{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:C42J6MSCSAIXMEM4YANY2OJ6VP","short_pith_number":"pith:C42J6MSC","canonical_record":{"source":{"id":"2606.12113","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-10T14:07:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"aaff992c98d8f5961b8d9688b24f31498102510dba856b2093942fbf53ab01c8","abstract_canon_sha256":"26ee00a950c77a468e3b2722bec44705d124f05ea1602d9e87023275b94bac94"},"schema_version":"1.0"},"canonical_sha256":"17349f3242901176119cc01b8d393eabdce7ac7ba15a0e8089c6d440a46622b0","source":{"kind":"arxiv","id":"2606.12113","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.12113","created_at":"2026-06-11T01:10:49Z"},{"alias_kind":"arxiv_version","alias_value":"2606.12113v1","created_at":"2026-06-11T01:10:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12113","created_at":"2026-06-11T01:10:49Z"},{"alias_kind":"pith_short_12","alias_value":"C42J6MSCSAIX","created_at":"2026-06-11T01:10:49Z"},{"alias_kind":"pith_short_16","alias_value":"C42J6MSCSAIXMEM4","created_at":"2026-06-11T01:10:49Z"},{"alias_kind":"pith_short_8","alias_value":"C42J6MSC","created_at":"2026-06-11T01:10:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:C42J6MSCSAIXMEM4YANY2OJ6VP","target":"record","payload":{"canonical_record":{"source":{"id":"2606.12113","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-10T14:07:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"aaff992c98d8f5961b8d9688b24f31498102510dba856b2093942fbf53ab01c8","abstract_canon_sha256":"26ee00a950c77a468e3b2722bec44705d124f05ea1602d9e87023275b94bac94"},"schema_version":"1.0"},"canonical_sha256":"17349f3242901176119cc01b8d393eabdce7ac7ba15a0e8089c6d440a46622b0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:10:49.142804Z","signature_b64":"RSOh64w0BMkV82ssM/bnZvbHqTh27KyhXxiDrBX27PhEUPBvJLTbCMW0duDWARzEJGWYEEfL1siX7SFmYfTpCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17349f3242901176119cc01b8d393eabdce7ac7ba15a0e8089c6d440a46622b0","last_reissued_at":"2026-06-11T01:10:49.141856Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:10:49.141856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.12113","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":"2026-06-11T01:10:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"473sDaSwMlI8C/8F18X+Q3A1nYgYqg4UtiQk1piAZent2wpUUt7bM8cLXFzjP/fKMajzDk3wX/q+nVE44fGvDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T02:17:43.954332Z"},"content_sha256":"1442ae7fbbbbeef67f6b1b4d1e0ad21cb6557847c4555b7e68326bb79b294614","schema_version":"1.0","event_id":"sha256:1442ae7fbbbbeef67f6b1b4d1e0ad21cb6557847c4555b7e68326bb79b294614"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:C42J6MSCSAIXMEM4YANY2OJ6VP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Augmenting Molecular Language Models with Local $n$-gram Memory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"He Cao, Irwin King, Xinni Zhang, Yu Li, Zijing Liu","submitted_at":"2026-06-10T14:07:18Z","abstract_excerpt":"Transformer-based language models for SMILES strings suffer from a locality gap: standard character-level tokenization fragments chemically meaningful motifs, forcing models to repeatedly learn local syntax at the expense of long-range dependencies. To address this without disrupting standard tokenizers, we propose MolGram, which integrates a conditional $n$-gram memory module into molecular language models. MolGram maps local string patterns to learned embeddings via scalable hash lookups and dynamically injects this regional context into hidden states. Evaluations across three tasks, includi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12113","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/2606.12113/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":"2026-06-11T01:10:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bZHFO12wrj9mKcMmT6tp+wkPSGlaswYGCJtAErUlumUqpyeMD/ub0gc6jrhsT4w2yJEmGEQxLwDaTQtccXjrBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T02:17:43.954706Z"},"content_sha256":"5ffe564e919c1cd6ca83778075932c57c281f96d7184c78467d02701b6219a94","schema_version":"1.0","event_id":"sha256:5ffe564e919c1cd6ca83778075932c57c281f96d7184c78467d02701b6219a94"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C42J6MSCSAIXMEM4YANY2OJ6VP/bundle.json","state_url":"https://pith.science/pith/C42J6MSCSAIXMEM4YANY2OJ6VP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C42J6MSCSAIXMEM4YANY2OJ6VP/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":"2026-06-28T02:17:43Z","links":{"resolver":"https://pith.science/pith/C42J6MSCSAIXMEM4YANY2OJ6VP","bundle":"https://pith.science/pith/C42J6MSCSAIXMEM4YANY2OJ6VP/bundle.json","state":"https://pith.science/pith/C42J6MSCSAIXMEM4YANY2OJ6VP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C42J6MSCSAIXMEM4YANY2OJ6VP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:C42J6MSCSAIXMEM4YANY2OJ6VP","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":"26ee00a950c77a468e3b2722bec44705d124f05ea1602d9e87023275b94bac94","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-10T14:07:18Z","title_canon_sha256":"aaff992c98d8f5961b8d9688b24f31498102510dba856b2093942fbf53ab01c8"},"schema_version":"1.0","source":{"id":"2606.12113","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.12113","created_at":"2026-06-11T01:10:49Z"},{"alias_kind":"arxiv_version","alias_value":"2606.12113v1","created_at":"2026-06-11T01:10:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12113","created_at":"2026-06-11T01:10:49Z"},{"alias_kind":"pith_short_12","alias_value":"C42J6MSCSAIX","created_at":"2026-06-11T01:10:49Z"},{"alias_kind":"pith_short_16","alias_value":"C42J6MSCSAIXMEM4","created_at":"2026-06-11T01:10:49Z"},{"alias_kind":"pith_short_8","alias_value":"C42J6MSC","created_at":"2026-06-11T01:10:49Z"}],"graph_snapshots":[{"event_id":"sha256:5ffe564e919c1cd6ca83778075932c57c281f96d7184c78467d02701b6219a94","target":"graph","created_at":"2026-06-11T01:10:49Z","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/2606.12113/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformer-based language models for SMILES strings suffer from a locality gap: standard character-level tokenization fragments chemically meaningful motifs, forcing models to repeatedly learn local syntax at the expense of long-range dependencies. To address this without disrupting standard tokenizers, we propose MolGram, which integrates a conditional $n$-gram memory module into molecular language models. MolGram maps local string patterns to learned embeddings via scalable hash lookups and dynamically injects this regional context into hidden states. Evaluations across three tasks, includi","authors_text":"He Cao, Irwin King, Xinni Zhang, Yu Li, Zijing Liu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-10T14:07:18Z","title":"Augmenting Molecular Language Models with Local $n$-gram Memory"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12113","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":"sha256:1442ae7fbbbbeef67f6b1b4d1e0ad21cb6557847c4555b7e68326bb79b294614","target":"record","created_at":"2026-06-11T01:10:49Z","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":"26ee00a950c77a468e3b2722bec44705d124f05ea1602d9e87023275b94bac94","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-10T14:07:18Z","title_canon_sha256":"aaff992c98d8f5961b8d9688b24f31498102510dba856b2093942fbf53ab01c8"},"schema_version":"1.0","source":{"id":"2606.12113","kind":"arxiv","version":1}},"canonical_sha256":"17349f3242901176119cc01b8d393eabdce7ac7ba15a0e8089c6d440a46622b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"17349f3242901176119cc01b8d393eabdce7ac7ba15a0e8089c6d440a46622b0","first_computed_at":"2026-06-11T01:10:49.141856Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-11T01:10:49.141856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RSOh64w0BMkV82ssM/bnZvbHqTh27KyhXxiDrBX27PhEUPBvJLTbCMW0duDWARzEJGWYEEfL1siX7SFmYfTpCw==","signature_status":"signed_v1","signed_at":"2026-06-11T01:10:49.142804Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.12113","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1442ae7fbbbbeef67f6b1b4d1e0ad21cb6557847c4555b7e68326bb79b294614","sha256:5ffe564e919c1cd6ca83778075932c57c281f96d7184c78467d02701b6219a94"],"state_sha256":"3e0f855260a4948dd974f5c2e44a86acea5c05ed99792af7fc4e68864cec2eff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"39/vGtwr+ue7QxPCw79rGhs23eZnBcmNApGbTuSC2glLz7IcxrBN7Uk521C/XQ7u9x4STH52Q/HtQcztpcSVAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T02:17:43.956967Z","bundle_sha256":"1a2eb532c96867450da732d74b6b85a427d78bcb40679a5b6c593ddde4f6167b"}}