{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DBQQLTM74WLKKE6XDHIJZPX656","short_pith_number":"pith:DBQQLTM7","canonical_record":{"source":{"id":"2409.13120","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-19T23:20:49Z","cross_cats_sorted":["cs.AI","cs.CY"],"title_canon_sha256":"3ccb58f108ae0b126a8f9d4b600154ae8beb6fa4592f77ad3d063ddd93bab104","abstract_canon_sha256":"d8fd638cf7e187fb2bd6e917cc80a0353d4deb0466387b5e07e9a383ee551f08"},"schema_version":"1.0"},"canonical_sha256":"186105cd9fe596a513d719d09cbefeefbd7205e54903059c6429ff8d7b9b8e48","source":{"kind":"arxiv","id":"2409.13120","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.13120","created_at":"2026-07-05T09:09:29Z"},{"alias_kind":"arxiv_version","alias_value":"2409.13120v1","created_at":"2026-07-05T09:09:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.13120","created_at":"2026-07-05T09:09:29Z"},{"alias_kind":"pith_short_12","alias_value":"DBQQLTM74WLK","created_at":"2026-07-05T09:09:29Z"},{"alias_kind":"pith_short_16","alias_value":"DBQQLTM74WLKKE6X","created_at":"2026-07-05T09:09:29Z"},{"alias_kind":"pith_short_8","alias_value":"DBQQLTM7","created_at":"2026-07-05T09:09:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DBQQLTM74WLKKE6XDHIJZPX656","target":"record","payload":{"canonical_record":{"source":{"id":"2409.13120","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-19T23:20:49Z","cross_cats_sorted":["cs.AI","cs.CY"],"title_canon_sha256":"3ccb58f108ae0b126a8f9d4b600154ae8beb6fa4592f77ad3d063ddd93bab104","abstract_canon_sha256":"d8fd638cf7e187fb2bd6e917cc80a0353d4deb0466387b5e07e9a383ee551f08"},"schema_version":"1.0"},"canonical_sha256":"186105cd9fe596a513d719d09cbefeefbd7205e54903059c6429ff8d7b9b8e48","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:09:29.396433Z","signature_b64":"r3/oXleVwI1YHjaXxWROiyEZn9K29w/SmcidGmdlcyScpGBu0i6tnNXjDUbxq1gw3NgOsenyqsnUotqzG/h6DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"186105cd9fe596a513d719d09cbefeefbd7205e54903059c6429ff8d7b9b8e48","last_reissued_at":"2026-07-05T09:09:29.395907Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:09:29.395907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.13120","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":"2026-07-05T09:09:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QvR/7lZxo2BOR7hEdpeMeew5Iak4Hl3Eh3VwlaxJ5u1goeEjfFjqC0BfEBNEq2ilacvefE8n1rg/2p40z98nBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:15:01.762454Z"},"content_sha256":"2adfb8a27913697379a7940e9414d6b151737ff2ea629da9d8c0139dd297033b","schema_version":"1.0","event_id":"sha256:2adfb8a27913697379a7940e9414d6b151737ff2ea629da9d8c0139dd297033b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DBQQLTM74WLKKE6XDHIJZPX656","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Are Large Language Models Good Essay Graders?","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CL","authors_text":"Anindita Kundu, Denilson Barbosa","submitted_at":"2024-09-19T23:20:49Z","abstract_excerpt":"We evaluate the effectiveness of Large Language Models (LLMs) in assessing essay quality, focusing on their alignment with human grading. More precisely, we evaluate ChatGPT and Llama in the Automated Essay Scoring (AES) task, a crucial natural language processing (NLP) application in Education. We consider both zero-shot and few-shot learning and different prompting approaches. We compare the numeric grade provided by the LLMs to human rater-provided scores utilizing the ASAP dataset, a well-known benchmark for the AES task. Our research reveals that both LLMs generally assign lower scores co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.13120","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/2409.13120/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":"2026-07-05T09:09:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8ATygYshjlvY1IfYMRcarfjXwbyskfF+vBG9eK8xxbLsiqxr7vGkc7A8gidW1swRPGF/t+zUxAnMDTGDSrpeCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:15:01.763309Z"},"content_sha256":"ac7d09153766ce43cf8a6e5142f700fe71f9058ce331b96fe44c8575416f0192","schema_version":"1.0","event_id":"sha256:ac7d09153766ce43cf8a6e5142f700fe71f9058ce331b96fe44c8575416f0192"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DBQQLTM74WLKKE6XDHIJZPX656/bundle.json","state_url":"https://pith.science/pith/DBQQLTM74WLKKE6XDHIJZPX656/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DBQQLTM74WLKKE6XDHIJZPX656/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":"2026-08-08T18:15:01Z","links":{"resolver":"https://pith.science/pith/DBQQLTM74WLKKE6XDHIJZPX656","bundle":"https://pith.science/pith/DBQQLTM74WLKKE6XDHIJZPX656/bundle.json","state":"https://pith.science/pith/DBQQLTM74WLKKE6XDHIJZPX656/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DBQQLTM74WLKKE6XDHIJZPX656/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DBQQLTM74WLKKE6XDHIJZPX656","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":"d8fd638cf7e187fb2bd6e917cc80a0353d4deb0466387b5e07e9a383ee551f08","cross_cats_sorted":["cs.AI","cs.CY"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-19T23:20:49Z","title_canon_sha256":"3ccb58f108ae0b126a8f9d4b600154ae8beb6fa4592f77ad3d063ddd93bab104"},"schema_version":"1.0","source":{"id":"2409.13120","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.13120","created_at":"2026-07-05T09:09:29Z"},{"alias_kind":"arxiv_version","alias_value":"2409.13120v1","created_at":"2026-07-05T09:09:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.13120","created_at":"2026-07-05T09:09:29Z"},{"alias_kind":"pith_short_12","alias_value":"DBQQLTM74WLK","created_at":"2026-07-05T09:09:29Z"},{"alias_kind":"pith_short_16","alias_value":"DBQQLTM74WLKKE6X","created_at":"2026-07-05T09:09:29Z"},{"alias_kind":"pith_short_8","alias_value":"DBQQLTM7","created_at":"2026-07-05T09:09:29Z"}],"graph_snapshots":[{"event_id":"sha256:ac7d09153766ce43cf8a6e5142f700fe71f9058ce331b96fe44c8575416f0192","target":"graph","created_at":"2026-07-05T09:09:29Z","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/2409.13120/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We evaluate the effectiveness of Large Language Models (LLMs) in assessing essay quality, focusing on their alignment with human grading. More precisely, we evaluate ChatGPT and Llama in the Automated Essay Scoring (AES) task, a crucial natural language processing (NLP) application in Education. We consider both zero-shot and few-shot learning and different prompting approaches. We compare the numeric grade provided by the LLMs to human rater-provided scores utilizing the ASAP dataset, a well-known benchmark for the AES task. Our research reveals that both LLMs generally assign lower scores co","authors_text":"Anindita Kundu, Denilson Barbosa","cross_cats":["cs.AI","cs.CY"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-19T23:20:49Z","title":"Are Large Language Models Good Essay Graders?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.13120","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":"sha256:2adfb8a27913697379a7940e9414d6b151737ff2ea629da9d8c0139dd297033b","target":"record","created_at":"2026-07-05T09:09:29Z","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":"d8fd638cf7e187fb2bd6e917cc80a0353d4deb0466387b5e07e9a383ee551f08","cross_cats_sorted":["cs.AI","cs.CY"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-19T23:20:49Z","title_canon_sha256":"3ccb58f108ae0b126a8f9d4b600154ae8beb6fa4592f77ad3d063ddd93bab104"},"schema_version":"1.0","source":{"id":"2409.13120","kind":"arxiv","version":1}},"canonical_sha256":"186105cd9fe596a513d719d09cbefeefbd7205e54903059c6429ff8d7b9b8e48","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"186105cd9fe596a513d719d09cbefeefbd7205e54903059c6429ff8d7b9b8e48","first_computed_at":"2026-07-05T09:09:29.395907Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:09:29.395907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r3/oXleVwI1YHjaXxWROiyEZn9K29w/SmcidGmdlcyScpGBu0i6tnNXjDUbxq1gw3NgOsenyqsnUotqzG/h6DA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:09:29.396433Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.13120","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2adfb8a27913697379a7940e9414d6b151737ff2ea629da9d8c0139dd297033b","sha256:ac7d09153766ce43cf8a6e5142f700fe71f9058ce331b96fe44c8575416f0192"],"state_sha256":"a627e1d32649d7e045d09a6f5de31a43c25f095c63c1fcb9f88d4fb65a6a54cc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I1p1/TJcwm/0bJdx/LWxzflQB71FevCFWt3dnZ9xl91At0sk7aK6X4J63hkTYRjmmeLkHH0CMqblj9MfDJjVAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T18:15:01.770884Z","bundle_sha256":"47cc2dbb78c6c0ab7876f38d03d735bd7d13d051613a3365cb26994d8407be9d"}}