{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:X6LHCROT6OIAHLYRRUFD5CA4SR","short_pith_number":"pith:X6LHCROT","schema_version":"1.0","canonical_sha256":"bf967145d3f39003af118d0a3e881c947429b44eae37ce0362435c8a886f5957","source":{"kind":"arxiv","id":"2406.14479","version":3},"attestation_state":"computed","paper":{"title":"Tracing Representation Progression: Analyzing and Enhancing Layer-Wise Similarity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.AI","authors_text":"Jiachen Jiang, Jinxin Zhou, Zhihui Zhu","submitted_at":"2024-06-20T16:41:09Z","abstract_excerpt":"Analyzing the similarity of internal representations has been an important technique for understanding the behavior of deep neural networks. Most existing methods for analyzing the similarity between representations of high dimensions, such as those based on Centered Kernel Alignment (CKA), rely on statistical properties of the representations for a set of data points. In this paper, we focus on transformer models and study the similarity of representations between the hidden layers of individual transformers. In this context, we show that a simple sample-wise cosine similarity metric is capab"},"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":"2406.14479","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-20T16:41:09Z","cross_cats_sorted":["cs.CL","cs.CV","cs.LG"],"title_canon_sha256":"d831f447fcb49f357bd39ae30cd212cc8dccc3a8e0b98e7f7d7ca375ed32aab8","abstract_canon_sha256":"000922f5296e81e49e520e6db12a1cc20752b4beb5af13814963cdf73cec6054"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:58.155509Z","signature_b64":"0fuZuoG2vd3ujWhlNkwR1VICM5IyG2IVv5dw8JDMNqm5AOi5P78/V6UFB2HTUHF9MM5GxvmJACPnkO8GsvkyDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf967145d3f39003af118d0a3e881c947429b44eae37ce0362435c8a886f5957","last_reissued_at":"2026-07-05T11:07:58.154948Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:58.154948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tracing Representation Progression: Analyzing and Enhancing Layer-Wise Similarity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.AI","authors_text":"Jiachen Jiang, Jinxin Zhou, Zhihui Zhu","submitted_at":"2024-06-20T16:41:09Z","abstract_excerpt":"Analyzing the similarity of internal representations has been an important technique for understanding the behavior of deep neural networks. Most existing methods for analyzing the similarity between representations of high dimensions, such as those based on Centered Kernel Alignment (CKA), rely on statistical properties of the representations for a set of data points. In this paper, we focus on transformer models and study the similarity of representations between the hidden layers of individual transformers. In this context, we show that a simple sample-wise cosine similarity metric is capab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14479","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2406.14479/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":"2406.14479","created_at":"2026-07-05T11:07:58.155012+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.14479v3","created_at":"2026-07-05T11:07:58.155012+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14479","created_at":"2026-07-05T11:07:58.155012+00:00"},{"alias_kind":"pith_short_12","alias_value":"X6LHCROT6OIA","created_at":"2026-07-05T11:07:58.155012+00:00"},{"alias_kind":"pith_short_16","alias_value":"X6LHCROT6OIAHLYR","created_at":"2026-07-05T11:07:58.155012+00:00"},{"alias_kind":"pith_short_8","alias_value":"X6LHCROT","created_at":"2026-07-05T11:07:58.155012+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20708","citing_title":"Rethinking Cross-Layer Information Routing in Diffusion Transformers","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20708","citing_title":"Rethinking Cross-Layer Information Routing in Diffusion Transformers","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2509.18993","citing_title":"CR-Net: Scaling Parameter-Efficient Training with Cross-Layer Low-Rank Structure","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2603.07475","citing_title":"A Comparative analysis of Layer-wise Representational Capacity in AR and Diffusion LLMs","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12714","citing_title":"Layer-wise Representation Dynamics: An Empirical Investigation Across Embedders and Base LLMs","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09271","citing_title":"Shaping Schema via Language Representation as the Next Frontier for LLM Intelligence Expanding","ref_index":134,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18572","citing_title":"Back into Plato's Cave: Examining Cross-modal Representational Convergence at Scale","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X6LHCROT6OIAHLYRRUFD5CA4SR","json":"https://pith.science/pith/X6LHCROT6OIAHLYRRUFD5CA4SR.json","graph_json":"https://pith.science/api/pith-number/X6LHCROT6OIAHLYRRUFD5CA4SR/graph.json","events_json":"https://pith.science/api/pith-number/X6LHCROT6OIAHLYRRUFD5CA4SR/events.json","paper":"https://pith.science/paper/X6LHCROT"},"agent_actions":{"view_html":"https://pith.science/pith/X6LHCROT6OIAHLYRRUFD5CA4SR","download_json":"https://pith.science/pith/X6LHCROT6OIAHLYRRUFD5CA4SR.json","view_paper":"https://pith.science/paper/X6LHCROT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.14479&json=true","fetch_graph":"https://pith.science/api/pith-number/X6LHCROT6OIAHLYRRUFD5CA4SR/graph.json","fetch_events":"https://pith.science/api/pith-number/X6LHCROT6OIAHLYRRUFD5CA4SR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X6LHCROT6OIAHLYRRUFD5CA4SR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X6LHCROT6OIAHLYRRUFD5CA4SR/action/storage_attestation","attest_author":"https://pith.science/pith/X6LHCROT6OIAHLYRRUFD5CA4SR/action/author_attestation","sign_citation":"https://pith.science/pith/X6LHCROT6OIAHLYRRUFD5CA4SR/action/citation_signature","submit_replication":"https://pith.science/pith/X6LHCROT6OIAHLYRRUFD5CA4SR/action/replication_record"}},"created_at":"2026-07-05T11:07:58.155012+00:00","updated_at":"2026-07-05T11:07:58.155012+00:00"}