{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SFZT2LTUEZPZ4UQNVSBKWGPZAY","short_pith_number":"pith:SFZT2LTU","canonical_record":{"source":{"id":"2405.17336","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-27T16:37:17Z","cross_cats_sorted":[],"title_canon_sha256":"80962eaf18f1f9dd86c0c7a45aea4961179c9ac0d5c9ee18281f816066136cf0","abstract_canon_sha256":"78c5c2cf695508b596bd59fa0eb5151c7cfb09b5759ba2a7121921d384ce4030"},"schema_version":"1.0"},"canonical_sha256":"91733d2e74265f9e520dac82ab19f9060b90fffaacec93c9d062bb9d9d3b0f8d","source":{"kind":"arxiv","id":"2405.17336","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.17336","created_at":"2026-07-05T09:50:47Z"},{"alias_kind":"arxiv_version","alias_value":"2405.17336v2","created_at":"2026-07-05T09:50:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17336","created_at":"2026-07-05T09:50:47Z"},{"alias_kind":"pith_short_12","alias_value":"SFZT2LTUEZPZ","created_at":"2026-07-05T09:50:47Z"},{"alias_kind":"pith_short_16","alias_value":"SFZT2LTUEZPZ4UQN","created_at":"2026-07-05T09:50:47Z"},{"alias_kind":"pith_short_8","alias_value":"SFZT2LTU","created_at":"2026-07-05T09:50:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SFZT2LTUEZPZ4UQNVSBKWGPZAY","target":"record","payload":{"canonical_record":{"source":{"id":"2405.17336","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-27T16:37:17Z","cross_cats_sorted":[],"title_canon_sha256":"80962eaf18f1f9dd86c0c7a45aea4961179c9ac0d5c9ee18281f816066136cf0","abstract_canon_sha256":"78c5c2cf695508b596bd59fa0eb5151c7cfb09b5759ba2a7121921d384ce4030"},"schema_version":"1.0"},"canonical_sha256":"91733d2e74265f9e520dac82ab19f9060b90fffaacec93c9d062bb9d9d3b0f8d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:47.834447Z","signature_b64":"ALzXyBJu7a95TKN+GTifCJD/HEGs1lJQfkblLDOoPLslsZwmAijrXz/TcAembHi39r/+9KqCXRKhe98xJnwhCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91733d2e74265f9e520dac82ab19f9060b90fffaacec93c9d062bb9d9d3b0f8d","last_reissued_at":"2026-07-05T09:50:47.833940Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:47.833940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.17336","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:50:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iwGDIBjtupei/ZlTJ8PJuE20ssJ866wtCK92tNzC8031H0fJL4tMpANt6hTpFoB6MVizH1V8vjrwkZRNDRFbAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:04:36.771728Z"},"content_sha256":"7b9ffa30494b8db3439d09353fc251987a553af91324a8cdc001cce7050f5599","schema_version":"1.0","event_id":"sha256:7b9ffa30494b8db3439d09353fc251987a553af91324a8cdc001cce7050f5599"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SFZT2LTUEZPZ4UQNVSBKWGPZAY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"XFormParser: A Simple and Effective Multimodal Multilingual Semi-structured Form Parser","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fei Liu, Hang Zhang, Jian Yang, Kui Wu, Tao Sun, Tongliang Li, Weixiao Zhou, Xianfu Cheng, Xiang Li, Xiangyuan Guan, Xianjie Wu, Zhoujun Li","submitted_at":"2024-05-27T16:37:17Z","abstract_excerpt":"In the domain of Document AI, parsing semi-structured image form is a crucial Key Information Extraction (KIE) task. The advent of pre-trained multimodal models significantly empowers Document AI frameworks to extract key information from form documents in different formats such as PDF, Word, and images. Nonetheless, form parsing is still encumbered by notable challenges like subpar capabilities in multilingual parsing and diminished recall in industrial contexts in rich text and rich visuals. In this work, we introduce a simple but effective \\textbf{M}ultimodal and \\textbf{M}ultilingual semi-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17336","kind":"arxiv","version":2},"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/2405.17336/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":"2026-07-05T09:50:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oBZLVGZnZyWNiL92ppT6biyPFk8u2EsDDD/KpsqXj6+UMli9nHotue5+IVcbTcAFPqo8XYgEabcL2Lee5XpHDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:04:36.772104Z"},"content_sha256":"b979f85198294b9250d633a2e26ccc6fbaf79a90cd558ee799682d4d4eff4c32","schema_version":"1.0","event_id":"sha256:b979f85198294b9250d633a2e26ccc6fbaf79a90cd558ee799682d4d4eff4c32"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SFZT2LTUEZPZ4UQNVSBKWGPZAY/bundle.json","state_url":"https://pith.science/pith/SFZT2LTUEZPZ4UQNVSBKWGPZAY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SFZT2LTUEZPZ4UQNVSBKWGPZAY/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":"2026-07-07T14:04:36Z","links":{"resolver":"https://pith.science/pith/SFZT2LTUEZPZ4UQNVSBKWGPZAY","bundle":"https://pith.science/pith/SFZT2LTUEZPZ4UQNVSBKWGPZAY/bundle.json","state":"https://pith.science/pith/SFZT2LTUEZPZ4UQNVSBKWGPZAY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SFZT2LTUEZPZ4UQNVSBKWGPZAY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SFZT2LTUEZPZ4UQNVSBKWGPZAY","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":"78c5c2cf695508b596bd59fa0eb5151c7cfb09b5759ba2a7121921d384ce4030","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-27T16:37:17Z","title_canon_sha256":"80962eaf18f1f9dd86c0c7a45aea4961179c9ac0d5c9ee18281f816066136cf0"},"schema_version":"1.0","source":{"id":"2405.17336","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.17336","created_at":"2026-07-05T09:50:47Z"},{"alias_kind":"arxiv_version","alias_value":"2405.17336v2","created_at":"2026-07-05T09:50:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17336","created_at":"2026-07-05T09:50:47Z"},{"alias_kind":"pith_short_12","alias_value":"SFZT2LTUEZPZ","created_at":"2026-07-05T09:50:47Z"},{"alias_kind":"pith_short_16","alias_value":"SFZT2LTUEZPZ4UQN","created_at":"2026-07-05T09:50:47Z"},{"alias_kind":"pith_short_8","alias_value":"SFZT2LTU","created_at":"2026-07-05T09:50:47Z"}],"graph_snapshots":[{"event_id":"sha256:b979f85198294b9250d633a2e26ccc6fbaf79a90cd558ee799682d4d4eff4c32","target":"graph","created_at":"2026-07-05T09:50:47Z","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/2405.17336/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the domain of Document AI, parsing semi-structured image form is a crucial Key Information Extraction (KIE) task. The advent of pre-trained multimodal models significantly empowers Document AI frameworks to extract key information from form documents in different formats such as PDF, Word, and images. Nonetheless, form parsing is still encumbered by notable challenges like subpar capabilities in multilingual parsing and diminished recall in industrial contexts in rich text and rich visuals. In this work, we introduce a simple but effective \\textbf{M}ultimodal and \\textbf{M}ultilingual semi-","authors_text":"Fei Liu, Hang Zhang, Jian Yang, Kui Wu, Tao Sun, Tongliang Li, Weixiao Zhou, Xianfu Cheng, Xiang Li, Xiangyuan Guan, Xianjie Wu, Zhoujun Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-27T16:37:17Z","title":"XFormParser: A Simple and Effective Multimodal Multilingual Semi-structured Form Parser"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17336","kind":"arxiv","version":2},"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":"sha256:7b9ffa30494b8db3439d09353fc251987a553af91324a8cdc001cce7050f5599","target":"record","created_at":"2026-07-05T09:50:47Z","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":"78c5c2cf695508b596bd59fa0eb5151c7cfb09b5759ba2a7121921d384ce4030","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-27T16:37:17Z","title_canon_sha256":"80962eaf18f1f9dd86c0c7a45aea4961179c9ac0d5c9ee18281f816066136cf0"},"schema_version":"1.0","source":{"id":"2405.17336","kind":"arxiv","version":2}},"canonical_sha256":"91733d2e74265f9e520dac82ab19f9060b90fffaacec93c9d062bb9d9d3b0f8d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"91733d2e74265f9e520dac82ab19f9060b90fffaacec93c9d062bb9d9d3b0f8d","first_computed_at":"2026-07-05T09:50:47.833940Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:50:47.833940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ALzXyBJu7a95TKN+GTifCJD/HEGs1lJQfkblLDOoPLslsZwmAijrXz/TcAembHi39r/+9KqCXRKhe98xJnwhCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:50:47.834447Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.17336","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7b9ffa30494b8db3439d09353fc251987a553af91324a8cdc001cce7050f5599","sha256:b979f85198294b9250d633a2e26ccc6fbaf79a90cd558ee799682d4d4eff4c32"],"state_sha256":"82bb3972e0760145f23d7b33eda6ca4cdbccabf1f2ae4e8b44badfad33a0f22c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rR8ZmsB5qiJjh+R0ESlR4LzetnJICWHgigEDcqNb9TvyxDdLCnfsPtcdx+AVFwyxfCV7hucPMCO3JNT0wVMpCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T14:04:36.774504Z","bundle_sha256":"06989c5df3fe19b0a980f1a7f4ec099e9732dd81c627236cb7cf2789cb2f6afc"}}