{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:DHOEDGBFHRDYO4QZRLUW3LHYZD","short_pith_number":"pith:DHOEDGBF","canonical_record":{"source":{"id":"2607.22314","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-24T13:55:21Z","cross_cats_sorted":[],"title_canon_sha256":"890d9d48c6ba8f4f12c60417c97878ddbf2c6bd34583e1de899dad5599307918","abstract_canon_sha256":"bcacebdd9cf7fd10022a59a6efb520869c12a8ce54bcb8050ec1be684610d59f"},"schema_version":"1.0"},"canonical_sha256":"19dc4198253c478772198ae96dacf8c8f7868b156039db9d1f392a758ec5d48b","source":{"kind":"arxiv","id":"2607.22314","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.22314","created_at":"2026-07-27T01:20:59Z"},{"alias_kind":"arxiv_version","alias_value":"2607.22314v1","created_at":"2026-07-27T01:20:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22314","created_at":"2026-07-27T01:20:59Z"},{"alias_kind":"pith_short_12","alias_value":"DHOEDGBFHRDY","created_at":"2026-07-27T01:20:59Z"},{"alias_kind":"pith_short_16","alias_value":"DHOEDGBFHRDYO4QZ","created_at":"2026-07-27T01:20:59Z"},{"alias_kind":"pith_short_8","alias_value":"DHOEDGBF","created_at":"2026-07-27T01:20:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:DHOEDGBFHRDYO4QZRLUW3LHYZD","target":"record","payload":{"canonical_record":{"source":{"id":"2607.22314","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-24T13:55:21Z","cross_cats_sorted":[],"title_canon_sha256":"890d9d48c6ba8f4f12c60417c97878ddbf2c6bd34583e1de899dad5599307918","abstract_canon_sha256":"bcacebdd9cf7fd10022a59a6efb520869c12a8ce54bcb8050ec1be684610d59f"},"schema_version":"1.0"},"canonical_sha256":"19dc4198253c478772198ae96dacf8c8f7868b156039db9d1f392a758ec5d48b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-27T01:20:59.446976Z","signature_b64":"AyHc2qdtnoPglbGwvEyJRuJ3pX9ULG53YWWFU+LtdIPOpUMrLqMx6QWzN2C7ROdHVkd6cuWPo36sdU68Z0jJAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19dc4198253c478772198ae96dacf8c8f7868b156039db9d1f392a758ec5d48b","last_reissued_at":"2026-07-27T01:20:59.446070Z","signature_status":"signed_v1","first_computed_at":"2026-07-27T01:20:59.446070Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.22314","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-27T01:20:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ozlMUpk15JPn4avIcDUcvnX+Jeg6c/SNc5WXKi4CdMGs52e2asL8JkGIriAVEzws+Fs4AUTqOy+kLBWHwOkSCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T08:34:12.423944Z"},"content_sha256":"ff87be6841e580faceccc14fbc46044ee0c0e01ed6ad4e304532a4ecafa7b0f1","schema_version":"1.0","event_id":"sha256:ff87be6841e580faceccc14fbc46044ee0c0e01ed6ad4e304532a4ecafa7b0f1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:DHOEDGBFHRDYO4QZRLUW3LHYZD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evolution-Aware MSA Reasoning for Subsampling via Factor Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haotian Yu, Jie Zheng, Jingyi Yu, Kewei Tu, Kexin Zhang, Mingrui Li, Minzhang Li, Sixian Shen, Zhangzhi Xiong","submitted_at":"2026-07-24T13:55:21Z","abstract_excerpt":"Multiple Sequence Alignments (MSAs) provide protein language models with explicit evolutionary context, but their large depth makes subsampling unavoidable under limited token budgets. Existing strategies, including random selection, identity-based filtering, and diversity-driven sampling, are effective heuristics, yet provide limited control over the evolutionary signals retained in the subset. In this work, we recast MSA subsampling as an explicit optimization problem, where key evolutionary measures, including query identity and diversity, are treated as controllable objectives. Building on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22314","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/2607.22314/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-27T01:20:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"radCsBpwloM8zGpsT2wHNZ4l122SOSg+yV0HE4FICcNxtjin7D8G7sDzNYGoluQtnDeyJ8IKAwt+fkC8blDSAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T08:34:12.424442Z"},"content_sha256":"67d55913a106b1728a28991679d9eaa39afae8dad5614594f5a9dddaef383c4e","schema_version":"1.0","event_id":"sha256:67d55913a106b1728a28991679d9eaa39afae8dad5614594f5a9dddaef383c4e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DHOEDGBFHRDYO4QZRLUW3LHYZD/bundle.json","state_url":"https://pith.science/pith/DHOEDGBFHRDYO4QZRLUW3LHYZD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DHOEDGBFHRDYO4QZRLUW3LHYZD/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-21T08:34:12Z","links":{"resolver":"https://pith.science/pith/DHOEDGBFHRDYO4QZRLUW3LHYZD","bundle":"https://pith.science/pith/DHOEDGBFHRDYO4QZRLUW3LHYZD/bundle.json","state":"https://pith.science/pith/DHOEDGBFHRDYO4QZRLUW3LHYZD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DHOEDGBFHRDYO4QZRLUW3LHYZD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DHOEDGBFHRDYO4QZRLUW3LHYZD","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":"bcacebdd9cf7fd10022a59a6efb520869c12a8ce54bcb8050ec1be684610d59f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-24T13:55:21Z","title_canon_sha256":"890d9d48c6ba8f4f12c60417c97878ddbf2c6bd34583e1de899dad5599307918"},"schema_version":"1.0","source":{"id":"2607.22314","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.22314","created_at":"2026-07-27T01:20:59Z"},{"alias_kind":"arxiv_version","alias_value":"2607.22314v1","created_at":"2026-07-27T01:20:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22314","created_at":"2026-07-27T01:20:59Z"},{"alias_kind":"pith_short_12","alias_value":"DHOEDGBFHRDY","created_at":"2026-07-27T01:20:59Z"},{"alias_kind":"pith_short_16","alias_value":"DHOEDGBFHRDYO4QZ","created_at":"2026-07-27T01:20:59Z"},{"alias_kind":"pith_short_8","alias_value":"DHOEDGBF","created_at":"2026-07-27T01:20:59Z"}],"graph_snapshots":[{"event_id":"sha256:67d55913a106b1728a28991679d9eaa39afae8dad5614594f5a9dddaef383c4e","target":"graph","created_at":"2026-07-27T01:20:59Z","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/2607.22314/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multiple Sequence Alignments (MSAs) provide protein language models with explicit evolutionary context, but their large depth makes subsampling unavoidable under limited token budgets. Existing strategies, including random selection, identity-based filtering, and diversity-driven sampling, are effective heuristics, yet provide limited control over the evolutionary signals retained in the subset. In this work, we recast MSA subsampling as an explicit optimization problem, where key evolutionary measures, including query identity and diversity, are treated as controllable objectives. Building on","authors_text":"Haotian Yu, Jie Zheng, Jingyi Yu, Kewei Tu, Kexin Zhang, Mingrui Li, Minzhang Li, Sixian Shen, Zhangzhi Xiong","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-24T13:55:21Z","title":"Evolution-Aware MSA Reasoning for Subsampling via Factor Graphs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22314","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:ff87be6841e580faceccc14fbc46044ee0c0e01ed6ad4e304532a4ecafa7b0f1","target":"record","created_at":"2026-07-27T01:20:59Z","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":"bcacebdd9cf7fd10022a59a6efb520869c12a8ce54bcb8050ec1be684610d59f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-24T13:55:21Z","title_canon_sha256":"890d9d48c6ba8f4f12c60417c97878ddbf2c6bd34583e1de899dad5599307918"},"schema_version":"1.0","source":{"id":"2607.22314","kind":"arxiv","version":1}},"canonical_sha256":"19dc4198253c478772198ae96dacf8c8f7868b156039db9d1f392a758ec5d48b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"19dc4198253c478772198ae96dacf8c8f7868b156039db9d1f392a758ec5d48b","first_computed_at":"2026-07-27T01:20:59.446070Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-27T01:20:59.446070Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AyHc2qdtnoPglbGwvEyJRuJ3pX9ULG53YWWFU+LtdIPOpUMrLqMx6QWzN2C7ROdHVkd6cuWPo36sdU68Z0jJAw==","signature_status":"signed_v1","signed_at":"2026-07-27T01:20:59.446976Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.22314","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff87be6841e580faceccc14fbc46044ee0c0e01ed6ad4e304532a4ecafa7b0f1","sha256:67d55913a106b1728a28991679d9eaa39afae8dad5614594f5a9dddaef383c4e"],"state_sha256":"3546250baf6fc335554de64341be421f01324b244276c4c8cd05d7130575e1ee"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vaFMjkvp3gLIA4s7s0Vc9Zt21uYmpe8Ps4kel/BC+m4bMnQbiMGZj4aJa830NFymz4XUlL+o4RHtxboMoWR/Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T08:34:12.428968Z","bundle_sha256":"88c7995b0187ca1fa8f5dedd7026be12ca3fc2d5a55a738ed37b8a2ec39ef260"}}