{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QCFM6J3Q2V2BWXZPQNEBIM5E5L","short_pith_number":"pith:QCFM6J3Q","canonical_record":{"source":{"id":"2411.14215","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-21T15:25:08Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d6b2e02cc3102505fb8abe2636c330ac647a09f4a2cb5407772ccae8aeaccee8","abstract_canon_sha256":"4819f2872a7f73efa7450561e9ffbcb62fb7c03d51b9de9c43bcbb676e326600"},"schema_version":"1.0"},"canonical_sha256":"808acf2770d5741b5f2f83481433a4eadd14a1c23ce5785a99eae801a1bbfa4c","source":{"kind":"arxiv","id":"2411.14215","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14215","created_at":"2026-07-05T09:38:43Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14215v1","created_at":"2026-07-05T09:38:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14215","created_at":"2026-07-05T09:38:43Z"},{"alias_kind":"pith_short_12","alias_value":"QCFM6J3Q2V2B","created_at":"2026-07-05T09:38:43Z"},{"alias_kind":"pith_short_16","alias_value":"QCFM6J3Q2V2BWXZP","created_at":"2026-07-05T09:38:43Z"},{"alias_kind":"pith_short_8","alias_value":"QCFM6J3Q","created_at":"2026-07-05T09:38:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QCFM6J3Q2V2BWXZPQNEBIM5E5L","target":"record","payload":{"canonical_record":{"source":{"id":"2411.14215","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-21T15:25:08Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d6b2e02cc3102505fb8abe2636c330ac647a09f4a2cb5407772ccae8aeaccee8","abstract_canon_sha256":"4819f2872a7f73efa7450561e9ffbcb62fb7c03d51b9de9c43bcbb676e326600"},"schema_version":"1.0"},"canonical_sha256":"808acf2770d5741b5f2f83481433a4eadd14a1c23ce5785a99eae801a1bbfa4c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:43.411685Z","signature_b64":"kKgrqcbKH1fgAkjHKz1KRcw4xqNazZqYJlTZdejLPBoi3ZV/PIWqY4JExw03+wEJFxgzA5ItLccNPu0wcv3zCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"808acf2770d5741b5f2f83481433a4eadd14a1c23ce5785a99eae801a1bbfa4c","last_reissued_at":"2026-07-05T09:38:43.411208Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:43.411208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.14215","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":"2026-07-05T09:38:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Od3ikUd5zBEnKmy9JesvVxXpMwb8k4lEFAPAZ6sG0/l4liw9XEraA43Y+HZtsCJOiaNDGXcbEb9gwgvu2n+ZCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:54:47.182849Z"},"content_sha256":"eb13dd546e38b1cca6012c933e9b9846646004431e7362a506e3c50a2c2da411","schema_version":"1.0","event_id":"sha256:eb13dd546e38b1cca6012c933e9b9846646004431e7362a506e3c50a2c2da411"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QCFM6J3Q2V2BWXZPQNEBIM5E5L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluating the Robustness of Analogical Reasoning in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Martha Lewis, Melanie Mitchell","submitted_at":"2024-11-21T15:25:08Z","abstract_excerpt":"LLMs have performed well on several reasoning benchmarks, including ones that test analogical reasoning abilities. However, there is debate on the extent to which they are performing general abstract reasoning versus employing non-robust processes, e.g., that overly rely on similarity to pre-training data. Here we investigate the robustness of analogy-making abilities previously claimed for LLMs on three of four domains studied by Webb, Holyoak, and Lu (2023): letter-string analogies, digit matrices, and story analogies. For each domain we test humans and GPT models on robustness to variants o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14215","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/2411.14215/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":"2026-07-05T09:38:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tNUFa1k3ESrTSEiJRXMCq8oOu4mvdFZ14P4vF6x+8c6tbaCUDXh+8cGdnz1SRxktP8020OEd8UjreUinZ0H5DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:54:47.183945Z"},"content_sha256":"5229f8df11f71c0008e5c89334869b0f0d93127a9f513b6f2f5d6e51d3b8aa68","schema_version":"1.0","event_id":"sha256:5229f8df11f71c0008e5c89334869b0f0d93127a9f513b6f2f5d6e51d3b8aa68"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QCFM6J3Q2V2BWXZPQNEBIM5E5L/bundle.json","state_url":"https://pith.science/pith/QCFM6J3Q2V2BWXZPQNEBIM5E5L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QCFM6J3Q2V2BWXZPQNEBIM5E5L/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":"2026-08-07T19:54:47Z","links":{"resolver":"https://pith.science/pith/QCFM6J3Q2V2BWXZPQNEBIM5E5L","bundle":"https://pith.science/pith/QCFM6J3Q2V2BWXZPQNEBIM5E5L/bundle.json","state":"https://pith.science/pith/QCFM6J3Q2V2BWXZPQNEBIM5E5L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QCFM6J3Q2V2BWXZPQNEBIM5E5L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QCFM6J3Q2V2BWXZPQNEBIM5E5L","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":"4819f2872a7f73efa7450561e9ffbcb62fb7c03d51b9de9c43bcbb676e326600","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-21T15:25:08Z","title_canon_sha256":"d6b2e02cc3102505fb8abe2636c330ac647a09f4a2cb5407772ccae8aeaccee8"},"schema_version":"1.0","source":{"id":"2411.14215","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14215","created_at":"2026-07-05T09:38:43Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14215v1","created_at":"2026-07-05T09:38:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14215","created_at":"2026-07-05T09:38:43Z"},{"alias_kind":"pith_short_12","alias_value":"QCFM6J3Q2V2B","created_at":"2026-07-05T09:38:43Z"},{"alias_kind":"pith_short_16","alias_value":"QCFM6J3Q2V2BWXZP","created_at":"2026-07-05T09:38:43Z"},{"alias_kind":"pith_short_8","alias_value":"QCFM6J3Q","created_at":"2026-07-05T09:38:43Z"}],"graph_snapshots":[{"event_id":"sha256:5229f8df11f71c0008e5c89334869b0f0d93127a9f513b6f2f5d6e51d3b8aa68","target":"graph","created_at":"2026-07-05T09:38:43Z","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/2411.14215/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLMs have performed well on several reasoning benchmarks, including ones that test analogical reasoning abilities. However, there is debate on the extent to which they are performing general abstract reasoning versus employing non-robust processes, e.g., that overly rely on similarity to pre-training data. Here we investigate the robustness of analogy-making abilities previously claimed for LLMs on three of four domains studied by Webb, Holyoak, and Lu (2023): letter-string analogies, digit matrices, and story analogies. For each domain we test humans and GPT models on robustness to variants o","authors_text":"Martha Lewis, Melanie Mitchell","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-21T15:25:08Z","title":"Evaluating the Robustness of Analogical Reasoning in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14215","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:eb13dd546e38b1cca6012c933e9b9846646004431e7362a506e3c50a2c2da411","target":"record","created_at":"2026-07-05T09:38:43Z","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":"4819f2872a7f73efa7450561e9ffbcb62fb7c03d51b9de9c43bcbb676e326600","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-21T15:25:08Z","title_canon_sha256":"d6b2e02cc3102505fb8abe2636c330ac647a09f4a2cb5407772ccae8aeaccee8"},"schema_version":"1.0","source":{"id":"2411.14215","kind":"arxiv","version":1}},"canonical_sha256":"808acf2770d5741b5f2f83481433a4eadd14a1c23ce5785a99eae801a1bbfa4c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"808acf2770d5741b5f2f83481433a4eadd14a1c23ce5785a99eae801a1bbfa4c","first_computed_at":"2026-07-05T09:38:43.411208Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:38:43.411208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kKgrqcbKH1fgAkjHKz1KRcw4xqNazZqYJlTZdejLPBoi3ZV/PIWqY4JExw03+wEJFxgzA5ItLccNPu0wcv3zCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:38:43.411685Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.14215","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb13dd546e38b1cca6012c933e9b9846646004431e7362a506e3c50a2c2da411","sha256:5229f8df11f71c0008e5c89334869b0f0d93127a9f513b6f2f5d6e51d3b8aa68"],"state_sha256":"e784bcc38c3f6d10133813dcbedd59fda0ba9c90ee94820d21eb3c2da85ee9b3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UdJF4gwBDjaBXrGo3W0IzFci+vOkid3BkEUOtgD8I3n/7kWUS6Z2wGnw9fex6toAqIoIkwr6b7XquSL4HrC3Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T19:54:47.190752Z","bundle_sha256":"d1b5d3627c45adf713c51773bcc80e5037db2c544978a18faba8cb2c976702c7"}}