{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:G6H6DZYRO7HLX4QP2PWEG4SDXF","short_pith_number":"pith:G6H6DZYR","canonical_record":{"source":{"id":"2506.11115","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T04:59:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"347c1d0caea1881da1ad2b571bcb6f4ac9e5c44f5f2aae94216706e808490f67","abstract_canon_sha256":"0cfd7ffbe8991c203de26146d02b31dadd2d3ff06a08684354ee8d1783defebb"},"schema_version":"1.0"},"canonical_sha256":"378fe1e71177cebbf20fd3ec437243b957356d0d21cbfb5f31b1fef725645fdf","source":{"kind":"arxiv","id":"2506.11115","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.11115","created_at":"2026-07-05T11:20:59Z"},{"alias_kind":"arxiv_version","alias_value":"2506.11115v1","created_at":"2026-07-05T11:20:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11115","created_at":"2026-07-05T11:20:59Z"},{"alias_kind":"pith_short_12","alias_value":"G6H6DZYRO7HL","created_at":"2026-07-05T11:20:59Z"},{"alias_kind":"pith_short_16","alias_value":"G6H6DZYRO7HLX4QP","created_at":"2026-07-05T11:20:59Z"},{"alias_kind":"pith_short_8","alias_value":"G6H6DZYR","created_at":"2026-07-05T11:20:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:G6H6DZYRO7HLX4QP2PWEG4SDXF","target":"record","payload":{"canonical_record":{"source":{"id":"2506.11115","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T04:59:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"347c1d0caea1881da1ad2b571bcb6f4ac9e5c44f5f2aae94216706e808490f67","abstract_canon_sha256":"0cfd7ffbe8991c203de26146d02b31dadd2d3ff06a08684354ee8d1783defebb"},"schema_version":"1.0"},"canonical_sha256":"378fe1e71177cebbf20fd3ec437243b957356d0d21cbfb5f31b1fef725645fdf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:59.679496Z","signature_b64":"7X2jNfHQzqIWnPOeLxKuEDpzRxqzK0ixBC37lV+Uk+4W0vXTnJVwPQDGRtT43a2euQ5h6UZbqS86eNHBvjIPCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"378fe1e71177cebbf20fd3ec437243b957356d0d21cbfb5f31b1fef725645fdf","last_reissued_at":"2026-07-05T11:20:59.679107Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:59.679107Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.11115","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":"2026-07-05T11:20:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2QC0jRkwlikFnYBmvB7P97VoxbEpA2NqNEiP7QVijzLvrbdl9eMmkTBX2Mb/HS0cOOZEBZn72ZmUfpP+0FvRAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T15:30:05.897178Z"},"content_sha256":"d02303b8eccfb1da45f42dc793e36ffe2ce3e814c2c4418cc34c871bc6bfed67","schema_version":"1.0","event_id":"sha256:d02303b8eccfb1da45f42dc793e36ffe2ce3e814c2c4418cc34c871bc6bfed67"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:G6H6DZYRO7HLX4QP2PWEG4SDXF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Incorporating Domain Knowledge into Materials Tokenization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Junho Kim, Jun-Hyung Park, SangKeun Lee, SungHo Kim, Yerim Oh","submitted_at":"2025-06-09T04:59:13Z","abstract_excerpt":"While language models are increasingly utilized in materials science, typical models rely on frequency-centric tokenization methods originally developed for natural language processing. However, these methods frequently produce excessive fragmentation and semantic loss, failing to maintain the structural and semantic integrity of material concepts. To address this issue, we propose MATTER, a novel tokenization approach that integrates material knowledge into tokenization. Based on MatDetector trained on our materials knowledge base and a re-ranking method prioritizing material concepts in toke"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11115","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/2506.11115/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":"2026-07-05T11:20:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4suD7vSbRPYusWPMRvR8F4cpCe9xGKsLJOW9NC1xmwrii6vJb1EkF2NJxWzC+YoibCumzGBwHWcOgSmmUHH8DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T15:30:05.897713Z"},"content_sha256":"4bc1437ac2276e764a635782bc6285596c3c542ca679a7541526a05d5d775139","schema_version":"1.0","event_id":"sha256:4bc1437ac2276e764a635782bc6285596c3c542ca679a7541526a05d5d775139"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G6H6DZYRO7HLX4QP2PWEG4SDXF/bundle.json","state_url":"https://pith.science/pith/G6H6DZYRO7HLX4QP2PWEG4SDXF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G6H6DZYRO7HLX4QP2PWEG4SDXF/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":"2026-08-09T15:30:05Z","links":{"resolver":"https://pith.science/pith/G6H6DZYRO7HLX4QP2PWEG4SDXF","bundle":"https://pith.science/pith/G6H6DZYRO7HLX4QP2PWEG4SDXF/bundle.json","state":"https://pith.science/pith/G6H6DZYRO7HLX4QP2PWEG4SDXF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G6H6DZYRO7HLX4QP2PWEG4SDXF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:G6H6DZYRO7HLX4QP2PWEG4SDXF","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":"0cfd7ffbe8991c203de26146d02b31dadd2d3ff06a08684354ee8d1783defebb","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T04:59:13Z","title_canon_sha256":"347c1d0caea1881da1ad2b571bcb6f4ac9e5c44f5f2aae94216706e808490f67"},"schema_version":"1.0","source":{"id":"2506.11115","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.11115","created_at":"2026-07-05T11:20:59Z"},{"alias_kind":"arxiv_version","alias_value":"2506.11115v1","created_at":"2026-07-05T11:20:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11115","created_at":"2026-07-05T11:20:59Z"},{"alias_kind":"pith_short_12","alias_value":"G6H6DZYRO7HL","created_at":"2026-07-05T11:20:59Z"},{"alias_kind":"pith_short_16","alias_value":"G6H6DZYRO7HLX4QP","created_at":"2026-07-05T11:20:59Z"},{"alias_kind":"pith_short_8","alias_value":"G6H6DZYR","created_at":"2026-07-05T11:20:59Z"}],"graph_snapshots":[{"event_id":"sha256:4bc1437ac2276e764a635782bc6285596c3c542ca679a7541526a05d5d775139","target":"graph","created_at":"2026-07-05T11:20:59Z","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/2506.11115/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While language models are increasingly utilized in materials science, typical models rely on frequency-centric tokenization methods originally developed for natural language processing. However, these methods frequently produce excessive fragmentation and semantic loss, failing to maintain the structural and semantic integrity of material concepts. To address this issue, we propose MATTER, a novel tokenization approach that integrates material knowledge into tokenization. Based on MatDetector trained on our materials knowledge base and a re-ranking method prioritizing material concepts in toke","authors_text":"Junho Kim, Jun-Hyung Park, SangKeun Lee, SungHo Kim, Yerim Oh","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T04:59:13Z","title":"Incorporating Domain Knowledge into Materials Tokenization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11115","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:d02303b8eccfb1da45f42dc793e36ffe2ce3e814c2c4418cc34c871bc6bfed67","target":"record","created_at":"2026-07-05T11:20:59Z","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":"0cfd7ffbe8991c203de26146d02b31dadd2d3ff06a08684354ee8d1783defebb","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T04:59:13Z","title_canon_sha256":"347c1d0caea1881da1ad2b571bcb6f4ac9e5c44f5f2aae94216706e808490f67"},"schema_version":"1.0","source":{"id":"2506.11115","kind":"arxiv","version":1}},"canonical_sha256":"378fe1e71177cebbf20fd3ec437243b957356d0d21cbfb5f31b1fef725645fdf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"378fe1e71177cebbf20fd3ec437243b957356d0d21cbfb5f31b1fef725645fdf","first_computed_at":"2026-07-05T11:20:59.679107Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:20:59.679107Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7X2jNfHQzqIWnPOeLxKuEDpzRxqzK0ixBC37lV+Uk+4W0vXTnJVwPQDGRtT43a2euQ5h6UZbqS86eNHBvjIPCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:20:59.679496Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.11115","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d02303b8eccfb1da45f42dc793e36ffe2ce3e814c2c4418cc34c871bc6bfed67","sha256:4bc1437ac2276e764a635782bc6285596c3c542ca679a7541526a05d5d775139"],"state_sha256":"0761f8a70fcd834ae62c7aaae1373adb3a25d80281d5a3fac7c454b5b9c0edee"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N6r/fymX/nD5+uvoyOTqGdR6S0ZwIkSUPj8ZZaarc8EIO3p3Oap/wdw5+31m8qIqErirLKV3ctHCeamty43HCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T15:30:05.903005Z","bundle_sha256":"89f69e4ab7fa4da5a6a095cbfc313cae2bc1bbe44991e41fe1829a3223b52791"}}