{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XRHRPY3VXSASLXOMVLMFEM5MMZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d03353c698c5fb6cda6735a175745a22960b8e17c513fbba3846ffb0b7e409b4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-13T15:20:41Z","title_canon_sha256":"d7d844326f0106221b2533883244b457176faf2669fcecfcda537d843886a475"},"schema_version":"1.0","source":{"id":"2604.11613","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.11613","created_at":"2026-06-01T01:03:53Z"},{"alias_kind":"arxiv_version","alias_value":"2604.11613v3","created_at":"2026-06-01T01:03:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.11613","created_at":"2026-06-01T01:03:53Z"},{"alias_kind":"pith_short_12","alias_value":"XRHRPY3VXSAS","created_at":"2026-06-01T01:03:53Z"},{"alias_kind":"pith_short_16","alias_value":"XRHRPY3VXSASLXOM","created_at":"2026-06-01T01:03:53Z"},{"alias_kind":"pith_short_8","alias_value":"XRHRPY3V","created_at":"2026-06-01T01:03:53Z"}],"graph_snapshots":[{"event_id":"sha256:0b6f3c714bc4fd1ec09114faa515d0d915fc5a3abf36ad3d474a91a64eed5938","target":"graph","created_at":"2026-06-01T01:03:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"By enforcing equivariance under feature and label permutations, transformer layers yield an explicit recursive update rule for in-context classification."}],"snapshot_sha256":"561e6a605abf43197d17f8a1e223739c36d2f3722d6bbcba401f3e99b0a59dbb"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.11613/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aditya Gangrade, Arjun Chandra, Patrick Lutz, Themistoklis Haris, Venkatesh Saligrama","cross_cats":["cs.AI"],"headline":"By enforcing equivariance under feature and label permutations, transformer layers yield an explicit recursive update rule for in-context classification.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-13T15:20:41Z","title":"Symmetry Reveals Layerwise Dynamics: How Transformers Perform In-Context Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.11613","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-10T15:02:13.402151Z","id":"6ec81c0c-c62c-464b-bc28-e8ae142e7a83","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"By enforcing equivariance under feature and label permutations, transformer layers yield an explicit recursive update rule for in-context classification.","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.","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."}},"verdict_id":"6ec81c0c-c62c-464b-bc28-e8ae142e7a83"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:11f6dddb8c123f24cbccf211bfc1486282c0e3bc50245641acd1e979fdfdbc0a","target":"record","created_at":"2026-06-01T01:03:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d03353c698c5fb6cda6735a175745a22960b8e17c513fbba3846ffb0b7e409b4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-13T15:20:41Z","title_canon_sha256":"d7d844326f0106221b2533883244b457176faf2669fcecfcda537d843886a475"},"schema_version":"1.0","source":{"id":"2604.11613","kind":"arxiv","version":3}},"canonical_sha256":"bc4f17e375bc8125ddccaad85233ac667c9793ce5d922d32508e391f225bedb4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bc4f17e375bc8125ddccaad85233ac667c9793ce5d922d32508e391f225bedb4","first_computed_at":"2026-06-01T01:03:53.039044Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:03:53.039044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h5t9u4sTYEqGsVkUZ6+IBbDmo7IlKgV4ahS0S7Cx5YGKMhrsBn3RhMCI8oYqTr8jl5YYDFz9JU26cnZzCw4xAw==","signature_status":"signed_v1","signed_at":"2026-06-01T01:03:53.040268Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.11613","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:11f6dddb8c123f24cbccf211bfc1486282c0e3bc50245641acd1e979fdfdbc0a","sha256:0b6f3c714bc4fd1ec09114faa515d0d915fc5a3abf36ad3d474a91a64eed5938"],"state_sha256":"2100fea376af97d1ffb5ab7d23af2795ba388350372e0410fa6e72254bdfab0f"}