{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:PV4UABT6UYU3GVGANKHVEYTPES","short_pith_number":"pith:PV4UABT6","schema_version":"1.0","canonical_sha256":"7d7940067ea629b354c06a8f52626f2491b69acdbefc56df268f092c4a73d40d","source":{"kind":"arxiv","id":"2107.04396","version":1},"attestation_state":"computed","paper":{"title":"Multi-Modal Association based Grouping for Form Structure Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Balaji Krishnamurthy, Hiresh Gupta, Mausoom Sarkar, Milan Aggarwal","submitted_at":"2021-07-09T12:49:34Z","abstract_excerpt":"Document structure extraction has been a widely researched area for decades. Recent work in this direction has been deep learning-based, mostly focusing on extracting structure using fully convolution NN through semantic segmentation. In this work, we present a novel multi-modal approach for form structure extraction. Given simple elements such as textruns and widgets, we extract higher-order structures such as TextBlocks, Text Fields, Choice Fields, and Choice Groups, which are essential for information collection in forms. To achieve this, we obtain a local image patch around each low-level "},"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":"2107.04396","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-07-09T12:49:34Z","cross_cats_sorted":[],"title_canon_sha256":"f170498b4c7670050b0a24ccb9d758e3d4dab25f17001fa7ee7726e704ea159f","abstract_canon_sha256":"34d538adca74ac5cf8ea4647f9b233b3f7731362bcb18220ada7c44449749099"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:56:32.934254Z","signature_b64":"tIkySOetQBacowRpU2YXRFAzKEaC3Ahlu2q6ZfT6B6XFJvwNyXld5oOiMwUb4R0nmDkyofKfFdURojLYUMABAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d7940067ea629b354c06a8f52626f2491b69acdbefc56df268f092c4a73d40d","last_reissued_at":"2026-07-05T02:56:32.933858Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:56:32.933858Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Modal Association based Grouping for Form Structure Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Balaji Krishnamurthy, Hiresh Gupta, Mausoom Sarkar, Milan Aggarwal","submitted_at":"2021-07-09T12:49:34Z","abstract_excerpt":"Document structure extraction has been a widely researched area for decades. Recent work in this direction has been deep learning-based, mostly focusing on extracting structure using fully convolution NN through semantic segmentation. In this work, we present a novel multi-modal approach for form structure extraction. Given simple elements such as textruns and widgets, we extract higher-order structures such as TextBlocks, Text Fields, Choice Fields, and Choice Groups, which are essential for information collection in forms. To achieve this, we obtain a local image patch around each low-level "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.04396","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/2107.04396/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":"2107.04396","created_at":"2026-07-05T02:56:32.933919+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.04396v1","created_at":"2026-07-05T02:56:32.933919+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.04396","created_at":"2026-07-05T02:56:32.933919+00:00"},{"alias_kind":"pith_short_12","alias_value":"PV4UABT6UYU3","created_at":"2026-07-05T02:56:32.933919+00:00"},{"alias_kind":"pith_short_16","alias_value":"PV4UABT6UYU3GVGA","created_at":"2026-07-05T02:56:32.933919+00:00"},{"alias_kind":"pith_short_8","alias_value":"PV4UABT6","created_at":"2026-07-05T02:56:32.933919+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.10396","citing_title":"FormStruct-Bench:A Hierarchical and Diagnostic Benchmark for Table-Form Document Structure Recognition","ref_index":2021,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PV4UABT6UYU3GVGANKHVEYTPES","json":"https://pith.science/pith/PV4UABT6UYU3GVGANKHVEYTPES.json","graph_json":"https://pith.science/api/pith-number/PV4UABT6UYU3GVGANKHVEYTPES/graph.json","events_json":"https://pith.science/api/pith-number/PV4UABT6UYU3GVGANKHVEYTPES/events.json","paper":"https://pith.science/paper/PV4UABT6"},"agent_actions":{"view_html":"https://pith.science/pith/PV4UABT6UYU3GVGANKHVEYTPES","download_json":"https://pith.science/pith/PV4UABT6UYU3GVGANKHVEYTPES.json","view_paper":"https://pith.science/paper/PV4UABT6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.04396&json=true","fetch_graph":"https://pith.science/api/pith-number/PV4UABT6UYU3GVGANKHVEYTPES/graph.json","fetch_events":"https://pith.science/api/pith-number/PV4UABT6UYU3GVGANKHVEYTPES/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PV4UABT6UYU3GVGANKHVEYTPES/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PV4UABT6UYU3GVGANKHVEYTPES/action/storage_attestation","attest_author":"https://pith.science/pith/PV4UABT6UYU3GVGANKHVEYTPES/action/author_attestation","sign_citation":"https://pith.science/pith/PV4UABT6UYU3GVGANKHVEYTPES/action/citation_signature","submit_replication":"https://pith.science/pith/PV4UABT6UYU3GVGANKHVEYTPES/action/replication_record"}},"created_at":"2026-07-05T02:56:32.933919+00:00","updated_at":"2026-07-05T02:56:32.933919+00:00"}