{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:W7TVENUX45GQWWUYHRB2YLJ2QK","short_pith_number":"pith:W7TVENUX","canonical_record":{"source":{"id":"2505.24477","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2025-05-30T11:26:32Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"44fe117a8d41ce7b0cf6d4195a66efff8c0000d8f3b676ebd2ac17ed21bb9376","abstract_canon_sha256":"210c594d8a579c82934cc69f579c46d2500e1f8fb6d225ee2cdeff2ce31c4a33"},"schema_version":"1.0"},"canonical_sha256":"b7e7523697e74d0b5a983c43ac2d3a8289cd48b3c9bd89d9f4fb6423cf22c2ff","source":{"kind":"arxiv","id":"2505.24477","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24477","created_at":"2026-07-05T11:12:50Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24477v1","created_at":"2026-07-05T11:12:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24477","created_at":"2026-07-05T11:12:50Z"},{"alias_kind":"pith_short_12","alias_value":"W7TVENUX45GQ","created_at":"2026-07-05T11:12:50Z"},{"alias_kind":"pith_short_16","alias_value":"W7TVENUX45GQWWUY","created_at":"2026-07-05T11:12:50Z"},{"alias_kind":"pith_short_8","alias_value":"W7TVENUX","created_at":"2026-07-05T11:12:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:W7TVENUX45GQWWUYHRB2YLJ2QK","target":"record","payload":{"canonical_record":{"source":{"id":"2505.24477","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2025-05-30T11:26:32Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"44fe117a8d41ce7b0cf6d4195a66efff8c0000d8f3b676ebd2ac17ed21bb9376","abstract_canon_sha256":"210c594d8a579c82934cc69f579c46d2500e1f8fb6d225ee2cdeff2ce31c4a33"},"schema_version":"1.0"},"canonical_sha256":"b7e7523697e74d0b5a983c43ac2d3a8289cd48b3c9bd89d9f4fb6423cf22c2ff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:50.654574Z","signature_b64":"GPDFe6WfzTRAjembPayyyoq7iLrqgpFIa9dqqDeLCcA0CuIhLTL7TVKxOy4gfNZ605RHdwtDt+Va2ZL299NQAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7e7523697e74d0b5a983c43ac2d3a8289cd48b3c9bd89d9f4fb6423cf22c2ff","last_reissued_at":"2026-07-05T11:12:50.653878Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:50.653878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.24477","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":"2026-07-05T11:12:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zShIoc/6qNHkY5ChBUaB6wlCuO/fuo+14qumNmtuq/+RUadEgj8o1rA6CIpR8RmA6DodPSwTDaAEyZoQzSnEDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:10:11.155718Z"},"content_sha256":"21451383474b26507372c52fcb80850ba4766ef3ae0907b9cbe1c8d4b32b22d7","schema_version":"1.0","event_id":"sha256:21451383474b26507372c52fcb80850ba4766ef3ae0907b9cbe1c8d4b32b22d7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:W7TVENUX45GQWWUYHRB2YLJ2QK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluating Gemini in an arena for learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CY","authors_text":"Aditya Srikanth Veerubhotla, Aliya Rysbek, Andrea Huber, Ankit Anand, Avishkar Bhoopchand, Brett Wiltshire, Daniel Gillick, Daniel Kasenberg, Eleni Sgouritsa, Gal Elidan, Hengrui Liu, Holger Winnemoeller, Irina Jurenka, James Cohan, Jennifer She, Julia Wilkowski, Kaiz Alarakyia, Kevin R. McKee, Komal Singh, LearnLM Team Google: Abhinit Modi, Lisa Wang, Markus Kunesch, Miruna P\\^islar, Niv Efron, Parsa Mahmoudieh, Pierre-Alexandre Kamienny, Sara Wiltberger, Shakir Mohamed, Shashank Agarwal, Shubham Milind Phal, Sun Jae Lee, Theofilos Strinopoulos, Wei-Jen Ko, Yael Gold-Zamir, Yael Haramaty, Yannis Assael","submitted_at":"2025-05-30T11:26:32Z","abstract_excerpt":"Artificial intelligence (AI) is poised to transform education, but the research community lacks a robust, general benchmark to evaluate AI models for learning. To assess state-of-the-art support for educational use cases, we ran an \"arena for learning\" where educators and pedagogy experts conduct blind, head-to-head, multi-turn comparisons of leading AI models. In particular, $N = 189$ educators drew from their experience to role-play realistic learning use cases, interacting with two models sequentially, after which $N = 206$ experts judged which model better supported the user's learning goa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24477","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/2505.24477/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":"2026-07-05T11:12:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C8GEBA34jxD0T3xiMknjfAdLBNDCVe0obX7bSFkPejo67ECb+eKu23r6dKkJ6QMzG34Rf5KSxcQOz7vh1kx5AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:10:11.156249Z"},"content_sha256":"7805225e4868ef4fa38622913acb8d3bc3494bde7062943981d028b185d6a504","schema_version":"1.0","event_id":"sha256:7805225e4868ef4fa38622913acb8d3bc3494bde7062943981d028b185d6a504"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W7TVENUX45GQWWUYHRB2YLJ2QK/bundle.json","state_url":"https://pith.science/pith/W7TVENUX45GQWWUYHRB2YLJ2QK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W7TVENUX45GQWWUYHRB2YLJ2QK/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":"2026-08-03T22:10:11Z","links":{"resolver":"https://pith.science/pith/W7TVENUX45GQWWUYHRB2YLJ2QK","bundle":"https://pith.science/pith/W7TVENUX45GQWWUYHRB2YLJ2QK/bundle.json","state":"https://pith.science/pith/W7TVENUX45GQWWUYHRB2YLJ2QK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W7TVENUX45GQWWUYHRB2YLJ2QK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:W7TVENUX45GQWWUYHRB2YLJ2QK","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":"210c594d8a579c82934cc69f579c46d2500e1f8fb6d225ee2cdeff2ce31c4a33","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2025-05-30T11:26:32Z","title_canon_sha256":"44fe117a8d41ce7b0cf6d4195a66efff8c0000d8f3b676ebd2ac17ed21bb9376"},"schema_version":"1.0","source":{"id":"2505.24477","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24477","created_at":"2026-07-05T11:12:50Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24477v1","created_at":"2026-07-05T11:12:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24477","created_at":"2026-07-05T11:12:50Z"},{"alias_kind":"pith_short_12","alias_value":"W7TVENUX45GQ","created_at":"2026-07-05T11:12:50Z"},{"alias_kind":"pith_short_16","alias_value":"W7TVENUX45GQWWUY","created_at":"2026-07-05T11:12:50Z"},{"alias_kind":"pith_short_8","alias_value":"W7TVENUX","created_at":"2026-07-05T11:12:50Z"}],"graph_snapshots":[{"event_id":"sha256:7805225e4868ef4fa38622913acb8d3bc3494bde7062943981d028b185d6a504","target":"graph","created_at":"2026-07-05T11:12:50Z","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/2505.24477/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Artificial intelligence (AI) is poised to transform education, but the research community lacks a robust, general benchmark to evaluate AI models for learning. To assess state-of-the-art support for educational use cases, we ran an \"arena for learning\" where educators and pedagogy experts conduct blind, head-to-head, multi-turn comparisons of leading AI models. In particular, $N = 189$ educators drew from their experience to role-play realistic learning use cases, interacting with two models sequentially, after which $N = 206$ experts judged which model better supported the user's learning goa","authors_text":"Aditya Srikanth Veerubhotla, Aliya Rysbek, Andrea Huber, Ankit Anand, Avishkar Bhoopchand, Brett Wiltshire, Daniel Gillick, Daniel Kasenberg, Eleni Sgouritsa, Gal Elidan, Hengrui Liu, Holger Winnemoeller, Irina Jurenka, James Cohan, Jennifer She, Julia Wilkowski, Kaiz Alarakyia, Kevin R. McKee, Komal Singh, LearnLM Team Google: Abhinit Modi, Lisa Wang, Markus Kunesch, Miruna P\\^islar, Niv Efron, Parsa Mahmoudieh, Pierre-Alexandre Kamienny, Sara Wiltberger, Shakir Mohamed, Shashank Agarwal, Shubham Milind Phal, Sun Jae Lee, Theofilos Strinopoulos, Wei-Jen Ko, Yael Gold-Zamir, Yael Haramaty, Yannis Assael","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2025-05-30T11:26:32Z","title":"Evaluating Gemini in an arena for learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24477","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":"sha256:21451383474b26507372c52fcb80850ba4766ef3ae0907b9cbe1c8d4b32b22d7","target":"record","created_at":"2026-07-05T11:12:50Z","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":"210c594d8a579c82934cc69f579c46d2500e1f8fb6d225ee2cdeff2ce31c4a33","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2025-05-30T11:26:32Z","title_canon_sha256":"44fe117a8d41ce7b0cf6d4195a66efff8c0000d8f3b676ebd2ac17ed21bb9376"},"schema_version":"1.0","source":{"id":"2505.24477","kind":"arxiv","version":1}},"canonical_sha256":"b7e7523697e74d0b5a983c43ac2d3a8289cd48b3c9bd89d9f4fb6423cf22c2ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b7e7523697e74d0b5a983c43ac2d3a8289cd48b3c9bd89d9f4fb6423cf22c2ff","first_computed_at":"2026-07-05T11:12:50.653878Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:50.653878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GPDFe6WfzTRAjembPayyyoq7iLrqgpFIa9dqqDeLCcA0CuIhLTL7TVKxOy4gfNZ605RHdwtDt+Va2ZL299NQAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:50.654574Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.24477","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:21451383474b26507372c52fcb80850ba4766ef3ae0907b9cbe1c8d4b32b22d7","sha256:7805225e4868ef4fa38622913acb8d3bc3494bde7062943981d028b185d6a504"],"state_sha256":"1f165a7870fcafa8768d86d2da25694f541a31f2b2c299a3f693ec8e8978066c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TCiJ6ygjvinqtzp0d8hW2mKpvzqC8PB2C1zysQ46WQj54v3rq6t3ZPwa3dJxi93QRxJUzYHn3kzOeGK6w4hODA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T22:10:11.160565Z","bundle_sha256":"4c23c1bd6a7893331d4f83f52fd28db311b9fff527921360de391fa56dbd0af4"}}