{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Q5TO3UEWYJJMLRX35N4MRSBDR3","short_pith_number":"pith:Q5TO3UEW","schema_version":"1.0","canonical_sha256":"8766edd096c252c5c6fbeb78c8c8238edae742d61ddccf17cc17a8137ad5017f","source":{"kind":"arxiv","id":"2606.25491","version":1},"attestation_state":"computed","paper":{"title":"HG-Bench: A Benchmark for Multi-Page Handwritten Answer-Region Grounding in Automated Homework Assessment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Boyan Shi, Canran Xiao, Chuangxin Zhao, Jiali Chen, Ji Qi, Juanzi Li, Jun Xia, Yanling Wang, Yan Wang, Yijian Lu","submitted_at":"2026-06-24T07:18:50Z","abstract_excerpt":"Automated homework assessment depends not only on recognizing student answers, but also on accurately locating where each answer and each intermediate reasoning step appears in noisy, multi-page handwritten work. This paper addresses the missing evaluation setting of page-aware, two-level answer-region grounding: given a sequence of homework page images, a model must localize complete answer regions and their ordered step-level subregions. We introduce HG-Bench, a benchmark of 500 human-annotated K-12 homework samples curated from a 1,489,278-image source pool, with question-level and step-lev"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.25491","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-24T07:18:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"547712735d2c4e7b9040cd598293d6e79536e9282fd5dbb508888a87dd8a80a5","abstract_canon_sha256":"5b385f10a2913fd03f51dc1f32a4a5e4fbd30423f74fcb13d8de622752e789e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T01:18:06.802288Z","signature_b64":"gbXk6BlDqadCNv0jcuOJKUnPWsDvVP3QQNBL89kcio07QONrnfnglqxTwQtl4VQuLaq8UJ8lt8MuFLyRgaqpAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8766edd096c252c5c6fbeb78c8c8238edae742d61ddccf17cc17a8137ad5017f","last_reissued_at":"2026-06-25T01:18:06.801879Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T01:18:06.801879Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HG-Bench: A Benchmark for Multi-Page Handwritten Answer-Region Grounding in Automated Homework Assessment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Boyan Shi, Canran Xiao, Chuangxin Zhao, Jiali Chen, Ji Qi, Juanzi Li, Jun Xia, Yanling Wang, Yan Wang, Yijian Lu","submitted_at":"2026-06-24T07:18:50Z","abstract_excerpt":"Automated homework assessment depends not only on recognizing student answers, but also on accurately locating where each answer and each intermediate reasoning step appears in noisy, multi-page handwritten work. This paper addresses the missing evaluation setting of page-aware, two-level answer-region grounding: given a sequence of homework page images, a model must localize complete answer regions and their ordered step-level subregions. We introduce HG-Bench, a benchmark of 500 human-annotated K-12 homework samples curated from a 1,489,278-image source pool, with question-level and step-lev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25491","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/2606.25491/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.25491","created_at":"2026-06-25T01:18:06.801944+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.25491v1","created_at":"2026-06-25T01:18:06.801944+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25491","created_at":"2026-06-25T01:18:06.801944+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q5TO3UEWYJJM","created_at":"2026-06-25T01:18:06.801944+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q5TO3UEWYJJMLRX3","created_at":"2026-06-25T01:18:06.801944+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q5TO3UEW","created_at":"2026-06-25T01:18:06.801944+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q5TO3UEWYJJMLRX35N4MRSBDR3","json":"https://pith.science/pith/Q5TO3UEWYJJMLRX35N4MRSBDR3.json","graph_json":"https://pith.science/api/pith-number/Q5TO3UEWYJJMLRX35N4MRSBDR3/graph.json","events_json":"https://pith.science/api/pith-number/Q5TO3UEWYJJMLRX35N4MRSBDR3/events.json","paper":"https://pith.science/paper/Q5TO3UEW"},"agent_actions":{"view_html":"https://pith.science/pith/Q5TO3UEWYJJMLRX35N4MRSBDR3","download_json":"https://pith.science/pith/Q5TO3UEWYJJMLRX35N4MRSBDR3.json","view_paper":"https://pith.science/paper/Q5TO3UEW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.25491&json=true","fetch_graph":"https://pith.science/api/pith-number/Q5TO3UEWYJJMLRX35N4MRSBDR3/graph.json","fetch_events":"https://pith.science/api/pith-number/Q5TO3UEWYJJMLRX35N4MRSBDR3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q5TO3UEWYJJMLRX35N4MRSBDR3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q5TO3UEWYJJMLRX35N4MRSBDR3/action/storage_attestation","attest_author":"https://pith.science/pith/Q5TO3UEWYJJMLRX35N4MRSBDR3/action/author_attestation","sign_citation":"https://pith.science/pith/Q5TO3UEWYJJMLRX35N4MRSBDR3/action/citation_signature","submit_replication":"https://pith.science/pith/Q5TO3UEWYJJMLRX35N4MRSBDR3/action/replication_record"}},"created_at":"2026-06-25T01:18:06.801944+00:00","updated_at":"2026-06-25T01:18:06.801944+00:00"}