{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:E5Z5RE5DSDWAH7RNUSPOWSSQUL","short_pith_number":"pith:E5Z5RE5D","schema_version":"1.0","canonical_sha256":"2773d893a390ec03fe2da49eeb4a50a2d839a835b34b18d1d1805f54f0bfb541","source":{"kind":"arxiv","id":"2606.25610","version":1},"attestation_state":"computed","paper":{"title":"The Galaxy's Guide to the Tokenizer: A Benchmark for Scientific Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["astro-ph.GA"],"primary_cat":"astro-ph.IM","authors_text":"Bahram Mobasher, Gabriela Canalizo, Juan Rafael Mart\\'inez-Galarza, Manuel P\\'erez-Carrasco, Michael J. Smith, Sogol Sanjaripour","submitted_at":"2026-06-24T09:17:17Z","abstract_excerpt":"Tokenization is central to adapting scientific data for transformer-based foundation models, yet its impact on learned representations remains poorly understood. We compare four tokenization strategies, Affine, AIM, JetFormer, and VQ-VAE, within a unified transformer framework for astronomical imaging. Using 640,000 galaxy images from the DESI Legacy Survey and a shared AstroPT backbone, we evaluate each method on reconstruction fidelity and prediction of physical properties. Our results reveal trade-offs across approaches. The flow-based JetFormer achieves higher reconstruction quality, while"},"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":"2606.25610","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"astro-ph.IM","submitted_at":"2026-06-24T09:17:17Z","cross_cats_sorted":["astro-ph.GA"],"title_canon_sha256":"5c466f56e62d61db0804701dc831fb2e36870c5dc089302471d8cfb5b31f94c4","abstract_canon_sha256":"d3fa43c3e1f31df4a6376485c4f7cb7fb3477cadf3b3c7fd0f7fb0c377314b6a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T01:18:10.373910Z","signature_b64":"z5UKfOXfAv7L+YZFIWrLHHrHupmqYGggOVz5atTBuOVrQbyf0YtlcglIaKPSVL+IU55VW/CcCrAD0useLl3RDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2773d893a390ec03fe2da49eeb4a50a2d839a835b34b18d1d1805f54f0bfb541","last_reissued_at":"2026-06-25T01:18:10.373502Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T01:18:10.373502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Galaxy's Guide to the Tokenizer: A Benchmark for Scientific Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["astro-ph.GA"],"primary_cat":"astro-ph.IM","authors_text":"Bahram Mobasher, Gabriela Canalizo, Juan Rafael Mart\\'inez-Galarza, Manuel P\\'erez-Carrasco, Michael J. Smith, Sogol Sanjaripour","submitted_at":"2026-06-24T09:17:17Z","abstract_excerpt":"Tokenization is central to adapting scientific data for transformer-based foundation models, yet its impact on learned representations remains poorly understood. We compare four tokenization strategies, Affine, AIM, JetFormer, and VQ-VAE, within a unified transformer framework for astronomical imaging. Using 640,000 galaxy images from the DESI Legacy Survey and a shared AstroPT backbone, we evaluate each method on reconstruction fidelity and prediction of physical properties. Our results reveal trade-offs across approaches. The flow-based JetFormer achieves higher reconstruction quality, while"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25610","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/2606.25610/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":"2606.25610","created_at":"2026-06-25T01:18:10.373570+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.25610v1","created_at":"2026-06-25T01:18:10.373570+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25610","created_at":"2026-06-25T01:18:10.373570+00:00"},{"alias_kind":"pith_short_12","alias_value":"E5Z5RE5DSDWA","created_at":"2026-06-25T01:18:10.373570+00:00"},{"alias_kind":"pith_short_16","alias_value":"E5Z5RE5DSDWAH7RN","created_at":"2026-06-25T01:18:10.373570+00:00"},{"alias_kind":"pith_short_8","alias_value":"E5Z5RE5D","created_at":"2026-06-25T01:18:10.373570+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/E5Z5RE5DSDWAH7RNUSPOWSSQUL","json":"https://pith.science/pith/E5Z5RE5DSDWAH7RNUSPOWSSQUL.json","graph_json":"https://pith.science/api/pith-number/E5Z5RE5DSDWAH7RNUSPOWSSQUL/graph.json","events_json":"https://pith.science/api/pith-number/E5Z5RE5DSDWAH7RNUSPOWSSQUL/events.json","paper":"https://pith.science/paper/E5Z5RE5D"},"agent_actions":{"view_html":"https://pith.science/pith/E5Z5RE5DSDWAH7RNUSPOWSSQUL","download_json":"https://pith.science/pith/E5Z5RE5DSDWAH7RNUSPOWSSQUL.json","view_paper":"https://pith.science/paper/E5Z5RE5D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.25610&json=true","fetch_graph":"https://pith.science/api/pith-number/E5Z5RE5DSDWAH7RNUSPOWSSQUL/graph.json","fetch_events":"https://pith.science/api/pith-number/E5Z5RE5DSDWAH7RNUSPOWSSQUL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E5Z5RE5DSDWAH7RNUSPOWSSQUL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E5Z5RE5DSDWAH7RNUSPOWSSQUL/action/storage_attestation","attest_author":"https://pith.science/pith/E5Z5RE5DSDWAH7RNUSPOWSSQUL/action/author_attestation","sign_citation":"https://pith.science/pith/E5Z5RE5DSDWAH7RNUSPOWSSQUL/action/citation_signature","submit_replication":"https://pith.science/pith/E5Z5RE5DSDWAH7RNUSPOWSSQUL/action/replication_record"}},"created_at":"2026-06-25T01:18:10.373570+00:00","updated_at":"2026-06-25T01:18:10.373570+00:00"}