{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OAO7BMNNIESW5SRS2ANCIFAZ6V","short_pith_number":"pith:OAO7BMNN","canonical_record":{"source":{"id":"2509.10744","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-12T23:22:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f26993624c4c4a30d7ab773bc899dc47b419d8d397949b2fad9f15cfcdac9857","abstract_canon_sha256":"86e9925e79518b141713d8c96971aa1b4d1027e0978313413f9cbaa980fad2d9"},"schema_version":"1.0"},"canonical_sha256":"701df0b1ad41256eca32d01a241419f57bf1ecfdcbe41e75664dab03555beb97","source":{"kind":"arxiv","id":"2509.10744","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.10744","created_at":"2026-07-05T12:11:27Z"},{"alias_kind":"arxiv_version","alias_value":"2509.10744v1","created_at":"2026-07-05T12:11:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.10744","created_at":"2026-07-05T12:11:27Z"},{"alias_kind":"pith_short_12","alias_value":"OAO7BMNNIESW","created_at":"2026-07-05T12:11:27Z"},{"alias_kind":"pith_short_16","alias_value":"OAO7BMNNIESW5SRS","created_at":"2026-07-05T12:11:27Z"},{"alias_kind":"pith_short_8","alias_value":"OAO7BMNN","created_at":"2026-07-05T12:11:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OAO7BMNNIESW5SRS2ANCIFAZ6V","target":"record","payload":{"canonical_record":{"source":{"id":"2509.10744","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-12T23:22:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f26993624c4c4a30d7ab773bc899dc47b419d8d397949b2fad9f15cfcdac9857","abstract_canon_sha256":"86e9925e79518b141713d8c96971aa1b4d1027e0978313413f9cbaa980fad2d9"},"schema_version":"1.0"},"canonical_sha256":"701df0b1ad41256eca32d01a241419f57bf1ecfdcbe41e75664dab03555beb97","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:11:27.292443Z","signature_b64":"RwQODpRg4gX35b6ZFLd+RNoUBVS2n5Esk5LL7zKw5I7nI4qDlvugjhqNo4v98gZEi+xLvEd/sZSBe0CWHhq2Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"701df0b1ad41256eca32d01a241419f57bf1ecfdcbe41e75664dab03555beb97","last_reissued_at":"2026-07-05T12:11:27.291935Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:11:27.291935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.10744","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":"2026-07-05T12:11:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ztTElhU4w13TrYfIeSQ4q268a4rJMXane+Lzpez497i6DwaWKjKNqToFiVm2YE14Fai1ugblpjJ5C/4xpSmNCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T21:59:54.857866Z"},"content_sha256":"f33833e27291ae2ea86ab0adbc424e6f64a30647f610c6adcabfa6180e9fbe14","schema_version":"1.0","event_id":"sha256:f33833e27291ae2ea86ab0adbc424e6f64a30647f610c6adcabfa6180e9fbe14"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OAO7BMNNIESW5SRS2ANCIFAZ6V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Automated MCQA Benchmarking at Scale: Evaluating Reasoning Traces as Retrieval Sources for Domain Adaptation of Small Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Arvind Ramanathan, Franck Cappello, Ian T. Foster, Neil Getty, Ozan Gokdemir, Rick L. Stevens, Robert Underwood, Sandeep Madireddy","submitted_at":"2025-09-12T23:22:49Z","abstract_excerpt":"As scientific knowledge grows at an unprecedented pace, evaluation benchmarks must evolve to reflect new discoveries and ensure language models are tested on current, diverse literature. We propose a scalable, modular framework for generating multiple-choice question-answering (MCQA) benchmarks directly from large corpora of scientific papers. Our pipeline automates every stage of MCQA creation, including PDF parsing, semantic chunking, question generation, and model evaluation. As a case study, we generate more than 16,000 MCQs from 22,000 open-access articles in radiation and cancer biology."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.10744","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/2509.10744/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":"2026-07-05T12:11:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CXyMq1TkAtRhFb1ShOI6q8oOd9DygpTivmFN8S6qGNX81jDfNm+50wzcMO+GsT9OyD/CP7yuyzmw1MakYQyCDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T21:59:54.858402Z"},"content_sha256":"d07f6dcf203ca3cecfcc258be3df3ae775cbef43ded15bcd7c37843b4843b79b","schema_version":"1.0","event_id":"sha256:d07f6dcf203ca3cecfcc258be3df3ae775cbef43ded15bcd7c37843b4843b79b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OAO7BMNNIESW5SRS2ANCIFAZ6V/bundle.json","state_url":"https://pith.science/pith/OAO7BMNNIESW5SRS2ANCIFAZ6V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OAO7BMNNIESW5SRS2ANCIFAZ6V/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":"2026-08-15T21:59:54Z","links":{"resolver":"https://pith.science/pith/OAO7BMNNIESW5SRS2ANCIFAZ6V","bundle":"https://pith.science/pith/OAO7BMNNIESW5SRS2ANCIFAZ6V/bundle.json","state":"https://pith.science/pith/OAO7BMNNIESW5SRS2ANCIFAZ6V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OAO7BMNNIESW5SRS2ANCIFAZ6V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OAO7BMNNIESW5SRS2ANCIFAZ6V","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":"86e9925e79518b141713d8c96971aa1b4d1027e0978313413f9cbaa980fad2d9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-12T23:22:49Z","title_canon_sha256":"f26993624c4c4a30d7ab773bc899dc47b419d8d397949b2fad9f15cfcdac9857"},"schema_version":"1.0","source":{"id":"2509.10744","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.10744","created_at":"2026-07-05T12:11:27Z"},{"alias_kind":"arxiv_version","alias_value":"2509.10744v1","created_at":"2026-07-05T12:11:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.10744","created_at":"2026-07-05T12:11:27Z"},{"alias_kind":"pith_short_12","alias_value":"OAO7BMNNIESW","created_at":"2026-07-05T12:11:27Z"},{"alias_kind":"pith_short_16","alias_value":"OAO7BMNNIESW5SRS","created_at":"2026-07-05T12:11:27Z"},{"alias_kind":"pith_short_8","alias_value":"OAO7BMNN","created_at":"2026-07-05T12:11:27Z"}],"graph_snapshots":[{"event_id":"sha256:d07f6dcf203ca3cecfcc258be3df3ae775cbef43ded15bcd7c37843b4843b79b","target":"graph","created_at":"2026-07-05T12:11:27Z","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/2509.10744/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As scientific knowledge grows at an unprecedented pace, evaluation benchmarks must evolve to reflect new discoveries and ensure language models are tested on current, diverse literature. We propose a scalable, modular framework for generating multiple-choice question-answering (MCQA) benchmarks directly from large corpora of scientific papers. Our pipeline automates every stage of MCQA creation, including PDF parsing, semantic chunking, question generation, and model evaluation. As a case study, we generate more than 16,000 MCQs from 22,000 open-access articles in radiation and cancer biology.","authors_text":"Arvind Ramanathan, Franck Cappello, Ian T. Foster, Neil Getty, Ozan Gokdemir, Rick L. Stevens, Robert Underwood, Sandeep Madireddy","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-12T23:22:49Z","title":"Automated MCQA Benchmarking at Scale: Evaluating Reasoning Traces as Retrieval Sources for Domain Adaptation of Small Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.10744","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:f33833e27291ae2ea86ab0adbc424e6f64a30647f610c6adcabfa6180e9fbe14","target":"record","created_at":"2026-07-05T12:11:27Z","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":"86e9925e79518b141713d8c96971aa1b4d1027e0978313413f9cbaa980fad2d9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-12T23:22:49Z","title_canon_sha256":"f26993624c4c4a30d7ab773bc899dc47b419d8d397949b2fad9f15cfcdac9857"},"schema_version":"1.0","source":{"id":"2509.10744","kind":"arxiv","version":1}},"canonical_sha256":"701df0b1ad41256eca32d01a241419f57bf1ecfdcbe41e75664dab03555beb97","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"701df0b1ad41256eca32d01a241419f57bf1ecfdcbe41e75664dab03555beb97","first_computed_at":"2026-07-05T12:11:27.291935Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:11:27.291935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RwQODpRg4gX35b6ZFLd+RNoUBVS2n5Esk5LL7zKw5I7nI4qDlvugjhqNo4v98gZEi+xLvEd/sZSBe0CWHhq2Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:11:27.292443Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.10744","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f33833e27291ae2ea86ab0adbc424e6f64a30647f610c6adcabfa6180e9fbe14","sha256:d07f6dcf203ca3cecfcc258be3df3ae775cbef43ded15bcd7c37843b4843b79b"],"state_sha256":"5e048318ae47feaf444f3d96e39ad17edd472ae0cb2d896e3143ea15492c7e5f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NLp6LjTnV+I9OcT1hltsD/UZFblcesAGrVm0nVAV+1OsIx0Yy0f8yGiZVBNW7TdlF/cvSwpM1onjc3KJe/DjBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T21:59:54.863665Z","bundle_sha256":"f4e02a4afde5b3febb2c90b4792fdcb091e6ad4137d09ad04ff86001fdd2a113"}}