{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:244ZGABNGKGS3JSJNV7AIGKVLW","short_pith_number":"pith:244ZGABN","canonical_record":{"source":{"id":"2501.15007","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-01-25T00:59:12Z","cross_cats_sorted":["cs.CE","q-bio.QM"],"title_canon_sha256":"b9545eb8eefba98d568041eb115802a19b51c44a60de85183e1a863cef578929","abstract_canon_sha256":"0328ed4f015eb0b1b2b908d122346a4a73ec15dec0842c39ab8243e327f54fb8"},"schema_version":"1.0"},"canonical_sha256":"d73993002d328d2da6496d7e0419555dbba31330f769c1b4359c92beb6a7e65e","source":{"kind":"arxiv","id":"2501.15007","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.15007","created_at":"2026-07-05T10:05:22Z"},{"alias_kind":"arxiv_version","alias_value":"2501.15007v1","created_at":"2026-07-05T10:05:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15007","created_at":"2026-07-05T10:05:22Z"},{"alias_kind":"pith_short_12","alias_value":"244ZGABNGKGS","created_at":"2026-07-05T10:05:22Z"},{"alias_kind":"pith_short_16","alias_value":"244ZGABNGKGS3JSJ","created_at":"2026-07-05T10:05:22Z"},{"alias_kind":"pith_short_8","alias_value":"244ZGABN","created_at":"2026-07-05T10:05:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:244ZGABNGKGS3JSJNV7AIGKVLW","target":"record","payload":{"canonical_record":{"source":{"id":"2501.15007","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-01-25T00:59:12Z","cross_cats_sorted":["cs.CE","q-bio.QM"],"title_canon_sha256":"b9545eb8eefba98d568041eb115802a19b51c44a60de85183e1a863cef578929","abstract_canon_sha256":"0328ed4f015eb0b1b2b908d122346a4a73ec15dec0842c39ab8243e327f54fb8"},"schema_version":"1.0"},"canonical_sha256":"d73993002d328d2da6496d7e0419555dbba31330f769c1b4359c92beb6a7e65e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:22.127911Z","signature_b64":"npud5U12LBckvc2J/ictWH2FX4eGI9TPqZ6ESxm7AWkzBrRRKQV3Mh2Bc5CtChBHoigmuTLncLZ7SBWKFJpXAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d73993002d328d2da6496d7e0419555dbba31330f769c1b4359c92beb6a7e65e","last_reissued_at":"2026-07-05T10:05:22.127442Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:22.127442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.15007","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":"2026-07-05T10:05:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QaVMoT3dPFoinIQfr+ebIk9Vr9u1a1ERzbZbwLilXWTCr40SLKzmzKtGGEn1MQ2v3YosQ7VruC0RKW1isewUCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:10:43.753400Z"},"content_sha256":"40d2b5d6e38cecccd2eaefd18e0c048b091dc7ace28ecaae0d2887ca9d7f7253","schema_version":"1.0","event_id":"sha256:40d2b5d6e38cecccd2eaefd18e0c048b091dc7ace28ecaae0d2887ca9d7f7253"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:244ZGABNGKGS3JSJNV7AIGKVLW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Controllable Protein Sequence Generation with LLM Preference Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CE","q-bio.QM"],"primary_cat":"cs.AI","authors_text":"Silei Chen, Wei Hu, Xiangyu Liu, Yi Liu","submitted_at":"2025-01-25T00:59:12Z","abstract_excerpt":"Designing proteins with specific attributes offers an important solution to address biomedical challenges. Pre-trained protein large language models (LLMs) have shown promising results on protein sequence generation. However, to control sequence generation for specific attributes, existing work still exhibits poor functionality and structural stability. In this paper, we propose a novel controllable protein design method called CtrlProt. We finetune a protein LLM with a new multi-listwise preference optimization strategy to improve generation quality and support multi-attribute controllable ge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15007","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/2501.15007/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":"2026-07-05T10:05:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tHjb3Gu9dJxbsLtKAXaUfcGwXk7XeIv88e2EHZRPrIX/DXf7G4F64k/U+JwdQheDi58EXH1WLz75oQkgZa8CDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:10:43.753903Z"},"content_sha256":"8b4706429bb616fb80533e72f1699a617dd2865ca607e5e3ad4b8d3c4cb6395b","schema_version":"1.0","event_id":"sha256:8b4706429bb616fb80533e72f1699a617dd2865ca607e5e3ad4b8d3c4cb6395b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/244ZGABNGKGS3JSJNV7AIGKVLW/bundle.json","state_url":"https://pith.science/pith/244ZGABNGKGS3JSJNV7AIGKVLW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/244ZGABNGKGS3JSJNV7AIGKVLW/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":"2026-08-08T09:10:43Z","links":{"resolver":"https://pith.science/pith/244ZGABNGKGS3JSJNV7AIGKVLW","bundle":"https://pith.science/pith/244ZGABNGKGS3JSJNV7AIGKVLW/bundle.json","state":"https://pith.science/pith/244ZGABNGKGS3JSJNV7AIGKVLW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/244ZGABNGKGS3JSJNV7AIGKVLW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:244ZGABNGKGS3JSJNV7AIGKVLW","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":"0328ed4f015eb0b1b2b908d122346a4a73ec15dec0842c39ab8243e327f54fb8","cross_cats_sorted":["cs.CE","q-bio.QM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-01-25T00:59:12Z","title_canon_sha256":"b9545eb8eefba98d568041eb115802a19b51c44a60de85183e1a863cef578929"},"schema_version":"1.0","source":{"id":"2501.15007","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.15007","created_at":"2026-07-05T10:05:22Z"},{"alias_kind":"arxiv_version","alias_value":"2501.15007v1","created_at":"2026-07-05T10:05:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15007","created_at":"2026-07-05T10:05:22Z"},{"alias_kind":"pith_short_12","alias_value":"244ZGABNGKGS","created_at":"2026-07-05T10:05:22Z"},{"alias_kind":"pith_short_16","alias_value":"244ZGABNGKGS3JSJ","created_at":"2026-07-05T10:05:22Z"},{"alias_kind":"pith_short_8","alias_value":"244ZGABN","created_at":"2026-07-05T10:05:22Z"}],"graph_snapshots":[{"event_id":"sha256:8b4706429bb616fb80533e72f1699a617dd2865ca607e5e3ad4b8d3c4cb6395b","target":"graph","created_at":"2026-07-05T10:05:22Z","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/2501.15007/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Designing proteins with specific attributes offers an important solution to address biomedical challenges. Pre-trained protein large language models (LLMs) have shown promising results on protein sequence generation. However, to control sequence generation for specific attributes, existing work still exhibits poor functionality and structural stability. In this paper, we propose a novel controllable protein design method called CtrlProt. We finetune a protein LLM with a new multi-listwise preference optimization strategy to improve generation quality and support multi-attribute controllable ge","authors_text":"Silei Chen, Wei Hu, Xiangyu Liu, Yi Liu","cross_cats":["cs.CE","q-bio.QM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-01-25T00:59:12Z","title":"Controllable Protein Sequence Generation with LLM Preference Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15007","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":"sha256:40d2b5d6e38cecccd2eaefd18e0c048b091dc7ace28ecaae0d2887ca9d7f7253","target":"record","created_at":"2026-07-05T10:05:22Z","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":"0328ed4f015eb0b1b2b908d122346a4a73ec15dec0842c39ab8243e327f54fb8","cross_cats_sorted":["cs.CE","q-bio.QM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-01-25T00:59:12Z","title_canon_sha256":"b9545eb8eefba98d568041eb115802a19b51c44a60de85183e1a863cef578929"},"schema_version":"1.0","source":{"id":"2501.15007","kind":"arxiv","version":1}},"canonical_sha256":"d73993002d328d2da6496d7e0419555dbba31330f769c1b4359c92beb6a7e65e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d73993002d328d2da6496d7e0419555dbba31330f769c1b4359c92beb6a7e65e","first_computed_at":"2026-07-05T10:05:22.127442Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:05:22.127442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"npud5U12LBckvc2J/ictWH2FX4eGI9TPqZ6ESxm7AWkzBrRRKQV3Mh2Bc5CtChBHoigmuTLncLZ7SBWKFJpXAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:05:22.127911Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.15007","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:40d2b5d6e38cecccd2eaefd18e0c048b091dc7ace28ecaae0d2887ca9d7f7253","sha256:8b4706429bb616fb80533e72f1699a617dd2865ca607e5e3ad4b8d3c4cb6395b"],"state_sha256":"f2202be10e19329499f5131673a7ae3efc708be5523f6ffc3675952e00804eb5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PwwVdkHcyI0ijz2FPPmvS9kERqKla+RaDaVJ3Pi6uW5DXeX5L/f5WCQbFOu1cTXGxlqMV6qk5pd3KaiPAefvCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T09:10:43.758908Z","bundle_sha256":"cfb6568abadb09cf5b27203418b447d6fffa1a87da1d4077f2dd4b55c17d4e3f"}}