{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:M46DJJBQX3UXYN4ZYEM5RTKU7D","short_pith_number":"pith:M46DJJBQ","schema_version":"1.0","canonical_sha256":"673c34a430bee97c3799c119d8cd54f8e383a6d9a9cad19497f2e99a2f179378","source":{"kind":"arxiv","id":"2512.07331","version":2},"attestation_state":"computed","paper":{"title":"The Inductive Bottleneck: Data-Driven Emergence of Representational Sparsity in Vision Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kanishk Awadhiya","submitted_at":"2025-12-08T09:18:32Z","abstract_excerpt":"Vision Transformers (ViTs) lack the hierarchical inductive biases inherent to Convolutional Neural Networks (CNNs), theoretically allowing them to maintain high-dimensional representations throughout all layers. However, recent observations suggest ViTs often spontaneously manifest a \"U-shaped\" entropy profile-compressing information in middle layers before expanding it for the final classification. In this work, we demonstrate that this \"Inductive Bottleneck\" is not an architectural artifact, but a data-dependent adaptation. By analyzing the layer-wise Effective Encoding Dimension (EED) of DI"},"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":"2512.07331","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-08T09:18:32Z","cross_cats_sorted":[],"title_canon_sha256":"828e2206eb5d0e74bb9392469535633075cac86147a874562dfe4fd37ef3ecfc","abstract_canon_sha256":"df8d9335704973cfc117516c88fd223d24f91a0ae4f68d800745770b306af095"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T01:20:41.085879Z","signature_b64":"T0zclzDPckV7aglf5OXS38Oc5u0N7xXssP7m5fqoQxwH9Bca49o2kGEtkTVK1ouBKbX07XxdlkJchGxbjYflAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"673c34a430bee97c3799c119d8cd54f8e383a6d9a9cad19497f2e99a2f179378","last_reissued_at":"2026-07-17T01:20:41.084990Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T01:20:41.084990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Inductive Bottleneck: Data-Driven Emergence of Representational Sparsity in Vision Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kanishk Awadhiya","submitted_at":"2025-12-08T09:18:32Z","abstract_excerpt":"Vision Transformers (ViTs) lack the hierarchical inductive biases inherent to Convolutional Neural Networks (CNNs), theoretically allowing them to maintain high-dimensional representations throughout all layers. However, recent observations suggest ViTs often spontaneously manifest a \"U-shaped\" entropy profile-compressing information in middle layers before expanding it for the final classification. In this work, we demonstrate that this \"Inductive Bottleneck\" is not an architectural artifact, but a data-dependent adaptation. By analyzing the layer-wise Effective Encoding Dimension (EED) of DI"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.07331","kind":"arxiv","version":2},"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/2512.07331/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":"2512.07331","created_at":"2026-07-17T01:20:41.085411+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.07331v2","created_at":"2026-07-17T01:20:41.085411+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.07331","created_at":"2026-07-17T01:20:41.085411+00:00"},{"alias_kind":"pith_short_12","alias_value":"M46DJJBQX3UX","created_at":"2026-07-17T01:20:41.085411+00:00"},{"alias_kind":"pith_short_16","alias_value":"M46DJJBQX3UXYN4Z","created_at":"2026-07-17T01:20:41.085411+00:00"},{"alias_kind":"pith_short_8","alias_value":"M46DJJBQ","created_at":"2026-07-17T01:20:41.085411+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/M46DJJBQX3UXYN4ZYEM5RTKU7D","json":"https://pith.science/pith/M46DJJBQX3UXYN4ZYEM5RTKU7D.json","graph_json":"https://pith.science/api/pith-number/M46DJJBQX3UXYN4ZYEM5RTKU7D/graph.json","events_json":"https://pith.science/api/pith-number/M46DJJBQX3UXYN4ZYEM5RTKU7D/events.json","paper":"https://pith.science/paper/M46DJJBQ"},"agent_actions":{"view_html":"https://pith.science/pith/M46DJJBQX3UXYN4ZYEM5RTKU7D","download_json":"https://pith.science/pith/M46DJJBQX3UXYN4ZYEM5RTKU7D.json","view_paper":"https://pith.science/paper/M46DJJBQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.07331&json=true","fetch_graph":"https://pith.science/api/pith-number/M46DJJBQX3UXYN4ZYEM5RTKU7D/graph.json","fetch_events":"https://pith.science/api/pith-number/M46DJJBQX3UXYN4ZYEM5RTKU7D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M46DJJBQX3UXYN4ZYEM5RTKU7D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M46DJJBQX3UXYN4ZYEM5RTKU7D/action/storage_attestation","attest_author":"https://pith.science/pith/M46DJJBQX3UXYN4ZYEM5RTKU7D/action/author_attestation","sign_citation":"https://pith.science/pith/M46DJJBQX3UXYN4ZYEM5RTKU7D/action/citation_signature","submit_replication":"https://pith.science/pith/M46DJJBQX3UXYN4ZYEM5RTKU7D/action/replication_record"}},"created_at":"2026-07-17T01:20:41.085411+00:00","updated_at":"2026-07-17T01:20:41.085411+00:00"}