{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DYLOAVRYWQ2UEUXWYXPDFTNQJI","short_pith_number":"pith:DYLOAVRY","canonical_record":{"source":{"id":"2411.01401","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2024-11-03T01:56:15Z","cross_cats_sorted":["cs.AI","cs.LG","physics.chem-ph"],"title_canon_sha256":"acdd48e915ff946f2f8e9086082c4bcf6b64fdbbcdfbcfc7e94ba969d64cd662","abstract_canon_sha256":"7fcd301153b6ccfc87c0cc3daf22213b8a152717641db90224eb2b70c48bd11e"},"schema_version":"1.0"},"canonical_sha256":"1e16e05638b4354252f6c5de32cdb04a2946048a80d04c8a3c8e240d98f69cb3","source":{"kind":"arxiv","id":"2411.01401","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.01401","created_at":"2026-07-05T09:30:29Z"},{"alias_kind":"arxiv_version","alias_value":"2411.01401v1","created_at":"2026-07-05T09:30:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.01401","created_at":"2026-07-05T09:30:29Z"},{"alias_kind":"pith_short_12","alias_value":"DYLOAVRYWQ2U","created_at":"2026-07-05T09:30:29Z"},{"alias_kind":"pith_short_16","alias_value":"DYLOAVRYWQ2UEUXW","created_at":"2026-07-05T09:30:29Z"},{"alias_kind":"pith_short_8","alias_value":"DYLOAVRY","created_at":"2026-07-05T09:30:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DYLOAVRYWQ2UEUXWYXPDFTNQJI","target":"record","payload":{"canonical_record":{"source":{"id":"2411.01401","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2024-11-03T01:56:15Z","cross_cats_sorted":["cs.AI","cs.LG","physics.chem-ph"],"title_canon_sha256":"acdd48e915ff946f2f8e9086082c4bcf6b64fdbbcdfbcfc7e94ba969d64cd662","abstract_canon_sha256":"7fcd301153b6ccfc87c0cc3daf22213b8a152717641db90224eb2b70c48bd11e"},"schema_version":"1.0"},"canonical_sha256":"1e16e05638b4354252f6c5de32cdb04a2946048a80d04c8a3c8e240d98f69cb3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:29.779304Z","signature_b64":"qkI58QUqXp6JJews1m5vsFr6yx3zfpPImXlNfDtHWovBi3bqh0zRg5nJ43XtFjqhRwOk8AujWZy4fEzeyR2QCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e16e05638b4354252f6c5de32cdb04a2946048a80d04c8a3c8e240d98f69cb3","last_reissued_at":"2026-07-05T09:30:29.778853Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:29.778853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.01401","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":"2026-07-05T09:30:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AlFEbV1bpf7d+uP+ua5hf25W9qzspHJE3K2DPzygp6tCY4T8C60nR3txK+FJbkqgfKHi73HnF6HJs6MTcDyiBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T05:53:21.818805Z"},"content_sha256":"3621c0e57e3dd5b096c589fb17a54e96378a85d5c5ff300ebbc4a1657a7c87e4","schema_version":"1.0","event_id":"sha256:3621c0e57e3dd5b096c589fb17a54e96378a85d5c5ff300ebbc4a1657a7c87e4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DYLOAVRYWQ2UEUXWYXPDFTNQJI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pre-trained Molecular Language Models with Random Functional Group Masking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","physics.chem-ph"],"primary_cat":"q-bio.BM","authors_text":"Haoyi Xiong, Jiang Bian, Linghe Kong, Ning Sui, Shahid Mumtaz, Tianhao Peng, Xuhong Li, Yanwu Xu, Yuchen Li, Zeke Xie","submitted_at":"2024-11-03T01:56:15Z","abstract_excerpt":"Recent advancements in computational chemistry have leveraged the power of trans-former-based language models, such as MoLFormer, pre-trained using a vast amount of simplified molecular-input line-entry system (SMILES) sequences, to understand and predict molecular properties and activities, a critical step in fields like drug discovery and materials science. To further improve performance, researchers have introduced graph neural networks with graph-based molecular representations, such as GEM, incorporating the topology, geometry, 2D or even 3D structures of molecules into pre-training. Whil"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.01401","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/2411.01401/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":"2026-07-05T09:30:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lIwYADFiiN5djnPXW1aMKCCLgWO/bZqOHbFA96hQd2PNy77OCK5gxgmdqT+aoeqYGVeTVe1dWL/yg3eL6wiVBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T05:53:21.819393Z"},"content_sha256":"9a08c54eff78e57def77d172f537c5fe1d63874c109569317bd4ce1eaee59d69","schema_version":"1.0","event_id":"sha256:9a08c54eff78e57def77d172f537c5fe1d63874c109569317bd4ce1eaee59d69"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DYLOAVRYWQ2UEUXWYXPDFTNQJI/bundle.json","state_url":"https://pith.science/pith/DYLOAVRYWQ2UEUXWYXPDFTNQJI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DYLOAVRYWQ2UEUXWYXPDFTNQJI/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":"2026-08-05T05:53:21Z","links":{"resolver":"https://pith.science/pith/DYLOAVRYWQ2UEUXWYXPDFTNQJI","bundle":"https://pith.science/pith/DYLOAVRYWQ2UEUXWYXPDFTNQJI/bundle.json","state":"https://pith.science/pith/DYLOAVRYWQ2UEUXWYXPDFTNQJI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DYLOAVRYWQ2UEUXWYXPDFTNQJI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DYLOAVRYWQ2UEUXWYXPDFTNQJI","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":"7fcd301153b6ccfc87c0cc3daf22213b8a152717641db90224eb2b70c48bd11e","cross_cats_sorted":["cs.AI","cs.LG","physics.chem-ph"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2024-11-03T01:56:15Z","title_canon_sha256":"acdd48e915ff946f2f8e9086082c4bcf6b64fdbbcdfbcfc7e94ba969d64cd662"},"schema_version":"1.0","source":{"id":"2411.01401","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.01401","created_at":"2026-07-05T09:30:29Z"},{"alias_kind":"arxiv_version","alias_value":"2411.01401v1","created_at":"2026-07-05T09:30:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.01401","created_at":"2026-07-05T09:30:29Z"},{"alias_kind":"pith_short_12","alias_value":"DYLOAVRYWQ2U","created_at":"2026-07-05T09:30:29Z"},{"alias_kind":"pith_short_16","alias_value":"DYLOAVRYWQ2UEUXW","created_at":"2026-07-05T09:30:29Z"},{"alias_kind":"pith_short_8","alias_value":"DYLOAVRY","created_at":"2026-07-05T09:30:29Z"}],"graph_snapshots":[{"event_id":"sha256:9a08c54eff78e57def77d172f537c5fe1d63874c109569317bd4ce1eaee59d69","target":"graph","created_at":"2026-07-05T09:30:29Z","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/2411.01401/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in computational chemistry have leveraged the power of trans-former-based language models, such as MoLFormer, pre-trained using a vast amount of simplified molecular-input line-entry system (SMILES) sequences, to understand and predict molecular properties and activities, a critical step in fields like drug discovery and materials science. To further improve performance, researchers have introduced graph neural networks with graph-based molecular representations, such as GEM, incorporating the topology, geometry, 2D or even 3D structures of molecules into pre-training. Whil","authors_text":"Haoyi Xiong, Jiang Bian, Linghe Kong, Ning Sui, Shahid Mumtaz, Tianhao Peng, Xuhong Li, Yanwu Xu, Yuchen Li, Zeke Xie","cross_cats":["cs.AI","cs.LG","physics.chem-ph"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2024-11-03T01:56:15Z","title":"Pre-trained Molecular Language Models with Random Functional Group Masking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.01401","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":"sha256:3621c0e57e3dd5b096c589fb17a54e96378a85d5c5ff300ebbc4a1657a7c87e4","target":"record","created_at":"2026-07-05T09:30:29Z","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":"7fcd301153b6ccfc87c0cc3daf22213b8a152717641db90224eb2b70c48bd11e","cross_cats_sorted":["cs.AI","cs.LG","physics.chem-ph"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2024-11-03T01:56:15Z","title_canon_sha256":"acdd48e915ff946f2f8e9086082c4bcf6b64fdbbcdfbcfc7e94ba969d64cd662"},"schema_version":"1.0","source":{"id":"2411.01401","kind":"arxiv","version":1}},"canonical_sha256":"1e16e05638b4354252f6c5de32cdb04a2946048a80d04c8a3c8e240d98f69cb3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1e16e05638b4354252f6c5de32cdb04a2946048a80d04c8a3c8e240d98f69cb3","first_computed_at":"2026-07-05T09:30:29.778853Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:30:29.778853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qkI58QUqXp6JJews1m5vsFr6yx3zfpPImXlNfDtHWovBi3bqh0zRg5nJ43XtFjqhRwOk8AujWZy4fEzeyR2QCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:30:29.779304Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.01401","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3621c0e57e3dd5b096c589fb17a54e96378a85d5c5ff300ebbc4a1657a7c87e4","sha256:9a08c54eff78e57def77d172f537c5fe1d63874c109569317bd4ce1eaee59d69"],"state_sha256":"e74e724355e80f27f62e055daaf4c63f1b70d06786a1a5ae2e96434819eb705e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o2PvfokuvfKvH6Rx51WqvMEjN9R3SZOjCflVsex552SUwBCSHE5fqcMOE2x14Gv4Yt9rARjO8st3WgF9qfUODg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T05:53:21.823015Z","bundle_sha256":"434897e210aca9f513f1e56901aecb0db64ec339bf5550e02e3e029f53c64b04"}}