{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:J7RNJLMMFVOZ43BWTEYTOAEYFZ","short_pith_number":"pith:J7RNJLMM","schema_version":"1.0","canonical_sha256":"4fe2d4ad8c2d5d9e6c3699313700982e48a26aca532aac4699e958254b9a8bdd","source":{"kind":"arxiv","id":"2509.24895","version":2},"attestation_state":"computed","paper":{"title":"Towards Understanding the Shape of Representations in Protein Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anders Malthe-S{\\o}renssen, Kosio Beshkov","submitted_at":"2025-09-29T15:06:24Z","abstract_excerpt":"While protein language models (PLMs) are one of the most promising avenues of research for future de novo protein design, the way in which they transform sequences to hidden representations, as well as the information encoded in such representations is yet to be fully understood. Several works have attempted to propose interpretability tools for PLMs, but they have focused on understanding how individual sequences are transformed by such models. Therefore, the way in which PLMs transform the whole space of sequences along with their relations is still unknown. In this work we attempt to unders"},"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":"2509.24895","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-29T15:06:24Z","cross_cats_sorted":[],"title_canon_sha256":"72aa141a7559247a8e324af4de563eec01aacba80b12d16d6b126fdd8e6997fc","abstract_canon_sha256":"593fab9666d6d8412f65e1e1894271619f2c346c648461301460a9c64386236c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:05:36.573995Z","signature_b64":"2t6O+cJSqNPfMarMzCTybs4jtIPpGYdMVy7DL+1NnRrqvBwEoKh+87KKQXkvLCTxxlvnn9Au7T0CQBpdwlxaBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4fe2d4ad8c2d5d9e6c3699313700982e48a26aca532aac4699e958254b9a8bdd","last_reissued_at":"2026-05-29T02:05:36.573555Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:05:36.573555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Understanding the Shape of Representations in Protein Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anders Malthe-S{\\o}renssen, Kosio Beshkov","submitted_at":"2025-09-29T15:06:24Z","abstract_excerpt":"While protein language models (PLMs) are one of the most promising avenues of research for future de novo protein design, the way in which they transform sequences to hidden representations, as well as the information encoded in such representations is yet to be fully understood. Several works have attempted to propose interpretability tools for PLMs, but they have focused on understanding how individual sequences are transformed by such models. Therefore, the way in which PLMs transform the whole space of sequences along with their relations is still unknown. In this work we attempt to unders"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.24895","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/2509.24895/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":"2509.24895","created_at":"2026-05-29T02:05:36.573612+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.24895v2","created_at":"2026-05-29T02:05:36.573612+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.24895","created_at":"2026-05-29T02:05:36.573612+00:00"},{"alias_kind":"pith_short_12","alias_value":"J7RNJLMMFVOZ","created_at":"2026-05-29T02:05:36.573612+00:00"},{"alias_kind":"pith_short_16","alias_value":"J7RNJLMMFVOZ43BW","created_at":"2026-05-29T02:05:36.573612+00:00"},{"alias_kind":"pith_short_8","alias_value":"J7RNJLMM","created_at":"2026-05-29T02:05:36.573612+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/J7RNJLMMFVOZ43BWTEYTOAEYFZ","json":"https://pith.science/pith/J7RNJLMMFVOZ43BWTEYTOAEYFZ.json","graph_json":"https://pith.science/api/pith-number/J7RNJLMMFVOZ43BWTEYTOAEYFZ/graph.json","events_json":"https://pith.science/api/pith-number/J7RNJLMMFVOZ43BWTEYTOAEYFZ/events.json","paper":"https://pith.science/paper/J7RNJLMM"},"agent_actions":{"view_html":"https://pith.science/pith/J7RNJLMMFVOZ43BWTEYTOAEYFZ","download_json":"https://pith.science/pith/J7RNJLMMFVOZ43BWTEYTOAEYFZ.json","view_paper":"https://pith.science/paper/J7RNJLMM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.24895&json=true","fetch_graph":"https://pith.science/api/pith-number/J7RNJLMMFVOZ43BWTEYTOAEYFZ/graph.json","fetch_events":"https://pith.science/api/pith-number/J7RNJLMMFVOZ43BWTEYTOAEYFZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J7RNJLMMFVOZ43BWTEYTOAEYFZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J7RNJLMMFVOZ43BWTEYTOAEYFZ/action/storage_attestation","attest_author":"https://pith.science/pith/J7RNJLMMFVOZ43BWTEYTOAEYFZ/action/author_attestation","sign_citation":"https://pith.science/pith/J7RNJLMMFVOZ43BWTEYTOAEYFZ/action/citation_signature","submit_replication":"https://pith.science/pith/J7RNJLMMFVOZ43BWTEYTOAEYFZ/action/replication_record"}},"created_at":"2026-05-29T02:05:36.573612+00:00","updated_at":"2026-05-29T02:05:36.573612+00:00"}