{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ASQEG52NX4GD7ZI3WVURPTPUJ6","short_pith_number":"pith:ASQEG52N","schema_version":"1.0","canonical_sha256":"04a043774dbf0c3fe51bb56917cdf44f87c26bb75f7666b575d68bb6e65091e6","source":{"kind":"arxiv","id":"2601.23169","version":2},"attestation_state":"computed","paper":{"title":"Names Don't Matter: Symbol-Invariant Transformer for Open-Vocabulary Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LO","cs.SC"],"primary_cat":"cs.LG","authors_text":"\\.Ilker I\\c{s}{\\i}k, Wenchao Li","submitted_at":"2026-01-30T16:53:01Z","abstract_excerpt":"Current neural architectures lack a principled way to handle interchangeable tokens, i.e., symbols that are semantically equivalent yet distinguishable, such as bound variables. As a result, models trained on fixed vocabularies often struggle to generalize to unseen symbols, even when the underlying semantics remain unchanged. We propose a novel Transformer-based mechanism that is provably invariant to the renaming of interchangeable tokens. Our approach employs parallel embedding streams to isolate the contribution of each interchangeable token in the input, combined with an aggregated attent"},"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":"2601.23169","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-30T16:53:01Z","cross_cats_sorted":["cs.LO","cs.SC"],"title_canon_sha256":"a1961a4ef672497334ebac29e6f27f3a28378a1b1877bdc268f8e813a5d6faf2","abstract_canon_sha256":"34011a9375a3e803de6db849b18f28eb496cc6015c54d52c2a101607a8d7a9d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:48.258104Z","signature_b64":"Ob75Xo8sL0+coGJZfEz1HBbv9RnUw/84t91IqwI3WEO4UXeTx6Z08Qeae/AWUvHVxUXADekyi8OTl+CwKZdDBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04a043774dbf0c3fe51bb56917cdf44f87c26bb75f7666b575d68bb6e65091e6","last_reissued_at":"2026-06-03T01:05:48.257618Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:48.257618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Names Don't Matter: Symbol-Invariant Transformer for Open-Vocabulary Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LO","cs.SC"],"primary_cat":"cs.LG","authors_text":"\\.Ilker I\\c{s}{\\i}k, Wenchao Li","submitted_at":"2026-01-30T16:53:01Z","abstract_excerpt":"Current neural architectures lack a principled way to handle interchangeable tokens, i.e., symbols that are semantically equivalent yet distinguishable, such as bound variables. As a result, models trained on fixed vocabularies often struggle to generalize to unseen symbols, even when the underlying semantics remain unchanged. We propose a novel Transformer-based mechanism that is provably invariant to the renaming of interchangeable tokens. Our approach employs parallel embedding streams to isolate the contribution of each interchangeable token in the input, combined with an aggregated attent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.23169","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/2601.23169/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":"2601.23169","created_at":"2026-06-03T01:05:48.257677+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.23169v2","created_at":"2026-06-03T01:05:48.257677+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.23169","created_at":"2026-06-03T01:05:48.257677+00:00"},{"alias_kind":"pith_short_12","alias_value":"ASQEG52NX4GD","created_at":"2026-06-03T01:05:48.257677+00:00"},{"alias_kind":"pith_short_16","alias_value":"ASQEG52NX4GD7ZI3","created_at":"2026-06-03T01:05:48.257677+00:00"},{"alias_kind":"pith_short_8","alias_value":"ASQEG52N","created_at":"2026-06-03T01:05:48.257677+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.07120","citing_title":"When Symbol Names Should Not Matter: A Logistic Theory of Fresh-Symbol Classification","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ASQEG52NX4GD7ZI3WVURPTPUJ6","json":"https://pith.science/pith/ASQEG52NX4GD7ZI3WVURPTPUJ6.json","graph_json":"https://pith.science/api/pith-number/ASQEG52NX4GD7ZI3WVURPTPUJ6/graph.json","events_json":"https://pith.science/api/pith-number/ASQEG52NX4GD7ZI3WVURPTPUJ6/events.json","paper":"https://pith.science/paper/ASQEG52N"},"agent_actions":{"view_html":"https://pith.science/pith/ASQEG52NX4GD7ZI3WVURPTPUJ6","download_json":"https://pith.science/pith/ASQEG52NX4GD7ZI3WVURPTPUJ6.json","view_paper":"https://pith.science/paper/ASQEG52N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.23169&json=true","fetch_graph":"https://pith.science/api/pith-number/ASQEG52NX4GD7ZI3WVURPTPUJ6/graph.json","fetch_events":"https://pith.science/api/pith-number/ASQEG52NX4GD7ZI3WVURPTPUJ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ASQEG52NX4GD7ZI3WVURPTPUJ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ASQEG52NX4GD7ZI3WVURPTPUJ6/action/storage_attestation","attest_author":"https://pith.science/pith/ASQEG52NX4GD7ZI3WVURPTPUJ6/action/author_attestation","sign_citation":"https://pith.science/pith/ASQEG52NX4GD7ZI3WVURPTPUJ6/action/citation_signature","submit_replication":"https://pith.science/pith/ASQEG52NX4GD7ZI3WVURPTPUJ6/action/replication_record"}},"created_at":"2026-06-03T01:05:48.257677+00:00","updated_at":"2026-06-03T01:05:48.257677+00:00"}