{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XRHRPY3VXSASLXOMVLMFEM5MMZ","short_pith_number":"pith:XRHRPY3V","schema_version":"1.0","canonical_sha256":"bc4f17e375bc8125ddccaad85233ac667c9793ce5d922d32508e391f225bedb4","source":{"kind":"arxiv","id":"2604.11613","version":3},"attestation_state":"computed","paper":{"title":"Symmetry Reveals Layerwise Dynamics: How Transformers Perform In-Context Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"By enforcing equivariance under feature and label permutations, transformer layers yield an explicit recursive update rule for in-context classification.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aditya Gangrade, Arjun Chandra, Patrick Lutz, Themistoklis Haris, Venkatesh Saligrama","submitted_at":"2026-04-13T15:20:41Z","abstract_excerpt":"Transformers can perform in-context classification from a few labeled examples, yet the inference-time algorithm remains opaque. We study multi-class linear classification in the hard no-margin regime and make the computation identifiable by enforcing feature- and label-permutation equivariance at every layer. This enables interpretability while maintaining functional equivalence and yields highly structured weights. From these models we extract an explicit depth-indexed recursion: an end-to-end identified, emergent update rule inside a softmax transformer, to our knowledge the first of its ki"},"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":"2604.11613","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-13T15:20:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d7d844326f0106221b2533883244b457176faf2669fcecfcda537d843886a475","abstract_canon_sha256":"d03353c698c5fb6cda6735a175745a22960b8e17c513fbba3846ffb0b7e409b4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:03:53.040268Z","signature_b64":"h5t9u4sTYEqGsVkUZ6+IBbDmo7IlKgV4ahS0S7Cx5YGKMhrsBn3RhMCI8oYqTr8jl5YYDFz9JU26cnZzCw4xAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc4f17e375bc8125ddccaad85233ac667c9793ce5d922d32508e391f225bedb4","last_reissued_at":"2026-06-01T01:03:53.039044Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:03:53.039044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Symmetry Reveals Layerwise Dynamics: How Transformers Perform In-Context Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"By enforcing equivariance under feature and label permutations, transformer layers yield an explicit recursive update rule for in-context classification.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aditya Gangrade, Arjun Chandra, Patrick Lutz, Themistoklis Haris, Venkatesh Saligrama","submitted_at":"2026-04-13T15:20:41Z","abstract_excerpt":"Transformers can perform in-context classification from a few labeled examples, yet the inference-time algorithm remains opaque. We study multi-class linear classification in the hard no-margin regime and make the computation identifiable by enforcing feature- and label-permutation equivariance at every layer. This enables interpretability while maintaining functional equivalence and yields highly structured weights. From these models we extract an explicit depth-indexed recursion: an end-to-end identified, emergent update rule inside a softmax transformer, to our knowledge the first of its ki"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"From these models we extract an explicit depth-indexed recursion: an end-to-end identified, emergent update rule inside a softmax transformer, to our knowledge the first of its kind. Attention matrices formed from mixed feature-label Gram structure drive coupled updates of training points, labels, and the test probe. The resulting dynamics implement a geometry-driven algorithmic motif, which can provably amplify class separation and yields robust expected class alignment.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"Enforcing feature- and label-permutation equivariance at every layer maintains functional equivalence to the original transformer while enabling interpretability and yielding highly structured weights from which the recursion can be extracted.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Enforcing feature- and label-permutation equivariance in transformers for in-context classification yields an identifiable emergent update rule driven by mixed feature-label Gram matrices that amplifies class separation.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"By enforcing equivariance under feature and label permutations, transformer layers yield an explicit recursive update rule for in-context classification.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"561e6a605abf43197d17f8a1e223739c36d2f3722d6bbcba401f3e99b0a59dbb"},"source":{"id":"2604.11613","kind":"arxiv","version":3},"verdict":{"id":"6ec81c0c-c62c-464b-bc28-e8ae142e7a83","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T15:02:13.402151Z","strongest_claim":"From these models we extract an explicit depth-indexed recursion: an end-to-end identified, emergent update rule inside a softmax transformer, to our knowledge the first of its kind. Attention matrices formed from mixed feature-label Gram structure drive coupled updates of training points, labels, and the test probe. The resulting dynamics implement a geometry-driven algorithmic motif, which can provably amplify class separation and yields robust expected class alignment.","one_line_summary":"Enforcing feature- and label-permutation equivariance in transformers for in-context classification yields an identifiable emergent update rule driven by mixed feature-label Gram matrices that amplifies class separation.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"Enforcing feature- and label-permutation equivariance at every layer maintains functional equivalence to the original transformer while enabling interpretability and yielding highly structured weights from which the recursion can be extracted.","pith_extraction_headline":"By enforcing equivariance under feature and label permutations, transformer layers yield an explicit recursive update rule for in-context classification."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.11613/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":"2604.11613","created_at":"2026-06-01T01:03:53.039222+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.11613v3","created_at":"2026-06-01T01:03:53.039222+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.11613","created_at":"2026-06-01T01:03:53.039222+00:00"},{"alias_kind":"pith_short_12","alias_value":"XRHRPY3VXSAS","created_at":"2026-06-01T01:03:53.039222+00:00"},{"alias_kind":"pith_short_16","alias_value":"XRHRPY3VXSASLXOM","created_at":"2026-06-01T01:03:53.039222+00:00"},{"alias_kind":"pith_short_8","alias_value":"XRHRPY3V","created_at":"2026-06-01T01:03:53.039222+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/XRHRPY3VXSASLXOMVLMFEM5MMZ","json":"https://pith.science/pith/XRHRPY3VXSASLXOMVLMFEM5MMZ.json","graph_json":"https://pith.science/api/pith-number/XRHRPY3VXSASLXOMVLMFEM5MMZ/graph.json","events_json":"https://pith.science/api/pith-number/XRHRPY3VXSASLXOMVLMFEM5MMZ/events.json","paper":"https://pith.science/paper/XRHRPY3V"},"agent_actions":{"view_html":"https://pith.science/pith/XRHRPY3VXSASLXOMVLMFEM5MMZ","download_json":"https://pith.science/pith/XRHRPY3VXSASLXOMVLMFEM5MMZ.json","view_paper":"https://pith.science/paper/XRHRPY3V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.11613&json=true","fetch_graph":"https://pith.science/api/pith-number/XRHRPY3VXSASLXOMVLMFEM5MMZ/graph.json","fetch_events":"https://pith.science/api/pith-number/XRHRPY3VXSASLXOMVLMFEM5MMZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XRHRPY3VXSASLXOMVLMFEM5MMZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XRHRPY3VXSASLXOMVLMFEM5MMZ/action/storage_attestation","attest_author":"https://pith.science/pith/XRHRPY3VXSASLXOMVLMFEM5MMZ/action/author_attestation","sign_citation":"https://pith.science/pith/XRHRPY3VXSASLXOMVLMFEM5MMZ/action/citation_signature","submit_replication":"https://pith.science/pith/XRHRPY3VXSASLXOMVLMFEM5MMZ/action/replication_record"}},"created_at":"2026-06-01T01:03:53.039222+00:00","updated_at":"2026-06-01T01:03:53.039222+00:00"}