{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LJZOWPGIU7HBN63D22VNZUIZ7Q","short_pith_number":"pith:LJZOWPGI","canonical_record":{"source":{"id":"2504.01253","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-01T23:45:44Z","cross_cats_sorted":[],"title_canon_sha256":"bb50251fa69f39701bd3fb0a8eaecfac9a9ef9194f00fda1d4aa6b7c2507efb6","abstract_canon_sha256":"7d9ffeae40d72752351ccb55c3fa56fb69bb3f412ad00b41138623645f20f397"},"schema_version":"1.0"},"canonical_sha256":"5a72eb3cc8a7ce16fb63d6aadcd119fc3f65c77c25ba4598ec9eede83e863172","source":{"kind":"arxiv","id":"2504.01253","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.01253","created_at":"2026-07-05T10:43:11Z"},{"alias_kind":"arxiv_version","alias_value":"2504.01253v1","created_at":"2026-07-05T10:43:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.01253","created_at":"2026-07-05T10:43:11Z"},{"alias_kind":"pith_short_12","alias_value":"LJZOWPGIU7HB","created_at":"2026-07-05T10:43:11Z"},{"alias_kind":"pith_short_16","alias_value":"LJZOWPGIU7HBN63D","created_at":"2026-07-05T10:43:11Z"},{"alias_kind":"pith_short_8","alias_value":"LJZOWPGI","created_at":"2026-07-05T10:43:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LJZOWPGIU7HBN63D22VNZUIZ7Q","target":"record","payload":{"canonical_record":{"source":{"id":"2504.01253","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-01T23:45:44Z","cross_cats_sorted":[],"title_canon_sha256":"bb50251fa69f39701bd3fb0a8eaecfac9a9ef9194f00fda1d4aa6b7c2507efb6","abstract_canon_sha256":"7d9ffeae40d72752351ccb55c3fa56fb69bb3f412ad00b41138623645f20f397"},"schema_version":"1.0"},"canonical_sha256":"5a72eb3cc8a7ce16fb63d6aadcd119fc3f65c77c25ba4598ec9eede83e863172","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:11.665177Z","signature_b64":"NF3zZF5typNvJiCb9kEOhtOC7kAWhGWpuETyjwohP402Rw76ENv0qxiQ6dGKXuI/VsKfAYYfj6/PNTY1zv0hBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a72eb3cc8a7ce16fb63d6aadcd119fc3f65c77c25ba4598ec9eede83e863172","last_reissued_at":"2026-07-05T10:43:11.664644Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:11.664644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.01253","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":"2026-07-05T10:43:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ooGMsN/sCJoOYrWNWFNzeoEOL7Hx4R0a9ZACiOD6jRQ7BQwH1xNHfBumK4eSngOBVk7D67ZkZRMfE6AzfyulAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T16:24:51.435603Z"},"content_sha256":"2375fb10813e3199e2af9297d65b99e331b4b36f0a5a1a9aae29be5684f53f9e","schema_version":"1.0","event_id":"sha256:2375fb10813e3199e2af9297d65b99e331b4b36f0a5a1a9aae29be5684f53f9e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LJZOWPGIU7HBN63D22VNZUIZ7Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Grade Guard: A Smart System for Short Answer Automated Grading","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Harsh Vardhan Singh, Niharika Dadu, Romi Banerjee (Indian Institute of Technology Jodhpur)","submitted_at":"2025-04-01T23:45:44Z","abstract_excerpt":"The advent of large language models (LLMs) in the education sector has provided impetus to automate grading short answer questions. LLMs make evaluating short answers very efficient, thus addressing issues like staff shortage. However, in the task of Automated Short Answer Grading (ASAG), LLM responses are influenced by diverse perspectives in their training dataset, leading to inaccuracies in evaluating nuanced or partially correct answers. To address this challenge, we propose a novel framework, Grade Guard.\n  1. To enhance the task-based specialization of the LLMs, the temperature parameter"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.01253","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/2504.01253/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":"2026-07-05T10:43:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yoigh4Maqvfn+iO4MExPHzRbzUvb7KcO7ZPEbn44IkVL1LAdFEjROwLHTc+dpXtsizZLIqqpfBQ8DGUe72ZcAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T16:24:51.436130Z"},"content_sha256":"b9b08dfc6ab62746b74d27c536de2bdaf0de3fcbd7ae93c1fe0598462c543c70","schema_version":"1.0","event_id":"sha256:b9b08dfc6ab62746b74d27c536de2bdaf0de3fcbd7ae93c1fe0598462c543c70"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LJZOWPGIU7HBN63D22VNZUIZ7Q/bundle.json","state_url":"https://pith.science/pith/LJZOWPGIU7HBN63D22VNZUIZ7Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LJZOWPGIU7HBN63D22VNZUIZ7Q/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":"2026-08-10T16:24:51Z","links":{"resolver":"https://pith.science/pith/LJZOWPGIU7HBN63D22VNZUIZ7Q","bundle":"https://pith.science/pith/LJZOWPGIU7HBN63D22VNZUIZ7Q/bundle.json","state":"https://pith.science/pith/LJZOWPGIU7HBN63D22VNZUIZ7Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LJZOWPGIU7HBN63D22VNZUIZ7Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LJZOWPGIU7HBN63D22VNZUIZ7Q","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":"7d9ffeae40d72752351ccb55c3fa56fb69bb3f412ad00b41138623645f20f397","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-01T23:45:44Z","title_canon_sha256":"bb50251fa69f39701bd3fb0a8eaecfac9a9ef9194f00fda1d4aa6b7c2507efb6"},"schema_version":"1.0","source":{"id":"2504.01253","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.01253","created_at":"2026-07-05T10:43:11Z"},{"alias_kind":"arxiv_version","alias_value":"2504.01253v1","created_at":"2026-07-05T10:43:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.01253","created_at":"2026-07-05T10:43:11Z"},{"alias_kind":"pith_short_12","alias_value":"LJZOWPGIU7HB","created_at":"2026-07-05T10:43:11Z"},{"alias_kind":"pith_short_16","alias_value":"LJZOWPGIU7HBN63D","created_at":"2026-07-05T10:43:11Z"},{"alias_kind":"pith_short_8","alias_value":"LJZOWPGI","created_at":"2026-07-05T10:43:11Z"}],"graph_snapshots":[{"event_id":"sha256:b9b08dfc6ab62746b74d27c536de2bdaf0de3fcbd7ae93c1fe0598462c543c70","target":"graph","created_at":"2026-07-05T10:43:11Z","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/2504.01253/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The advent of large language models (LLMs) in the education sector has provided impetus to automate grading short answer questions. LLMs make evaluating short answers very efficient, thus addressing issues like staff shortage. However, in the task of Automated Short Answer Grading (ASAG), LLM responses are influenced by diverse perspectives in their training dataset, leading to inaccuracies in evaluating nuanced or partially correct answers. To address this challenge, we propose a novel framework, Grade Guard.\n  1. To enhance the task-based specialization of the LLMs, the temperature parameter","authors_text":"Harsh Vardhan Singh, Niharika Dadu, Romi Banerjee (Indian Institute of Technology Jodhpur)","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-01T23:45:44Z","title":"Grade Guard: A Smart System for Short Answer Automated Grading"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.01253","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":"sha256:2375fb10813e3199e2af9297d65b99e331b4b36f0a5a1a9aae29be5684f53f9e","target":"record","created_at":"2026-07-05T10:43:11Z","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":"7d9ffeae40d72752351ccb55c3fa56fb69bb3f412ad00b41138623645f20f397","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-01T23:45:44Z","title_canon_sha256":"bb50251fa69f39701bd3fb0a8eaecfac9a9ef9194f00fda1d4aa6b7c2507efb6"},"schema_version":"1.0","source":{"id":"2504.01253","kind":"arxiv","version":1}},"canonical_sha256":"5a72eb3cc8a7ce16fb63d6aadcd119fc3f65c77c25ba4598ec9eede83e863172","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a72eb3cc8a7ce16fb63d6aadcd119fc3f65c77c25ba4598ec9eede83e863172","first_computed_at":"2026-07-05T10:43:11.664644Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:43:11.664644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NF3zZF5typNvJiCb9kEOhtOC7kAWhGWpuETyjwohP402Rw76ENv0qxiQ6dGKXuI/VsKfAYYfj6/PNTY1zv0hBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:43:11.665177Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.01253","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2375fb10813e3199e2af9297d65b99e331b4b36f0a5a1a9aae29be5684f53f9e","sha256:b9b08dfc6ab62746b74d27c536de2bdaf0de3fcbd7ae93c1fe0598462c543c70"],"state_sha256":"0622007356aa5e7b6057682eaaa248baec2dde8e1d310406b63767c04f8cf236"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HO6FWNATjnoclNKL6ObdROR9HPVSC1dw3s8BpA06ATb4bHTTHKOAv2+XiiyZLSvs8wi+rzrTVpvmcmeQ5JRLBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T16:24:51.442093Z","bundle_sha256":"e0f67a0fa213dee7576b7fdb15876a890188b6c41ecf5244dda7d4768e3b1ebd"}}