citation_signature","submit_replication":"https://pith.science/pith/ENVCGEEBRS75BLCW2RFIR4DD5A/action/replication_record"}},"created_at":"2026-05-18T00:45:21.942585+00:00","updated_at":"2026-05-18T00:45:21.942585+00:00"}