{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EIZJDNN6YS2DHWFOLOWEPOGVPE","short_pith_number":"pith:EIZJDNN6","canonical_record":{"source":{"id":"2412.14717","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-19T10:31:25Z","cross_cats_sorted":[],"title_canon_sha256":"82bf2835c0160857e2721780ca5151f47903ba802f537e1699d0dda8dd6c94bf","abstract_canon_sha256":"021ae18e33d9319d9e3fb32c6c7549659c87b06a9fac769b5cd53161633578e9"},"schema_version":"1.0"},"canonical_sha256":"223291b5bec4b433d8ae5bac47b8d57908d624dd9c4d87adefd862e4b1e89b76","source":{"kind":"arxiv","id":"2412.14717","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.14717","created_at":"2026-07-05T09:51:51Z"},{"alias_kind":"arxiv_version","alias_value":"2412.14717v1","created_at":"2026-07-05T09:51:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14717","created_at":"2026-07-05T09:51:51Z"},{"alias_kind":"pith_short_12","alias_value":"EIZJDNN6YS2D","created_at":"2026-07-05T09:51:51Z"},{"alias_kind":"pith_short_16","alias_value":"EIZJDNN6YS2DHWFO","created_at":"2026-07-05T09:51:51Z"},{"alias_kind":"pith_short_8","alias_value":"EIZJDNN6","created_at":"2026-07-05T09:51:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EIZJDNN6YS2DHWFOLOWEPOGVPE","target":"record","payload":{"canonical_record":{"source":{"id":"2412.14717","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-19T10:31:25Z","cross_cats_sorted":[],"title_canon_sha256":"82bf2835c0160857e2721780ca5151f47903ba802f537e1699d0dda8dd6c94bf","abstract_canon_sha256":"021ae18e33d9319d9e3fb32c6c7549659c87b06a9fac769b5cd53161633578e9"},"schema_version":"1.0"},"canonical_sha256":"223291b5bec4b433d8ae5bac47b8d57908d624dd9c4d87adefd862e4b1e89b76","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:51.641450Z","signature_b64":"o6gHweVZObYxj3OACOryUvNV3llLn9zQD+SfwikqDQLE2MxmCXj8odhbbJAJXKp6EU65FaMP0LW2nVkyPqNRBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"223291b5bec4b433d8ae5bac47b8d57908d624dd9c4d87adefd862e4b1e89b76","last_reissued_at":"2026-07-05T09:51:51.640980Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:51.640980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.14717","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":"2026-07-05T09:51:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"96oH8CArnFcmd3D9HbsgdNmwUx8Qyv3tHNvtglB6+vleLIZVtTfOXGVYyV+YVLOkwt/YPN51e+FsiJjLXbr/DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T15:55:21.105101Z"},"content_sha256":"1d2775b536b288bf9275aed1cd2dde7ca0b3dcdec43cd8bf6827a5dd8c594545","schema_version":"1.0","event_id":"sha256:1d2775b536b288bf9275aed1cd2dde7ca0b3dcdec43cd8bf6827a5dd8c594545"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EIZJDNN6YS2DHWFOLOWEPOGVPE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Computing Gram Matrix for SMILES Strings using RDKFingerprint and Sinkhorn-Knopp Algorithm","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haris Mansoor, Imdad Ullah Khan, Murray Patterson, Prakash Chourasia, Sarwan Ali","submitted_at":"2024-12-19T10:31:25Z","abstract_excerpt":"In molecular structure data, SMILES (Simplified Molecular Input Line Entry System) strings are used to analyze molecular structure design. Numerical feature representation of SMILES strings is a challenging task. This work proposes a kernel-based approach for encoding and analyzing molecular structures from SMILES strings. The proposed approach involves computing a kernel matrix using the Sinkhorn-Knopp algorithm while using kernel principal component analysis (PCA) for dimensionality reduction. The resulting low-dimensional embeddings are then used for classification and regression analysis. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14717","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/2412.14717/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":"2026-07-05T09:51:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NmORniPNUMmUu4VwoP7Z2YR9DyQloY89qDdK0qvy3GqE0Mo04EQGnXYANmbdmNyrBpMxr9QEei89uD3vIHqMCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T15:55:21.105438Z"},"content_sha256":"045cddf262b5c61e1cf26656aa9f22ebb1d3a7303e4893b3f048f015266ada3f","schema_version":"1.0","event_id":"sha256:045cddf262b5c61e1cf26656aa9f22ebb1d3a7303e4893b3f048f015266ada3f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EIZJDNN6YS2DHWFOLOWEPOGVPE/bundle.json","state_url":"https://pith.science/pith/EIZJDNN6YS2DHWFOLOWEPOGVPE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EIZJDNN6YS2DHWFOLOWEPOGVPE/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":"2026-08-13T15:55:21Z","links":{"resolver":"https://pith.science/pith/EIZJDNN6YS2DHWFOLOWEPOGVPE","bundle":"https://pith.science/pith/EIZJDNN6YS2DHWFOLOWEPOGVPE/bundle.json","state":"https://pith.science/pith/EIZJDNN6YS2DHWFOLOWEPOGVPE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EIZJDNN6YS2DHWFOLOWEPOGVPE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EIZJDNN6YS2DHWFOLOWEPOGVPE","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":"021ae18e33d9319d9e3fb32c6c7549659c87b06a9fac769b5cd53161633578e9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-19T10:31:25Z","title_canon_sha256":"82bf2835c0160857e2721780ca5151f47903ba802f537e1699d0dda8dd6c94bf"},"schema_version":"1.0","source":{"id":"2412.14717","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.14717","created_at":"2026-07-05T09:51:51Z"},{"alias_kind":"arxiv_version","alias_value":"2412.14717v1","created_at":"2026-07-05T09:51:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14717","created_at":"2026-07-05T09:51:51Z"},{"alias_kind":"pith_short_12","alias_value":"EIZJDNN6YS2D","created_at":"2026-07-05T09:51:51Z"},{"alias_kind":"pith_short_16","alias_value":"EIZJDNN6YS2DHWFO","created_at":"2026-07-05T09:51:51Z"},{"alias_kind":"pith_short_8","alias_value":"EIZJDNN6","created_at":"2026-07-05T09:51:51Z"}],"graph_snapshots":[{"event_id":"sha256:045cddf262b5c61e1cf26656aa9f22ebb1d3a7303e4893b3f048f015266ada3f","target":"graph","created_at":"2026-07-05T09:51:51Z","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/2412.14717/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In molecular structure data, SMILES (Simplified Molecular Input Line Entry System) strings are used to analyze molecular structure design. Numerical feature representation of SMILES strings is a challenging task. This work proposes a kernel-based approach for encoding and analyzing molecular structures from SMILES strings. The proposed approach involves computing a kernel matrix using the Sinkhorn-Knopp algorithm while using kernel principal component analysis (PCA) for dimensionality reduction. The resulting low-dimensional embeddings are then used for classification and regression analysis. ","authors_text":"Haris Mansoor, Imdad Ullah Khan, Murray Patterson, Prakash Chourasia, Sarwan Ali","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-19T10:31:25Z","title":"Computing Gram Matrix for SMILES Strings using RDKFingerprint and Sinkhorn-Knopp Algorithm"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14717","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":"sha256:1d2775b536b288bf9275aed1cd2dde7ca0b3dcdec43cd8bf6827a5dd8c594545","target":"record","created_at":"2026-07-05T09:51:51Z","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":"021ae18e33d9319d9e3fb32c6c7549659c87b06a9fac769b5cd53161633578e9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-19T10:31:25Z","title_canon_sha256":"82bf2835c0160857e2721780ca5151f47903ba802f537e1699d0dda8dd6c94bf"},"schema_version":"1.0","source":{"id":"2412.14717","kind":"arxiv","version":1}},"canonical_sha256":"223291b5bec4b433d8ae5bac47b8d57908d624dd9c4d87adefd862e4b1e89b76","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"223291b5bec4b433d8ae5bac47b8d57908d624dd9c4d87adefd862e4b1e89b76","first_computed_at":"2026-07-05T09:51:51.640980Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:51:51.640980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o6gHweVZObYxj3OACOryUvNV3llLn9zQD+SfwikqDQLE2MxmCXj8odhbbJAJXKp6EU65FaMP0LW2nVkyPqNRBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:51:51.641450Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.14717","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d2775b536b288bf9275aed1cd2dde7ca0b3dcdec43cd8bf6827a5dd8c594545","sha256:045cddf262b5c61e1cf26656aa9f22ebb1d3a7303e4893b3f048f015266ada3f"],"state_sha256":"655cd957e1485f959dde86854b50f72b3fc4e8c797680b47ae720086fee25440"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aVOy8ZRLWdPM3OVfAXWJ+Wzea/EWztB9sj4OfIM9klKe/gjoe1prXur26LTTkOiWsth9J7RRkvg1V5cewFuIDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T15:55:21.108664Z","bundle_sha256":"1d6d42f8cc4d5470d9308b5b80ab05c3fc8d3c4997a29a57ac9288118e582605"}}