{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YHQCCLOK52ATS2WILOKHJ7YCOT","short_pith_number":"pith:YHQCCLOK","schema_version":"1.0","canonical_sha256":"c1e0212dcaee81396ac85b9474ff0274d219ea523ad3f30f823147e6a0295d1b","source":{"kind":"arxiv","id":"2606.27242","version":1},"attestation_state":"computed","paper":{"title":"The Geometry of Updates: Fisher Alignment at Vocabulary Scale","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"John Sweeney","submitted_at":"2026-06-25T16:30:27Z","abstract_excerpt":"Training-free source selection for LLM families with shared vocabularies arises in scientific string domains such as SMILES, protein, and genomic sequences, where candidate corpora share a tokenizer but differ in prediction targets. This creates an activation-dark regime: representation-similarity metrics can be uninformative without assumptions about label-conditioned error geometry, while classical update-geometry metrics are computationally prohibitive at vocabulary scale. We show that, in a shared-output head setting, representation metrics (e.g., CKA) are non-identifiable for transfer; mo"},"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":"2606.27242","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-25T16:30:27Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"4dbae6287e3bf99bddcdd9d8e17d6cca08d08a89f3f97f9b9fc78582a7c41fdf","abstract_canon_sha256":"5e2251368846aa541c3f88ccaacfa0c638cbc1b81d4edf9c5630793b3d0c8247"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T01:16:16.032635Z","signature_b64":"qEVHhXlsVMXwCXnzxg5Y8GskVbmMzxJQfTgiFf649adJfdeWKyo6co+aTvgASD73eJubAUdjXwCv1hZpgtT0Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1e0212dcaee81396ac85b9474ff0274d219ea523ad3f30f823147e6a0295d1b","last_reissued_at":"2026-06-26T01:16:16.032218Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T01:16:16.032218Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Geometry of Updates: Fisher Alignment at Vocabulary Scale","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"John Sweeney","submitted_at":"2026-06-25T16:30:27Z","abstract_excerpt":"Training-free source selection for LLM families with shared vocabularies arises in scientific string domains such as SMILES, protein, and genomic sequences, where candidate corpora share a tokenizer but differ in prediction targets. This creates an activation-dark regime: representation-similarity metrics can be uninformative without assumptions about label-conditioned error geometry, while classical update-geometry metrics are computationally prohibitive at vocabulary scale. We show that, in a shared-output head setting, representation metrics (e.g., CKA) are non-identifiable for transfer; mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27242","kind":"arxiv","version":1},"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/2606.27242/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":"2606.27242","created_at":"2026-06-26T01:16:16.032277+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.27242v1","created_at":"2026-06-26T01:16:16.032277+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27242","created_at":"2026-06-26T01:16:16.032277+00:00"},{"alias_kind":"pith_short_12","alias_value":"YHQCCLOK52AT","created_at":"2026-06-26T01:16:16.032277+00:00"},{"alias_kind":"pith_short_16","alias_value":"YHQCCLOK52ATS2WI","created_at":"2026-06-26T01:16:16.032277+00:00"},{"alias_kind":"pith_short_8","alias_value":"YHQCCLOK","created_at":"2026-06-26T01:16:16.032277+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/YHQCCLOK52ATS2WILOKHJ7YCOT","json":"https://pith.science/pith/YHQCCLOK52ATS2WILOKHJ7YCOT.json","graph_json":"https://pith.science/api/pith-number/YHQCCLOK52ATS2WILOKHJ7YCOT/graph.json","events_json":"https://pith.science/api/pith-number/YHQCCLOK52ATS2WILOKHJ7YCOT/events.json","paper":"https://pith.science/paper/YHQCCLOK"},"agent_actions":{"view_html":"https://pith.science/pith/YHQCCLOK52ATS2WILOKHJ7YCOT","download_json":"https://pith.science/pith/YHQCCLOK52ATS2WILOKHJ7YCOT.json","view_paper":"https://pith.science/paper/YHQCCLOK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.27242&json=true","fetch_graph":"https://pith.science/api/pith-number/YHQCCLOK52ATS2WILOKHJ7YCOT/graph.json","fetch_events":"https://pith.science/api/pith-number/YHQCCLOK52ATS2WILOKHJ7YCOT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YHQCCLOK52ATS2WILOKHJ7YCOT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YHQCCLOK52ATS2WILOKHJ7YCOT/action/storage_attestation","attest_author":"https://pith.science/pith/YHQCCLOK52ATS2WILOKHJ7YCOT/action/author_attestation","sign_citation":"https://pith.science/pith/YHQCCLOK52ATS2WILOKHJ7YCOT/action/citation_signature","submit_replication":"https://pith.science/pith/YHQCCLOK52ATS2WILOKHJ7YCOT/action/replication_record"}},"created_at":"2026-06-26T01:16:16.032277+00:00","updated_at":"2026-06-26T01:16:16.032277+00:00"}