{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LDTPMLSD7477YEOD2O7OYA7YOY","short_pith_number":"pith:LDTPMLSD","schema_version":"1.0","canonical_sha256":"58e6f62e43ff3ffc11c3d3beec03f87616a5a346ba5a712d6fd59f8dc39c1dfe","source":{"kind":"arxiv","id":"2505.14131","version":1},"attestation_state":"computed","paper":{"title":"Texts or Images? A Fine-grained Analysis on the Effectiveness of Input Representations and Models for Table Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Annemarie Friedrich, Heike Adel, Mohsen Mesgar, Wei Zhou","submitted_at":"2025-05-20T09:36:17Z","abstract_excerpt":"In table question answering (TQA), tables are encoded as either texts or images. Prior work suggests that passing images of tables to multi-modal large language models (MLLMs) performs comparably to or even better than using textual input with large language models (LLMs). However, the lack of controlled setups limits fine-grained distinctions between these approaches. In this paper, we conduct the first controlled study on the effectiveness of several combinations of table representations and models from two perspectives: question complexity and table size. We build a new benchmark based on e"},"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":"2505.14131","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T09:36:17Z","cross_cats_sorted":[],"title_canon_sha256":"a2c03123f5057afd794f4a12fb433064022d807d65caae15cead128d2a2ce99b","abstract_canon_sha256":"0f759763be54027a6de85b5078063e0f924d58dbd3a8ea1ce95bc5101ab7eb63"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:56.644162Z","signature_b64":"YgSBcFERU483s1OiIPp/3E3NX8R2B/NA67c8M/xFOavfMbgaCWrI1s0NyppPFJGRack/JBu2KSVeh+roIWCUDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58e6f62e43ff3ffc11c3d3beec03f87616a5a346ba5a712d6fd59f8dc39c1dfe","last_reissued_at":"2026-07-05T11:05:56.643776Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:56.643776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Texts or Images? A Fine-grained Analysis on the Effectiveness of Input Representations and Models for Table Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Annemarie Friedrich, Heike Adel, Mohsen Mesgar, Wei Zhou","submitted_at":"2025-05-20T09:36:17Z","abstract_excerpt":"In table question answering (TQA), tables are encoded as either texts or images. Prior work suggests that passing images of tables to multi-modal large language models (MLLMs) performs comparably to or even better than using textual input with large language models (LLMs). However, the lack of controlled setups limits fine-grained distinctions between these approaches. In this paper, we conduct the first controlled study on the effectiveness of several combinations of table representations and models from two perspectives: question complexity and table size. We build a new benchmark based on e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14131","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/2505.14131/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":"2505.14131","created_at":"2026-07-05T11:05:56.643833+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.14131v1","created_at":"2026-07-05T11:05:56.643833+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14131","created_at":"2026-07-05T11:05:56.643833+00:00"},{"alias_kind":"pith_short_12","alias_value":"LDTPMLSD7477","created_at":"2026-07-05T11:05:56.643833+00:00"},{"alias_kind":"pith_short_16","alias_value":"LDTPMLSD7477YEOD","created_at":"2026-07-05T11:05:56.643833+00:00"},{"alias_kind":"pith_short_8","alias_value":"LDTPMLSD","created_at":"2026-07-05T11:05:56.643833+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/LDTPMLSD7477YEOD2O7OYA7YOY","json":"https://pith.science/pith/LDTPMLSD7477YEOD2O7OYA7YOY.json","graph_json":"https://pith.science/api/pith-number/LDTPMLSD7477YEOD2O7OYA7YOY/graph.json","events_json":"https://pith.science/api/pith-number/LDTPMLSD7477YEOD2O7OYA7YOY/events.json","paper":"https://pith.science/paper/LDTPMLSD"},"agent_actions":{"view_html":"https://pith.science/pith/LDTPMLSD7477YEOD2O7OYA7YOY","download_json":"https://pith.science/pith/LDTPMLSD7477YEOD2O7OYA7YOY.json","view_paper":"https://pith.science/paper/LDTPMLSD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.14131&json=true","fetch_graph":"https://pith.science/api/pith-number/LDTPMLSD7477YEOD2O7OYA7YOY/graph.json","fetch_events":"https://pith.science/api/pith-number/LDTPMLSD7477YEOD2O7OYA7YOY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LDTPMLSD7477YEOD2O7OYA7YOY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LDTPMLSD7477YEOD2O7OYA7YOY/action/storage_attestation","attest_author":"https://pith.science/pith/LDTPMLSD7477YEOD2O7OYA7YOY/action/author_attestation","sign_citation":"https://pith.science/pith/LDTPMLSD7477YEOD2O7OYA7YOY/action/citation_signature","submit_replication":"https://pith.science/pith/LDTPMLSD7477YEOD2O7OYA7YOY/action/replication_record"}},"created_at":"2026-07-05T11:05:56.643833+00:00","updated_at":"2026-07-05T11:05:56.643833+00:00"}