{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:EN7KHWA7LQ3VBCAFBALRCZU2CC","short_pith_number":"pith:EN7KHWA7","canonical_record":{"source":{"id":"2310.02989","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-10-04T17:26:16Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"ba3dc882d4a0be07a88ce61b4f72acb90bb8aceefb5c01754a9ee92f22e59e31","abstract_canon_sha256":"d363a54128481748d5bc76566f31f6f97eaea939e42ee332b2b95dfeed6b75ac"},"schema_version":"1.0"},"canonical_sha256":"237ea3d81f5c37508805081711669a10bbefc2de8117adda8c9aa6de1b0a422e","source":{"kind":"arxiv","id":"2310.02989","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.02989","created_at":"2026-07-05T09:49:00Z"},{"alias_kind":"arxiv_version","alias_value":"2310.02989v2","created_at":"2026-07-05T09:49:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.02989","created_at":"2026-07-05T09:49:00Z"},{"alias_kind":"pith_short_12","alias_value":"EN7KHWA7LQ3V","created_at":"2026-07-05T09:49:00Z"},{"alias_kind":"pith_short_16","alias_value":"EN7KHWA7LQ3VBCAF","created_at":"2026-07-05T09:49:00Z"},{"alias_kind":"pith_short_8","alias_value":"EN7KHWA7","created_at":"2026-07-05T09:49:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:EN7KHWA7LQ3VBCAFBALRCZU2CC","target":"record","payload":{"canonical_record":{"source":{"id":"2310.02989","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-10-04T17:26:16Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"ba3dc882d4a0be07a88ce61b4f72acb90bb8aceefb5c01754a9ee92f22e59e31","abstract_canon_sha256":"d363a54128481748d5bc76566f31f6f97eaea939e42ee332b2b95dfeed6b75ac"},"schema_version":"1.0"},"canonical_sha256":"237ea3d81f5c37508805081711669a10bbefc2de8117adda8c9aa6de1b0a422e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:00.417158Z","signature_b64":"RUT6/vMtt/Sl8newzY4VQCzGutzqVp0UIQ9y53Pe+IRVUQyG4ZbnE/bmYX8kXPp0pQGVFTv+SYvbW/y6mXEHBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"237ea3d81f5c37508805081711669a10bbefc2de8117adda8c9aa6de1b0a422e","last_reissued_at":"2026-07-05T09:49:00.416631Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:00.416631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.02989","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:49:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K1GyU/rt9dpamrd4O/b2D5Iy/Ufdkm3RmxTBsB8QJlvQ2jFx+CoWc485/FBuWeZEtGb/h0BIWqjxEeivnCKDBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:26:01.114069Z"},"content_sha256":"277f16c2acd023f4f6b6fda6446325f56292e39ca32fea46bd4543041f37086d","schema_version":"1.0","event_id":"sha256:277f16c2acd023f4f6b6fda6446325f56292e39ca32fea46bd4543041f37086d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:EN7KHWA7LQ3VBCAFBALRCZU2CC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"xVal: A Continuous Numerical Tokenization for Scientific Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"stat.ML","authors_text":"Alberto Bietti, Bruno R\\'egaldo-Saint Blancard, Francois Lanusse, Geraud Krawezik, Kyunghyun Cho, Liam Parker, Mariel Pettee, Michael Eickenberg, Michael McCabe, Miles Cranmer, Ruben Ohana, Shirley Ho, Siavash Golkar, Tiberiu Tesileanu","submitted_at":"2023-10-04T17:26:16Z","abstract_excerpt":"Due in part to their discontinuous and discrete default encodings for numbers, Large Language Models (LLMs) have not yet been commonly used to process numerically-dense scientific datasets. Rendering datasets as text, however, could help aggregate diverse and multi-modal scientific data into a single training corpus, thereby potentially facilitating the development of foundation models for science. In this work, we introduce xVal, a strategy for continuously tokenizing numbers within language models that results in a more appropriate inductive bias for scientific applications. By training spec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.02989","kind":"arxiv","version":2},"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/2310.02989/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":"2026-07-05T09:49:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WZte9r1utMWouUc8VOfKDDejhON6uh2qOy4TPfZPhChuLKLC9U8435bgcLQrSKx2nSPRgPshUvz8QKTLaNIBDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:26:01.115072Z"},"content_sha256":"95482462939662ad8e1e798f6a1c7d5678a50685a4bb155b545be9441a3c2725","schema_version":"1.0","event_id":"sha256:95482462939662ad8e1e798f6a1c7d5678a50685a4bb155b545be9441a3c2725"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EN7KHWA7LQ3VBCAFBALRCZU2CC/bundle.json","state_url":"https://pith.science/pith/EN7KHWA7LQ3VBCAFBALRCZU2CC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EN7KHWA7LQ3VBCAFBALRCZU2CC/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":"2026-08-07T18:26:01Z","links":{"resolver":"https://pith.science/pith/EN7KHWA7LQ3VBCAFBALRCZU2CC","bundle":"https://pith.science/pith/EN7KHWA7LQ3VBCAFBALRCZU2CC/bundle.json","state":"https://pith.science/pith/EN7KHWA7LQ3VBCAFBALRCZU2CC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EN7KHWA7LQ3VBCAFBALRCZU2CC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:EN7KHWA7LQ3VBCAFBALRCZU2CC","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":"d363a54128481748d5bc76566f31f6f97eaea939e42ee332b2b95dfeed6b75ac","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-10-04T17:26:16Z","title_canon_sha256":"ba3dc882d4a0be07a88ce61b4f72acb90bb8aceefb5c01754a9ee92f22e59e31"},"schema_version":"1.0","source":{"id":"2310.02989","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.02989","created_at":"2026-07-05T09:49:00Z"},{"alias_kind":"arxiv_version","alias_value":"2310.02989v2","created_at":"2026-07-05T09:49:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.02989","created_at":"2026-07-05T09:49:00Z"},{"alias_kind":"pith_short_12","alias_value":"EN7KHWA7LQ3V","created_at":"2026-07-05T09:49:00Z"},{"alias_kind":"pith_short_16","alias_value":"EN7KHWA7LQ3VBCAF","created_at":"2026-07-05T09:49:00Z"},{"alias_kind":"pith_short_8","alias_value":"EN7KHWA7","created_at":"2026-07-05T09:49:00Z"}],"graph_snapshots":[{"event_id":"sha256:95482462939662ad8e1e798f6a1c7d5678a50685a4bb155b545be9441a3c2725","target":"graph","created_at":"2026-07-05T09:49:00Z","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/2310.02989/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Due in part to their discontinuous and discrete default encodings for numbers, Large Language Models (LLMs) have not yet been commonly used to process numerically-dense scientific datasets. Rendering datasets as text, however, could help aggregate diverse and multi-modal scientific data into a single training corpus, thereby potentially facilitating the development of foundation models for science. In this work, we introduce xVal, a strategy for continuously tokenizing numbers within language models that results in a more appropriate inductive bias for scientific applications. By training spec","authors_text":"Alberto Bietti, Bruno R\\'egaldo-Saint Blancard, Francois Lanusse, Geraud Krawezik, Kyunghyun Cho, Liam Parker, Mariel Pettee, Michael Eickenberg, Michael McCabe, Miles Cranmer, Ruben Ohana, Shirley Ho, Siavash Golkar, Tiberiu Tesileanu","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-10-04T17:26:16Z","title":"xVal: A Continuous Numerical Tokenization for Scientific Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.02989","kind":"arxiv","version":2},"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":"sha256:277f16c2acd023f4f6b6fda6446325f56292e39ca32fea46bd4543041f37086d","target":"record","created_at":"2026-07-05T09:49:00Z","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":"d363a54128481748d5bc76566f31f6f97eaea939e42ee332b2b95dfeed6b75ac","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-10-04T17:26:16Z","title_canon_sha256":"ba3dc882d4a0be07a88ce61b4f72acb90bb8aceefb5c01754a9ee92f22e59e31"},"schema_version":"1.0","source":{"id":"2310.02989","kind":"arxiv","version":2}},"canonical_sha256":"237ea3d81f5c37508805081711669a10bbefc2de8117adda8c9aa6de1b0a422e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"237ea3d81f5c37508805081711669a10bbefc2de8117adda8c9aa6de1b0a422e","first_computed_at":"2026-07-05T09:49:00.416631Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:49:00.416631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RUT6/vMtt/Sl8newzY4VQCzGutzqVp0UIQ9y53Pe+IRVUQyG4ZbnE/bmYX8kXPp0pQGVFTv+SYvbW/y6mXEHBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:49:00.417158Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.02989","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:277f16c2acd023f4f6b6fda6446325f56292e39ca32fea46bd4543041f37086d","sha256:95482462939662ad8e1e798f6a1c7d5678a50685a4bb155b545be9441a3c2725"],"state_sha256":"586504f301a7e77a1c6bf2a63762511c826af9affe872a43937966e3ee7c14c7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"shR6tRvRV0k1mu7NLSml1s5ZvkWdglvFKMj9ripYrLuLtF03oWA+4C09Fijy2zaVcYyEAV+SubdNCzRSMojpDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T18:26:01.128203Z","bundle_sha256":"53972b35d1534cf51d8b3fb53778dd63ab6ad243ce7ce0eb1b1245b5d1c8d2ba"}}