{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2HA5Z5LZPAV4FMPMAWY5XZY7XO","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":"964a88b916d7a885f642d8e42c13fcb7d3797d5e6f1889bfc1583d17be9243d0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-14T21:15:53Z","title_canon_sha256":"0ba17e16d64c7483f9b3da659f4b62ff95c7c09d853013ce08c240ce465af75c"},"schema_version":"1.0","source":{"id":"2508.11075","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.11075","created_at":"2026-07-05T11:54:17Z"},{"alias_kind":"arxiv_version","alias_value":"2508.11075v1","created_at":"2026-07-05T11:54:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.11075","created_at":"2026-07-05T11:54:17Z"},{"alias_kind":"pith_short_12","alias_value":"2HA5Z5LZPAV4","created_at":"2026-07-05T11:54:17Z"},{"alias_kind":"pith_short_16","alias_value":"2HA5Z5LZPAV4FMPM","created_at":"2026-07-05T11:54:17Z"},{"alias_kind":"pith_short_8","alias_value":"2HA5Z5LZ","created_at":"2026-07-05T11:54:17Z"}],"graph_snapshots":[{"event_id":"sha256:df57a7fcda17541119fff03285122b6de45ceec78e63f83ac4bcf4b61c4dfcba","target":"graph","created_at":"2026-07-05T11:54:17Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2508.11075/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Microbiome sample representation to input into LLMs is essential for downstream tasks such as phenotype prediction and environmental classification. While prior studies have explored embedding-based representations of each microbiome sample, most rely on simple averaging over sequence embeddings, often overlooking the biological importance of taxa abundance. In this work, we propose an abundance-aware variant of the Set Transformer to construct fixed-size sample-level embeddings by weighting sequence embeddings according to their relative abundance. Without modifying the model architecture, we","authors_text":"Gail Rosen, Hyunwoo Yoo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-14T21:15:53Z","title":"Abundance-Aware Set Transformer for Microbiome Sample Embedding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.11075","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:dde633029b12318531f60cec9fe25fbf7937b504d38ad129a86a6f9b1668c1f0","target":"record","created_at":"2026-07-05T11:54:17Z","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":"964a88b916d7a885f642d8e42c13fcb7d3797d5e6f1889bfc1583d17be9243d0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-14T21:15:53Z","title_canon_sha256":"0ba17e16d64c7483f9b3da659f4b62ff95c7c09d853013ce08c240ce465af75c"},"schema_version":"1.0","source":{"id":"2508.11075","kind":"arxiv","version":1}},"canonical_sha256":"d1c1dcf579782bc2b1ec05b1dbe71fbb92db63abb3c10b3042a470319c48ec08","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d1c1dcf579782bc2b1ec05b1dbe71fbb92db63abb3c10b3042a470319c48ec08","first_computed_at":"2026-07-05T11:54:17.885597Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:54:17.885597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TLWQBvTWYeCpxtkjc5fDCPn8P4Cs4BMMlC1KQaKHzC9NE46bwMcWex5o3UL2iar6RKESzOecseqOmnmqIkTjAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:54:17.886041Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.11075","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dde633029b12318531f60cec9fe25fbf7937b504d38ad129a86a6f9b1668c1f0","sha256:df57a7fcda17541119fff03285122b6de45ceec78e63f83ac4bcf4b61c4dfcba"],"state_sha256":"63703d00cc69e46220fa450a8ebd86806729987c51b2b9937f00d6c520af3a85"}