{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:BYHZZIR77B7UQYFX3LMSKQ7XII","short_pith_number":"pith:BYHZZIR7","canonical_record":{"source":{"id":"2306.16762","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-29T08:02:23Z","cross_cats_sorted":[],"title_canon_sha256":"c44826501f8e2bc3c67ab6ca3f0796c2d46734e9ed304a22eac5d2dc68bb5e0d","abstract_canon_sha256":"ac59dc34c6505300131716b0952527287df15ab37200cba05f08be3e5b429d7b"},"schema_version":"1.0"},"canonical_sha256":"0e0f9ca23ff87f4860b7dad92543f7422d8293370b8ecbe9e01bd69fca672b96","source":{"kind":"arxiv","id":"2306.16762","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.16762","created_at":"2026-07-05T06:26:09Z"},{"alias_kind":"arxiv_version","alias_value":"2306.16762v1","created_at":"2026-07-05T06:26:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.16762","created_at":"2026-07-05T06:26:09Z"},{"alias_kind":"pith_short_12","alias_value":"BYHZZIR77B7U","created_at":"2026-07-05T06:26:09Z"},{"alias_kind":"pith_short_16","alias_value":"BYHZZIR77B7UQYFX","created_at":"2026-07-05T06:26:09Z"},{"alias_kind":"pith_short_8","alias_value":"BYHZZIR7","created_at":"2026-07-05T06:26:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:BYHZZIR77B7UQYFX3LMSKQ7XII","target":"record","payload":{"canonical_record":{"source":{"id":"2306.16762","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-29T08:02:23Z","cross_cats_sorted":[],"title_canon_sha256":"c44826501f8e2bc3c67ab6ca3f0796c2d46734e9ed304a22eac5d2dc68bb5e0d","abstract_canon_sha256":"ac59dc34c6505300131716b0952527287df15ab37200cba05f08be3e5b429d7b"},"schema_version":"1.0"},"canonical_sha256":"0e0f9ca23ff87f4860b7dad92543f7422d8293370b8ecbe9e01bd69fca672b96","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:26:09.303780Z","signature_b64":"dgB/gZnRb9tSDYn4KNg9A1qO4U4/q+TuuZYhRjFd0LbDkCunk5hqaZsbI8GJrrz8siGMgAUodPwAOeJ0/WbbCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e0f9ca23ff87f4860b7dad92543f7422d8293370b8ecbe9e01bd69fca672b96","last_reissued_at":"2026-07-05T06:26:09.303437Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:26:09.303437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.16762","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":"2026-07-05T06:26:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X+RiAroWDq1HQfgX4rt93LuEN1UGrktTADoOxm45Q2DAhfWfr71W9Iitx1eMcEankw8mHqF0dfZcrwIPl8mDAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:11:09.268944Z"},"content_sha256":"5f9b8af5f1baf36d42de6182d80fe64a8ee82d63707bd504d1ebfd4674e54670","schema_version":"1.0","event_id":"sha256:5f9b8af5f1baf36d42de6182d80fe64a8ee82d63707bd504d1ebfd4674e54670"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:BYHZZIR77B7UQYFX3LMSKQ7XII","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unified Language Representation for Question Answering over Text, Tables, and Images","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bowen Yu, Cheng Fu, Fei Huang, Haiyang Yu, Yongbin Li","submitted_at":"2023-06-29T08:02:23Z","abstract_excerpt":"When trying to answer complex questions, people often rely on multiple sources of information, such as visual, textual, and tabular data. Previous approaches to this problem have focused on designing input features or model structure in the multi-modal space, which is inflexible for cross-modal reasoning or data-efficient training. In this paper, we call for an alternative paradigm, which transforms the images and tables into unified language representations, so that we can simplify the task into a simpler textual QA problem that can be solved using three steps: retrieval, ranking, and generat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.16762","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/2306.16762/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":"2026-07-05T06:26:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gMi0qu5x2Z5AQaquNhLIYMEOqmMCLFJk9qP0yxwr4WonQqvTqJabk72949AEtgW2bRdDasMySbFZ4Ed2++dMAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:11:09.269443Z"},"content_sha256":"9ed06d427f3f035866d1be130fa3390996f6b9452c087453f2d8679bf1a821aa","schema_version":"1.0","event_id":"sha256:9ed06d427f3f035866d1be130fa3390996f6b9452c087453f2d8679bf1a821aa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BYHZZIR77B7UQYFX3LMSKQ7XII/bundle.json","state_url":"https://pith.science/pith/BYHZZIR77B7UQYFX3LMSKQ7XII/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BYHZZIR77B7UQYFX3LMSKQ7XII/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":"2026-08-07T17:11:09Z","links":{"resolver":"https://pith.science/pith/BYHZZIR77B7UQYFX3LMSKQ7XII","bundle":"https://pith.science/pith/BYHZZIR77B7UQYFX3LMSKQ7XII/bundle.json","state":"https://pith.science/pith/BYHZZIR77B7UQYFX3LMSKQ7XII/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BYHZZIR77B7UQYFX3LMSKQ7XII/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BYHZZIR77B7UQYFX3LMSKQ7XII","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":"ac59dc34c6505300131716b0952527287df15ab37200cba05f08be3e5b429d7b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-29T08:02:23Z","title_canon_sha256":"c44826501f8e2bc3c67ab6ca3f0796c2d46734e9ed304a22eac5d2dc68bb5e0d"},"schema_version":"1.0","source":{"id":"2306.16762","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.16762","created_at":"2026-07-05T06:26:09Z"},{"alias_kind":"arxiv_version","alias_value":"2306.16762v1","created_at":"2026-07-05T06:26:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.16762","created_at":"2026-07-05T06:26:09Z"},{"alias_kind":"pith_short_12","alias_value":"BYHZZIR77B7U","created_at":"2026-07-05T06:26:09Z"},{"alias_kind":"pith_short_16","alias_value":"BYHZZIR77B7UQYFX","created_at":"2026-07-05T06:26:09Z"},{"alias_kind":"pith_short_8","alias_value":"BYHZZIR7","created_at":"2026-07-05T06:26:09Z"}],"graph_snapshots":[{"event_id":"sha256:9ed06d427f3f035866d1be130fa3390996f6b9452c087453f2d8679bf1a821aa","target":"graph","created_at":"2026-07-05T06:26:09Z","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/2306.16762/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"When trying to answer complex questions, people often rely on multiple sources of information, such as visual, textual, and tabular data. Previous approaches to this problem have focused on designing input features or model structure in the multi-modal space, which is inflexible for cross-modal reasoning or data-efficient training. In this paper, we call for an alternative paradigm, which transforms the images and tables into unified language representations, so that we can simplify the task into a simpler textual QA problem that can be solved using three steps: retrieval, ranking, and generat","authors_text":"Bowen Yu, Cheng Fu, Fei Huang, Haiyang Yu, Yongbin Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-29T08:02:23Z","title":"Unified Language Representation for Question Answering over Text, Tables, and Images"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.16762","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":"sha256:5f9b8af5f1baf36d42de6182d80fe64a8ee82d63707bd504d1ebfd4674e54670","target":"record","created_at":"2026-07-05T06:26:09Z","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":"ac59dc34c6505300131716b0952527287df15ab37200cba05f08be3e5b429d7b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-29T08:02:23Z","title_canon_sha256":"c44826501f8e2bc3c67ab6ca3f0796c2d46734e9ed304a22eac5d2dc68bb5e0d"},"schema_version":"1.0","source":{"id":"2306.16762","kind":"arxiv","version":1}},"canonical_sha256":"0e0f9ca23ff87f4860b7dad92543f7422d8293370b8ecbe9e01bd69fca672b96","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e0f9ca23ff87f4860b7dad92543f7422d8293370b8ecbe9e01bd69fca672b96","first_computed_at":"2026-07-05T06:26:09.303437Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:26:09.303437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dgB/gZnRb9tSDYn4KNg9A1qO4U4/q+TuuZYhRjFd0LbDkCunk5hqaZsbI8GJrrz8siGMgAUodPwAOeJ0/WbbCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:26:09.303780Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.16762","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5f9b8af5f1baf36d42de6182d80fe64a8ee82d63707bd504d1ebfd4674e54670","sha256:9ed06d427f3f035866d1be130fa3390996f6b9452c087453f2d8679bf1a821aa"],"state_sha256":"b68b821b383caac0ed85da5fa14a6f738d14505b67330593b46633c05e3c0843"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fQEanFGgKhVNjVXGB/gWTc9wx/q44pxWslSX/6duIDfDTFHt5YvWbZ3VzYUYGuFPil0SnGr2dOI2REDEaumDBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T17:11:09.273023Z","bundle_sha256":"1d0bac15075742a1ea4a1010f735e0312a08db963ce368b2662e407fbd7a0418"}}