{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TISDN3LEQIYTO6NWWHHFOEJVEU","short_pith_number":"pith:TISDN3LE","schema_version":"1.0","canonical_sha256":"9a2436ed6482313779b6b1ce571135250ee0c610c65b5a0dc9e39a5aa045883c","source":{"kind":"arxiv","id":"2506.14583","version":1},"attestation_state":"computed","paper":{"title":"Synthetic Data Augmentation for Table Detection: Re-evaluating TableNet's Performance with Automatically Generated Document Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Andreas Fischer, Krishna Sahukara, Zineddine Bettouche","submitted_at":"2025-06-17T14:41:31Z","abstract_excerpt":"Document pages captured by smartphones or scanners often contain tables, yet manual extraction is slow and error-prone. We introduce an automated LaTeX-based pipeline that synthesizes realistic two-column pages with visually diverse table layouts and aligned ground-truth masks. The generated corpus augments the real-world Marmot benchmark and enables a systematic resolution study of TableNet. Training TableNet on our synthetic data achieves a pixel-wise XOR error of 4.04% on our synthetic test set with a 256x256 input resolution, and 4.33% with 1024x1024. The best performance on the Marmot ben"},"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":"2506.14583","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-17T14:41:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2e131db498d86dc13267d5455146d3f8481cdd033e3902ad4dbb19ee017d52e7","abstract_canon_sha256":"fddccaa8f2e0bdf8c62c875844d10c615d0086d72895a4d379ac0a8f385790d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:59.310781Z","signature_b64":"eSJCjc2qsQ0qomJvZ2JNS6uMyhEqkqHVIT0aPgZZNW5U+o2dSmnASHfFhkEDOe/sxMNTeNx0wkGWbtBPV/gVBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a2436ed6482313779b6b1ce571135250ee0c610c65b5a0dc9e39a5aa045883c","last_reissued_at":"2026-07-05T11:22:59.310255Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:59.310255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Synthetic Data Augmentation for Table Detection: Re-evaluating TableNet's Performance with Automatically Generated Document Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Andreas Fischer, Krishna Sahukara, Zineddine Bettouche","submitted_at":"2025-06-17T14:41:31Z","abstract_excerpt":"Document pages captured by smartphones or scanners often contain tables, yet manual extraction is slow and error-prone. We introduce an automated LaTeX-based pipeline that synthesizes realistic two-column pages with visually diverse table layouts and aligned ground-truth masks. The generated corpus augments the real-world Marmot benchmark and enables a systematic resolution study of TableNet. Training TableNet on our synthetic data achieves a pixel-wise XOR error of 4.04% on our synthetic test set with a 256x256 input resolution, and 4.33% with 1024x1024. The best performance on the Marmot ben"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14583","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/2506.14583/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":"2506.14583","created_at":"2026-07-05T11:22:59.310325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.14583v1","created_at":"2026-07-05T11:22:59.310325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14583","created_at":"2026-07-05T11:22:59.310325+00:00"},{"alias_kind":"pith_short_12","alias_value":"TISDN3LEQIYT","created_at":"2026-07-05T11:22:59.310325+00:00"},{"alias_kind":"pith_short_16","alias_value":"TISDN3LEQIYTO6NW","created_at":"2026-07-05T11:22:59.310325+00:00"},{"alias_kind":"pith_short_8","alias_value":"TISDN3LE","created_at":"2026-07-05T11:22:59.310325+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/TISDN3LEQIYTO6NWWHHFOEJVEU","json":"https://pith.science/pith/TISDN3LEQIYTO6NWWHHFOEJVEU.json","graph_json":"https://pith.science/api/pith-number/TISDN3LEQIYTO6NWWHHFOEJVEU/graph.json","events_json":"https://pith.science/api/pith-number/TISDN3LEQIYTO6NWWHHFOEJVEU/events.json","paper":"https://pith.science/paper/TISDN3LE"},"agent_actions":{"view_html":"https://pith.science/pith/TISDN3LEQIYTO6NWWHHFOEJVEU","download_json":"https://pith.science/pith/TISDN3LEQIYTO6NWWHHFOEJVEU.json","view_paper":"https://pith.science/paper/TISDN3LE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.14583&json=true","fetch_graph":"https://pith.science/api/pith-number/TISDN3LEQIYTO6NWWHHFOEJVEU/graph.json","fetch_events":"https://pith.science/api/pith-number/TISDN3LEQIYTO6NWWHHFOEJVEU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TISDN3LEQIYTO6NWWHHFOEJVEU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TISDN3LEQIYTO6NWWHHFOEJVEU/action/storage_attestation","attest_author":"https://pith.science/pith/TISDN3LEQIYTO6NWWHHFOEJVEU/action/author_attestation","sign_citation":"https://pith.science/pith/TISDN3LEQIYTO6NWWHHFOEJVEU/action/citation_signature","submit_replication":"https://pith.science/pith/TISDN3LEQIYTO6NWWHHFOEJVEU/action/replication_record"}},"created_at":"2026-07-05T11:22:59.310325+00:00","updated_at":"2026-07-05T11:22:59.310325+00:00"}