{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:E2Y7OAGZPMAHSIZBXHO4HRI3FO","short_pith_number":"pith:E2Y7OAGZ","canonical_record":{"source":{"id":"2412.18084","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-24T01:48:07Z","cross_cats_sorted":[],"title_canon_sha256":"32843c8b1e7b75a0e2e6b3165b32e57fd8441c4a5f45e48f0afc3c707e19110c","abstract_canon_sha256":"b57d9ce8219a3642ad6d1477c1b139cbd9f94a20496cf1b3aaca5ecbb7042baf"},"schema_version":"1.0"},"canonical_sha256":"26b1f700d97b00792321b9ddc3c51b2b90b53554d95e572c20ae90316aec9c45","source":{"kind":"arxiv","id":"2412.18084","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.18084","created_at":"2026-05-20T00:04:07Z"},{"alias_kind":"arxiv_version","alias_value":"2412.18084v6","created_at":"2026-05-20T00:04:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18084","created_at":"2026-05-20T00:04:07Z"},{"alias_kind":"pith_short_12","alias_value":"E2Y7OAGZPMAH","created_at":"2026-05-20T00:04:07Z"},{"alias_kind":"pith_short_16","alias_value":"E2Y7OAGZPMAHSIZB","created_at":"2026-05-20T00:04:07Z"},{"alias_kind":"pith_short_8","alias_value":"E2Y7OAGZ","created_at":"2026-05-20T00:04:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:E2Y7OAGZPMAHSIZBXHO4HRI3FO","target":"record","payload":{"canonical_record":{"source":{"id":"2412.18084","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-24T01:48:07Z","cross_cats_sorted":[],"title_canon_sha256":"32843c8b1e7b75a0e2e6b3165b32e57fd8441c4a5f45e48f0afc3c707e19110c","abstract_canon_sha256":"b57d9ce8219a3642ad6d1477c1b139cbd9f94a20496cf1b3aaca5ecbb7042baf"},"schema_version":"1.0"},"canonical_sha256":"26b1f700d97b00792321b9ddc3c51b2b90b53554d95e572c20ae90316aec9c45","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:07.186963Z","signature_b64":"IfiMs7P6gt/hLLU1Or1ro7gY1Nmzrw0+hnTUU6UaJ/kLSOlZPnUgu/8q0WD5J6/Xu0EReS0NAFfglqPg0YKUCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26b1f700d97b00792321b9ddc3c51b2b90b53554d95e572c20ae90316aec9c45","last_reissued_at":"2026-05-20T00:04:07.186288Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:07.186288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.18084","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:04:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cAPVsj6WJEYtnNHZ0OvzwWkCwld8vQelaPBZrJprkQ8u27k6u5NyDlNWw3VjvjLFLQIqANLIl1BG/YXTWgqZAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T17:35:54.558587Z"},"content_sha256":"fb04821eb9db3b1a02ebf1c5e25d5f0113bd263a29e8fb68c549ee8c1a4318ae","schema_version":"1.0","event_id":"sha256:fb04821eb9db3b1a02ebf1c5e25d5f0113bd263a29e8fb68c549ee8c1a4318ae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:E2Y7OAGZPMAHSIZBXHO4HRI3FO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Property Enhanced Instruction Tuning for Multi-task Molecule Generation with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Long Chen, Xiangxiang Zeng, Xuan Lin, Yangyang Chen, Yile Wang","submitted_at":"2024-12-24T01:48:07Z","abstract_excerpt":"Large language models (LLMs) are widely applied in various natural language processing tasks such as question answering and machine translation. However, due to the lack of labeled data and the difficulty of manual annotation for biochemical properties, the performance for molecule generation tasks is still limited, especially for tasks involving multi-properties constraints. In this work, we present a two-step framework PEIT (Property Enhanced Instruction Tuning) to improve LLMs for molecular-related tasks. In the first step, we use textual descriptions, SMILES, and biochemical properties as "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18084","kind":"arxiv","version":6},"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/2412.18084/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":"2026-05-20T00:04:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ABybQ1dipJo3HEvaY6f8PxFJ9NS2dRqEYewCfmbiNGq+iQdr4UieYj93HdetiBH7K75n5O0SeOchKeX+ZCTNAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T17:35:54.559371Z"},"content_sha256":"aa162fd832984e81125c959cb96c43fa64600335ab344315e603d844c31b83ef","schema_version":"1.0","event_id":"sha256:aa162fd832984e81125c959cb96c43fa64600335ab344315e603d844c31b83ef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E2Y7OAGZPMAHSIZBXHO4HRI3FO/bundle.json","state_url":"https://pith.science/pith/E2Y7OAGZPMAHSIZBXHO4HRI3FO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E2Y7OAGZPMAHSIZBXHO4HRI3FO/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":"2026-05-28T17:35:54Z","links":{"resolver":"https://pith.science/pith/E2Y7OAGZPMAHSIZBXHO4HRI3FO","bundle":"https://pith.science/pith/E2Y7OAGZPMAHSIZBXHO4HRI3FO/bundle.json","state":"https://pith.science/pith/E2Y7OAGZPMAHSIZBXHO4HRI3FO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E2Y7OAGZPMAHSIZBXHO4HRI3FO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:E2Y7OAGZPMAHSIZBXHO4HRI3FO","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":"b57d9ce8219a3642ad6d1477c1b139cbd9f94a20496cf1b3aaca5ecbb7042baf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-24T01:48:07Z","title_canon_sha256":"32843c8b1e7b75a0e2e6b3165b32e57fd8441c4a5f45e48f0afc3c707e19110c"},"schema_version":"1.0","source":{"id":"2412.18084","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.18084","created_at":"2026-05-20T00:04:07Z"},{"alias_kind":"arxiv_version","alias_value":"2412.18084v6","created_at":"2026-05-20T00:04:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18084","created_at":"2026-05-20T00:04:07Z"},{"alias_kind":"pith_short_12","alias_value":"E2Y7OAGZPMAH","created_at":"2026-05-20T00:04:07Z"},{"alias_kind":"pith_short_16","alias_value":"E2Y7OAGZPMAHSIZB","created_at":"2026-05-20T00:04:07Z"},{"alias_kind":"pith_short_8","alias_value":"E2Y7OAGZ","created_at":"2026-05-20T00:04:07Z"}],"graph_snapshots":[{"event_id":"sha256:aa162fd832984e81125c959cb96c43fa64600335ab344315e603d844c31b83ef","target":"graph","created_at":"2026-05-20T00:04:07Z","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/2412.18084/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are widely applied in various natural language processing tasks such as question answering and machine translation. However, due to the lack of labeled data and the difficulty of manual annotation for biochemical properties, the performance for molecule generation tasks is still limited, especially for tasks involving multi-properties constraints. In this work, we present a two-step framework PEIT (Property Enhanced Instruction Tuning) to improve LLMs for molecular-related tasks. In the first step, we use textual descriptions, SMILES, and biochemical properties as ","authors_text":"Long Chen, Xiangxiang Zeng, Xuan Lin, Yangyang Chen, Yile Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-24T01:48:07Z","title":"Property Enhanced Instruction Tuning for Multi-task Molecule Generation with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18084","kind":"arxiv","version":6},"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:fb04821eb9db3b1a02ebf1c5e25d5f0113bd263a29e8fb68c549ee8c1a4318ae","target":"record","created_at":"2026-05-20T00:04:07Z","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":"b57d9ce8219a3642ad6d1477c1b139cbd9f94a20496cf1b3aaca5ecbb7042baf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-24T01:48:07Z","title_canon_sha256":"32843c8b1e7b75a0e2e6b3165b32e57fd8441c4a5f45e48f0afc3c707e19110c"},"schema_version":"1.0","source":{"id":"2412.18084","kind":"arxiv","version":6}},"canonical_sha256":"26b1f700d97b00792321b9ddc3c51b2b90b53554d95e572c20ae90316aec9c45","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"26b1f700d97b00792321b9ddc3c51b2b90b53554d95e572c20ae90316aec9c45","first_computed_at":"2026-05-20T00:04:07.186288Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:04:07.186288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IfiMs7P6gt/hLLU1Or1ro7gY1Nmzrw0+hnTUU6UaJ/kLSOlZPnUgu/8q0WD5J6/Xu0EReS0NAFfglqPg0YKUCg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:04:07.186963Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.18084","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fb04821eb9db3b1a02ebf1c5e25d5f0113bd263a29e8fb68c549ee8c1a4318ae","sha256:aa162fd832984e81125c959cb96c43fa64600335ab344315e603d844c31b83ef"],"state_sha256":"7ae497ab9d9b48e7a58db28749b71796fb6764f7d0d4562174df3fa22af5b0a2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9k8NVbvE+ZEeDUN0Ufx/izZNeweRxCADgaNlrr7DbPsrhZGQH5N+oIIwV2Wx8hAimGrURe0Gke20ZTt5veXjCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T17:35:54.563371Z","bundle_sha256":"fbd16054a9412be38e37e7303f07202394e34abba0aa16403bffe2b155869212"}}