{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:Y44M3S75KOG7GONS5APXGUWNHC","short_pith_number":"pith:Y44M3S75","canonical_record":{"source":{"id":"2502.19587","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-26T22:00:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"48ed21f23532b52265d9b4fb0288046c89563fea6c71d522f6ccb4cb4beb8bec","abstract_canon_sha256":"242d1d8ad40992ef4e4098f4aba290b0d1a771499f97217bbb2b4e8e22d89f0e"},"schema_version":"1.0"},"canonical_sha256":"c738cdcbfd538df339b2e81f7352cd38b31bc164991f5209648c34fd3474afc9","source":{"kind":"arxiv","id":"2502.19587","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.19587","created_at":"2026-07-05T11:17:42Z"},{"alias_kind":"arxiv_version","alias_value":"2502.19587v2","created_at":"2026-07-05T11:17:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.19587","created_at":"2026-07-05T11:17:42Z"},{"alias_kind":"pith_short_12","alias_value":"Y44M3S75KOG7","created_at":"2026-07-05T11:17:42Z"},{"alias_kind":"pith_short_16","alias_value":"Y44M3S75KOG7GONS","created_at":"2026-07-05T11:17:42Z"},{"alias_kind":"pith_short_8","alias_value":"Y44M3S75","created_at":"2026-07-05T11:17:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:Y44M3S75KOG7GONS5APXGUWNHC","target":"record","payload":{"canonical_record":{"source":{"id":"2502.19587","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-26T22:00:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"48ed21f23532b52265d9b4fb0288046c89563fea6c71d522f6ccb4cb4beb8bec","abstract_canon_sha256":"242d1d8ad40992ef4e4098f4aba290b0d1a771499f97217bbb2b4e8e22d89f0e"},"schema_version":"1.0"},"canonical_sha256":"c738cdcbfd538df339b2e81f7352cd38b31bc164991f5209648c34fd3474afc9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:42.112826Z","signature_b64":"gNyltOWtGFvmLLTtU2ZlekbAYmKOeBElzW1uSo9R6+uFcXDyYXSHf9KRJ6oMDMfcIchf1TweWHOBBvt1q+h9AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c738cdcbfd538df339b2e81f7352cd38b31bc164991f5209648c34fd3474afc9","last_reissued_at":"2026-07-05T11:17:42.112280Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:42.112280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.19587","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":"2026-07-05T11:17:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m1Wx/YdMFV8+dAsRuTTiCMC+LzWPS3zt2Fur6lckHxp4zb0TJ+MuvT9sVIxY5QcMnCGNPcW/jFgN8rwe432JAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-22T02:51:31.600295Z"},"content_sha256":"a42a589a3e29a52d96f22bb66bd5ea397aeaaa6ed1ecfc9b8ad024e392277ab4","schema_version":"1.0","event_id":"sha256:a42a589a3e29a52d96f22bb66bd5ea397aeaaa6ed1ecfc9b8ad024e392277ab4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:Y44M3S75KOG7GONS5APXGUWNHC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"NeoBERT: A Next-Generation BERT","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"John X. Morris, Lola Le Breton, Mariam El Mezouar, Quentin Fournier, Sarath Chandar","submitted_at":"2025-02-26T22:00:22Z","abstract_excerpt":"Recent innovations in architecture, pre-training, and fine-tuning have led to the remarkable in-context learning and reasoning abilities of large auto-regressive language models such as LLaMA and DeepSeek. In contrast, encoders like BERT and RoBERTa have not seen the same level of progress despite being foundational for many downstream NLP applications. To bridge this gap, we introduce NeoBERT, a next-generation encoder that redefines the capabilities of bidirectional models by integrating state-of-the-art advancements in architecture, modern data, and optimized pre-training methodologies. Neo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.19587","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/2502.19587/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":"2026-07-05T11:17:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fGCxz1kmbp+u0K71ZMIe/pc1fVrY3Uk2rKGdifbTXQqKDcKscmiGmMZnSgawF5gg6NRUIewwfjQ7m2b0IVUHCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-22T02:51:31.600694Z"},"content_sha256":"2a872418fc21f3b970e468b623ee682bce00acb460c857bd62c1174c726b1e5a","schema_version":"1.0","event_id":"sha256:2a872418fc21f3b970e468b623ee682bce00acb460c857bd62c1174c726b1e5a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y44M3S75KOG7GONS5APXGUWNHC/bundle.json","state_url":"https://pith.science/pith/Y44M3S75KOG7GONS5APXGUWNHC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y44M3S75KOG7GONS5APXGUWNHC/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":"2026-07-22T02:51:31Z","links":{"resolver":"https://pith.science/pith/Y44M3S75KOG7GONS5APXGUWNHC","bundle":"https://pith.science/pith/Y44M3S75KOG7GONS5APXGUWNHC/bundle.json","state":"https://pith.science/pith/Y44M3S75KOG7GONS5APXGUWNHC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y44M3S75KOG7GONS5APXGUWNHC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Y44M3S75KOG7GONS5APXGUWNHC","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":"242d1d8ad40992ef4e4098f4aba290b0d1a771499f97217bbb2b4e8e22d89f0e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-26T22:00:22Z","title_canon_sha256":"48ed21f23532b52265d9b4fb0288046c89563fea6c71d522f6ccb4cb4beb8bec"},"schema_version":"1.0","source":{"id":"2502.19587","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.19587","created_at":"2026-07-05T11:17:42Z"},{"alias_kind":"arxiv_version","alias_value":"2502.19587v2","created_at":"2026-07-05T11:17:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.19587","created_at":"2026-07-05T11:17:42Z"},{"alias_kind":"pith_short_12","alias_value":"Y44M3S75KOG7","created_at":"2026-07-05T11:17:42Z"},{"alias_kind":"pith_short_16","alias_value":"Y44M3S75KOG7GONS","created_at":"2026-07-05T11:17:42Z"},{"alias_kind":"pith_short_8","alias_value":"Y44M3S75","created_at":"2026-07-05T11:17:42Z"}],"graph_snapshots":[{"event_id":"sha256:2a872418fc21f3b970e468b623ee682bce00acb460c857bd62c1174c726b1e5a","target":"graph","created_at":"2026-07-05T11:17:42Z","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/2502.19587/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent innovations in architecture, pre-training, and fine-tuning have led to the remarkable in-context learning and reasoning abilities of large auto-regressive language models such as LLaMA and DeepSeek. In contrast, encoders like BERT and RoBERTa have not seen the same level of progress despite being foundational for many downstream NLP applications. To bridge this gap, we introduce NeoBERT, a next-generation encoder that redefines the capabilities of bidirectional models by integrating state-of-the-art advancements in architecture, modern data, and optimized pre-training methodologies. Neo","authors_text":"John X. Morris, Lola Le Breton, Mariam El Mezouar, Quentin Fournier, Sarath Chandar","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-26T22:00:22Z","title":"NeoBERT: A Next-Generation BERT"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.19587","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:a42a589a3e29a52d96f22bb66bd5ea397aeaaa6ed1ecfc9b8ad024e392277ab4","target":"record","created_at":"2026-07-05T11:17:42Z","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":"242d1d8ad40992ef4e4098f4aba290b0d1a771499f97217bbb2b4e8e22d89f0e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-26T22:00:22Z","title_canon_sha256":"48ed21f23532b52265d9b4fb0288046c89563fea6c71d522f6ccb4cb4beb8bec"},"schema_version":"1.0","source":{"id":"2502.19587","kind":"arxiv","version":2}},"canonical_sha256":"c738cdcbfd538df339b2e81f7352cd38b31bc164991f5209648c34fd3474afc9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c738cdcbfd538df339b2e81f7352cd38b31bc164991f5209648c34fd3474afc9","first_computed_at":"2026-07-05T11:17:42.112280Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:42.112280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gNyltOWtGFvmLLTtU2ZlekbAYmKOeBElzW1uSo9R6+uFcXDyYXSHf9KRJ6oMDMfcIchf1TweWHOBBvt1q+h9AA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:42.112826Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.19587","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a42a589a3e29a52d96f22bb66bd5ea397aeaaa6ed1ecfc9b8ad024e392277ab4","sha256:2a872418fc21f3b970e468b623ee682bce00acb460c857bd62c1174c726b1e5a"],"state_sha256":"669287fd20f81de4f73899b308de5ec4307aaa8f403047513b4f3f0349c7668f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OMQDw1xU63WFm78AomDCQV3Kb/hOOsr01MilgXmJ0UNiuuQksTEdVTgatN3YSXe5rMwVRIVeXt8CD8cYs+a9Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-22T02:51:31.602805Z","bundle_sha256":"a5606156ea562aad7584fa2f4b4bbc6b57aee7c8e13728e460ae81736404b1d0"}}