{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:UUIAAANH2PBTSJIWDFEOVVIFH5","short_pith_number":"pith:UUIAAANH","canonical_record":{"source":{"id":"2602.12005","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-12T14:37:25Z","cross_cats_sorted":[],"title_canon_sha256":"060eafd4e213bdc3e5a93c04710c56985a29dec9c70617229e464587e9421a7a","abstract_canon_sha256":"80d47942552fb1692f2ec7667d45948fb3baf80aed9bdee309d1ebb6a314396c"},"schema_version":"1.0"},"canonical_sha256":"a5100001a7d3c33925161948ead5053f6d64806d5d8f2f776a7d7d6e52f13428","source":{"kind":"arxiv","id":"2602.12005","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.12005","created_at":"2026-05-20T00:00:34Z"},{"alias_kind":"arxiv_version","alias_value":"2602.12005v3","created_at":"2026-05-20T00:00:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.12005","created_at":"2026-05-20T00:00:34Z"},{"alias_kind":"pith_short_12","alias_value":"UUIAAANH2PBT","created_at":"2026-05-20T00:00:34Z"},{"alias_kind":"pith_short_16","alias_value":"UUIAAANH2PBTSJIW","created_at":"2026-05-20T00:00:34Z"},{"alias_kind":"pith_short_8","alias_value":"UUIAAANH","created_at":"2026-05-20T00:00:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:UUIAAANH2PBTSJIWDFEOVVIFH5","target":"record","payload":{"canonical_record":{"source":{"id":"2602.12005","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-12T14:37:25Z","cross_cats_sorted":[],"title_canon_sha256":"060eafd4e213bdc3e5a93c04710c56985a29dec9c70617229e464587e9421a7a","abstract_canon_sha256":"80d47942552fb1692f2ec7667d45948fb3baf80aed9bdee309d1ebb6a314396c"},"schema_version":"1.0"},"canonical_sha256":"a5100001a7d3c33925161948ead5053f6d64806d5d8f2f776a7d7d6e52f13428","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:34.220251Z","signature_b64":"WH5HZ1AU3ui1Al4zcyHL8Syda4Br+/BjQsbVZ/CokC7LszxFnFRrXHoDa9P9Gpvgk2Tn15Jb3oaIEW9l87sYCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5100001a7d3c33925161948ead5053f6d64806d5d8f2f776a7d7d6e52f13428","last_reissued_at":"2026-05-20T00:00:34.219590Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:34.219590Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2602.12005","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:00:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZrStLSLGWOgtgegY48XOnUDBd2lur+r+Nb1g6i8XnQ/TkxPj+GVoQscdLmkO+8wIjpN67HVOM/v5jLLbIoduAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T00:50:01.621363Z"},"content_sha256":"c2c4fd183584b341378614b213039b23340792ef84c55956bf39ac56dfad8d67","schema_version":"1.0","event_id":"sha256:c2c4fd183584b341378614b213039b23340792ef84c55956bf39ac56dfad8d67"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:UUIAAANH2PBTSJIWDFEOVVIFH5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LaCy: What Small Language Models Can and Should Learn is Not Just a Question of Loss","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jo\\~ao Monteiro, Louis B\\'ethune, Marco Cuturi, Michael Kirchhof, Pierre Ablin, Szilvia Ujv\\'ary","submitted_at":"2026-02-12T14:37:25Z","abstract_excerpt":"Language models have consistently grown to compress more world knowledge into their parameters, but the knowledge that can be pretrained into them is upper-bounded by their parameter size. Especially the capacity of Small Language Models (SLMs) is limited, leading to factually incorrect generations. This problem is often mitigated by giving the SLM access to an outside source: the ability to query a larger model, documents, or a database. Under this setting, we study the fundamental question of \\emph{which tokens an SLM can and should learn} during pretraining, versus \\emph{which ones it shoul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.12005","kind":"arxiv","version":3},"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/2602.12005/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":"2026-05-20T00:00:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fpaPk5rzOJwS6Ze0QvQOpKY+EOLQ9AMs0wh/GHjWiXipvogHAio37AvtWqKMyOslKMSB8k1JcNnYi5lSLrkuBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T00:50:01.622142Z"},"content_sha256":"bff185a14f16f79702bcafb654de6c9285110bbd23b1fc5e22c080395ba09ea4","schema_version":"1.0","event_id":"sha256:bff185a14f16f79702bcafb654de6c9285110bbd23b1fc5e22c080395ba09ea4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UUIAAANH2PBTSJIWDFEOVVIFH5/bundle.json","state_url":"https://pith.science/pith/UUIAAANH2PBTSJIWDFEOVVIFH5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UUIAAANH2PBTSJIWDFEOVVIFH5/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":"2026-05-26T00:50:01Z","links":{"resolver":"https://pith.science/pith/UUIAAANH2PBTSJIWDFEOVVIFH5","bundle":"https://pith.science/pith/UUIAAANH2PBTSJIWDFEOVVIFH5/bundle.json","state":"https://pith.science/pith/UUIAAANH2PBTSJIWDFEOVVIFH5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UUIAAANH2PBTSJIWDFEOVVIFH5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UUIAAANH2PBTSJIWDFEOVVIFH5","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":"80d47942552fb1692f2ec7667d45948fb3baf80aed9bdee309d1ebb6a314396c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-12T14:37:25Z","title_canon_sha256":"060eafd4e213bdc3e5a93c04710c56985a29dec9c70617229e464587e9421a7a"},"schema_version":"1.0","source":{"id":"2602.12005","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.12005","created_at":"2026-05-20T00:00:34Z"},{"alias_kind":"arxiv_version","alias_value":"2602.12005v3","created_at":"2026-05-20T00:00:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.12005","created_at":"2026-05-20T00:00:34Z"},{"alias_kind":"pith_short_12","alias_value":"UUIAAANH2PBT","created_at":"2026-05-20T00:00:34Z"},{"alias_kind":"pith_short_16","alias_value":"UUIAAANH2PBTSJIW","created_at":"2026-05-20T00:00:34Z"},{"alias_kind":"pith_short_8","alias_value":"UUIAAANH","created_at":"2026-05-20T00:00:34Z"}],"graph_snapshots":[{"event_id":"sha256:bff185a14f16f79702bcafb654de6c9285110bbd23b1fc5e22c080395ba09ea4","target":"graph","created_at":"2026-05-20T00:00:34Z","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/2602.12005/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models have consistently grown to compress more world knowledge into their parameters, but the knowledge that can be pretrained into them is upper-bounded by their parameter size. Especially the capacity of Small Language Models (SLMs) is limited, leading to factually incorrect generations. This problem is often mitigated by giving the SLM access to an outside source: the ability to query a larger model, documents, or a database. Under this setting, we study the fundamental question of \\emph{which tokens an SLM can and should learn} during pretraining, versus \\emph{which ones it shoul","authors_text":"Jo\\~ao Monteiro, Louis B\\'ethune, Marco Cuturi, Michael Kirchhof, Pierre Ablin, Szilvia Ujv\\'ary","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-12T14:37:25Z","title":"LaCy: What Small Language Models Can and Should Learn is Not Just a Question of Loss"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.12005","kind":"arxiv","version":3},"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:c2c4fd183584b341378614b213039b23340792ef84c55956bf39ac56dfad8d67","target":"record","created_at":"2026-05-20T00:00:34Z","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":"80d47942552fb1692f2ec7667d45948fb3baf80aed9bdee309d1ebb6a314396c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-12T14:37:25Z","title_canon_sha256":"060eafd4e213bdc3e5a93c04710c56985a29dec9c70617229e464587e9421a7a"},"schema_version":"1.0","source":{"id":"2602.12005","kind":"arxiv","version":3}},"canonical_sha256":"a5100001a7d3c33925161948ead5053f6d64806d5d8f2f776a7d7d6e52f13428","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a5100001a7d3c33925161948ead5053f6d64806d5d8f2f776a7d7d6e52f13428","first_computed_at":"2026-05-20T00:00:34.219590Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:00:34.219590Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WH5HZ1AU3ui1Al4zcyHL8Syda4Br+/BjQsbVZ/CokC7LszxFnFRrXHoDa9P9Gpvgk2Tn15Jb3oaIEW9l87sYCQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:00:34.220251Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.12005","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c2c4fd183584b341378614b213039b23340792ef84c55956bf39ac56dfad8d67","sha256:bff185a14f16f79702bcafb654de6c9285110bbd23b1fc5e22c080395ba09ea4"],"state_sha256":"281ea1c8b790d8cdb6cc41cb9d93b6322e4c3f6b1e3549cd421bc4f7e8dd5047"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xqjxnnG9jx/mQ+ZmJblO9sV3D96nXHz2IgruC9678yrR4k6s7zRpgwQ991jCjMmVZtX0/0TRilLT3s/2DX1tDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T00:50:01.626647Z","bundle_sha256":"c11625b704d72631835fba408275f92c3cf524918a7162dc6d163a8b9f455e6a"}}