{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:BB67GQVTLVY6XFACSLSQBYAKA2","short_pith_number":"pith:BB67GQVT","canonical_record":{"source":{"id":"2112.13305","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CE","submitted_at":"2021-12-26T01:35:54Z","cross_cats_sorted":[],"title_canon_sha256":"70d1c3e2fe21208d766e31c7dce5673f218aad21213fb063848453d2aec928a0","abstract_canon_sha256":"8331d575bfecddc3a0bd47c8622320db0c9939e27f20741de6b40d19d1170999"},"schema_version":"1.0"},"canonical_sha256":"087df342b35d71eb940292e500e00a06b90937eff0807d836611b81cc491aa2c","source":{"kind":"arxiv","id":"2112.13305","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.13305","created_at":"2026-07-05T03:43:52Z"},{"alias_kind":"arxiv_version","alias_value":"2112.13305v1","created_at":"2026-07-05T03:43:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.13305","created_at":"2026-07-05T03:43:52Z"},{"alias_kind":"pith_short_12","alias_value":"BB67GQVTLVY6","created_at":"2026-07-05T03:43:52Z"},{"alias_kind":"pith_short_16","alias_value":"BB67GQVTLVY6XFAC","created_at":"2026-07-05T03:43:52Z"},{"alias_kind":"pith_short_8","alias_value":"BB67GQVT","created_at":"2026-07-05T03:43:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:BB67GQVTLVY6XFACSLSQBYAKA2","target":"record","payload":{"canonical_record":{"source":{"id":"2112.13305","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CE","submitted_at":"2021-12-26T01:35:54Z","cross_cats_sorted":[],"title_canon_sha256":"70d1c3e2fe21208d766e31c7dce5673f218aad21213fb063848453d2aec928a0","abstract_canon_sha256":"8331d575bfecddc3a0bd47c8622320db0c9939e27f20741de6b40d19d1170999"},"schema_version":"1.0"},"canonical_sha256":"087df342b35d71eb940292e500e00a06b90937eff0807d836611b81cc491aa2c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:43:52.083480Z","signature_b64":"nc81f49arT9sDVM5Tw0KvlFoMrR7PkogAyJmqNgiII1t+ra0gSWMpkvNjL2WebxldcInX40aRv8MkCfl/3bNCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"087df342b35d71eb940292e500e00a06b90937eff0807d836611b81cc491aa2c","last_reissued_at":"2026-07-05T03:43:52.083145Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:43:52.083145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.13305","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":"2026-07-05T03:43:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iuuZVecD5Nap+tBHMaca8HLZnMPDtmJkplW7qEeCLnj4oZ/jSrtGupr+p3VsNGbCCv799y87HvOpjJJoc1AhAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T02:59:27.463293Z"},"content_sha256":"20d51951459ee42cb1801584f07f36d5bc69a442496d467be0f9736a11e25acc","schema_version":"1.0","event_id":"sha256:20d51951459ee42cb1801584f07f36d5bc69a442496d467be0f9736a11e25acc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:BB67GQVTLVY6XFACSLSQBYAKA2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stepping Back to SMILES Transformers for Fast Molecular Representation Inference","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CE","authors_text":"Guojie Song, Lingsheng Cai, Wenhao Zhu, Ziyao Li","submitted_at":"2021-12-26T01:35:54Z","abstract_excerpt":"In the intersection of molecular science and deep learning, tasks like virtual screening have driven the need for a high-throughput molecular representation generator on large chemical databases. However, as SMILES strings are the most common storage format for molecules, using deep graph models to extract molecular feature from raw SMILES data requires an SMILES-to-graph conversion, which significantly decelerates the whole process. Directly deriving molecular representations from SMILES is feasible, yet there exists a performance gap between the existing unpretrained SMILES-based models and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.13305","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/2112.13305/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":"2026-07-05T03:43:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Sojj8ZwLmsDQpQBILy8xsBAaW1Z5b6MYXk3mI+0LqTynaUCdOWWzuMb7t0wQBFn1JEVWI1clx0/BbjBsr+gLDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T02:59:27.463670Z"},"content_sha256":"bb21b637fac54d74c8f298f90b913b5d5691836e6c264a28def5cd4322bc30d1","schema_version":"1.0","event_id":"sha256:bb21b637fac54d74c8f298f90b913b5d5691836e6c264a28def5cd4322bc30d1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BB67GQVTLVY6XFACSLSQBYAKA2/bundle.json","state_url":"https://pith.science/pith/BB67GQVTLVY6XFACSLSQBYAKA2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BB67GQVTLVY6XFACSLSQBYAKA2/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":"2026-08-01T02:59:27Z","links":{"resolver":"https://pith.science/pith/BB67GQVTLVY6XFACSLSQBYAKA2","bundle":"https://pith.science/pith/BB67GQVTLVY6XFACSLSQBYAKA2/bundle.json","state":"https://pith.science/pith/BB67GQVTLVY6XFACSLSQBYAKA2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BB67GQVTLVY6XFACSLSQBYAKA2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:BB67GQVTLVY6XFACSLSQBYAKA2","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":"8331d575bfecddc3a0bd47c8622320db0c9939e27f20741de6b40d19d1170999","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CE","submitted_at":"2021-12-26T01:35:54Z","title_canon_sha256":"70d1c3e2fe21208d766e31c7dce5673f218aad21213fb063848453d2aec928a0"},"schema_version":"1.0","source":{"id":"2112.13305","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.13305","created_at":"2026-07-05T03:43:52Z"},{"alias_kind":"arxiv_version","alias_value":"2112.13305v1","created_at":"2026-07-05T03:43:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.13305","created_at":"2026-07-05T03:43:52Z"},{"alias_kind":"pith_short_12","alias_value":"BB67GQVTLVY6","created_at":"2026-07-05T03:43:52Z"},{"alias_kind":"pith_short_16","alias_value":"BB67GQVTLVY6XFAC","created_at":"2026-07-05T03:43:52Z"},{"alias_kind":"pith_short_8","alias_value":"BB67GQVT","created_at":"2026-07-05T03:43:52Z"}],"graph_snapshots":[{"event_id":"sha256:bb21b637fac54d74c8f298f90b913b5d5691836e6c264a28def5cd4322bc30d1","target":"graph","created_at":"2026-07-05T03:43:52Z","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/2112.13305/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the intersection of molecular science and deep learning, tasks like virtual screening have driven the need for a high-throughput molecular representation generator on large chemical databases. However, as SMILES strings are the most common storage format for molecules, using deep graph models to extract molecular feature from raw SMILES data requires an SMILES-to-graph conversion, which significantly decelerates the whole process. Directly deriving molecular representations from SMILES is feasible, yet there exists a performance gap between the existing unpretrained SMILES-based models and ","authors_text":"Guojie Song, Lingsheng Cai, Wenhao Zhu, Ziyao Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CE","submitted_at":"2021-12-26T01:35:54Z","title":"Stepping Back to SMILES Transformers for Fast Molecular Representation Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.13305","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":"sha256:20d51951459ee42cb1801584f07f36d5bc69a442496d467be0f9736a11e25acc","target":"record","created_at":"2026-07-05T03:43:52Z","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":"8331d575bfecddc3a0bd47c8622320db0c9939e27f20741de6b40d19d1170999","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CE","submitted_at":"2021-12-26T01:35:54Z","title_canon_sha256":"70d1c3e2fe21208d766e31c7dce5673f218aad21213fb063848453d2aec928a0"},"schema_version":"1.0","source":{"id":"2112.13305","kind":"arxiv","version":1}},"canonical_sha256":"087df342b35d71eb940292e500e00a06b90937eff0807d836611b81cc491aa2c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"087df342b35d71eb940292e500e00a06b90937eff0807d836611b81cc491aa2c","first_computed_at":"2026-07-05T03:43:52.083145Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:43:52.083145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nc81f49arT9sDVM5Tw0KvlFoMrR7PkogAyJmqNgiII1t+ra0gSWMpkvNjL2WebxldcInX40aRv8MkCfl/3bNCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:43:52.083480Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.13305","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:20d51951459ee42cb1801584f07f36d5bc69a442496d467be0f9736a11e25acc","sha256:bb21b637fac54d74c8f298f90b913b5d5691836e6c264a28def5cd4322bc30d1"],"state_sha256":"5c15fb7a3e32d5c6858f931c7008aba93dcc7decfb657a1e4d191adeaee3a2fd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"inwpRE3qng97asm+eBBCUgDVIlpDdUFoBYUS3jCL5q0YLJZcl9bZyHqmCWutKtt+2e0E9iTOHzhVxFaWLneICg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T02:59:27.466500Z","bundle_sha256":"e14ce3ac9babb0f6e171ff2383e972eaad2013efb5a5106a11ac3b801a3cf7f3"}}