{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:UJJVOX5KVLNEXX5A2PFMP3XJLI","short_pith_number":"pith:UJJVOX5K","canonical_record":{"source":{"id":"2305.03393","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-05T09:38:47Z","cross_cats_sorted":[],"title_canon_sha256":"562920172433b37e895f72a00368c0113ae3bb326c29e8d1fd2d25deee5bbc76","abstract_canon_sha256":"a5ec6e2ad6857edb52ffcbb54c6af49565505bd2488d73211c06d5c2f782eeeb"},"schema_version":"1.0"},"canonical_sha256":"a253575faaaada4bdfa0d3cac7eee95a22edf2cb6493585c33fdfb9d4c921ce1","source":{"kind":"arxiv","id":"2305.03393","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.03393","created_at":"2026-07-05T06:07:22Z"},{"alias_kind":"arxiv_version","alias_value":"2305.03393v1","created_at":"2026-07-05T06:07:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.03393","created_at":"2026-07-05T06:07:22Z"},{"alias_kind":"pith_short_12","alias_value":"UJJVOX5KVLNE","created_at":"2026-07-05T06:07:22Z"},{"alias_kind":"pith_short_16","alias_value":"UJJVOX5KVLNEXX5A","created_at":"2026-07-05T06:07:22Z"},{"alias_kind":"pith_short_8","alias_value":"UJJVOX5K","created_at":"2026-07-05T06:07:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:UJJVOX5KVLNEXX5A2PFMP3XJLI","target":"record","payload":{"canonical_record":{"source":{"id":"2305.03393","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-05T09:38:47Z","cross_cats_sorted":[],"title_canon_sha256":"562920172433b37e895f72a00368c0113ae3bb326c29e8d1fd2d25deee5bbc76","abstract_canon_sha256":"a5ec6e2ad6857edb52ffcbb54c6af49565505bd2488d73211c06d5c2f782eeeb"},"schema_version":"1.0"},"canonical_sha256":"a253575faaaada4bdfa0d3cac7eee95a22edf2cb6493585c33fdfb9d4c921ce1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:07:22.872113Z","signature_b64":"JOzn+1G6tygCDB808JYhIf90saeArrayq7qbyJJ2GJlPe7O+2Hw9ELDd6TGReEvZcXyBOFhtBsios7uoWEwaCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a253575faaaada4bdfa0d3cac7eee95a22edf2cb6493585c33fdfb9d4c921ce1","last_reissued_at":"2026-07-05T06:07:22.871473Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:07:22.871473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.03393","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":"2026-07-05T06:07:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z9BWQZH+iAYc5tLpGws5qdj3pK9/jXOqRlKGm2b3RFXuXf66gIQmlTRG0g6BABAKjz07QswOboovavdhxOncCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-28T23:49:22.560277Z"},"content_sha256":"eda1f71eb60b960705c5708f10c9446872dc38272e32062eb0007b18d232d806","schema_version":"1.0","event_id":"sha256:eda1f71eb60b960705c5708f10c9446872dc38272e32062eb0007b18d232d806"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:UJJVOX5KVLNEXX5A2PFMP3XJLI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimized Table Tokenization for Table Structure Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ahmed Nassar, Christoph Auer, Maksym Lysak, Nikolaos Livathinos, Peter Staar","submitted_at":"2023-05-05T09:38:47Z","abstract_excerpt":"Extracting tables from documents is a crucial task in any document conversion pipeline. Recently, transformer-based models have demonstrated that table-structure can be recognized with impressive accuracy using Image-to-Markup-Sequence (Im2Seq) approaches. Taking only the image of a table, such models predict a sequence of tokens (e.g. in HTML, LaTeX) which represent the structure of the table. Since the token representation of the table structure has a significant impact on the accuracy and run-time performance of any Im2Seq model, we investigate in this paper how table-structure representati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.03393","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/2305.03393/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":"2026-07-05T06:07:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TwF8OyO5haXgi68VhDkLwdJZHGRK84JlAKhHnprALKoJwZX/9fNh3M1DOa60V1hrOkTF3h4cOWtmQyZa7IUIAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-28T23:49:22.560670Z"},"content_sha256":"cb4351eb8b16cf82e84c066802952b9da786cafb19c7852ea12db0620c1fa874","schema_version":"1.0","event_id":"sha256:cb4351eb8b16cf82e84c066802952b9da786cafb19c7852ea12db0620c1fa874"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UJJVOX5KVLNEXX5A2PFMP3XJLI/bundle.json","state_url":"https://pith.science/pith/UJJVOX5KVLNEXX5A2PFMP3XJLI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UJJVOX5KVLNEXX5A2PFMP3XJLI/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":"2026-07-28T23:49:22Z","links":{"resolver":"https://pith.science/pith/UJJVOX5KVLNEXX5A2PFMP3XJLI","bundle":"https://pith.science/pith/UJJVOX5KVLNEXX5A2PFMP3XJLI/bundle.json","state":"https://pith.science/pith/UJJVOX5KVLNEXX5A2PFMP3XJLI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UJJVOX5KVLNEXX5A2PFMP3XJLI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UJJVOX5KVLNEXX5A2PFMP3XJLI","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":"a5ec6e2ad6857edb52ffcbb54c6af49565505bd2488d73211c06d5c2f782eeeb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-05T09:38:47Z","title_canon_sha256":"562920172433b37e895f72a00368c0113ae3bb326c29e8d1fd2d25deee5bbc76"},"schema_version":"1.0","source":{"id":"2305.03393","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.03393","created_at":"2026-07-05T06:07:22Z"},{"alias_kind":"arxiv_version","alias_value":"2305.03393v1","created_at":"2026-07-05T06:07:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.03393","created_at":"2026-07-05T06:07:22Z"},{"alias_kind":"pith_short_12","alias_value":"UJJVOX5KVLNE","created_at":"2026-07-05T06:07:22Z"},{"alias_kind":"pith_short_16","alias_value":"UJJVOX5KVLNEXX5A","created_at":"2026-07-05T06:07:22Z"},{"alias_kind":"pith_short_8","alias_value":"UJJVOX5K","created_at":"2026-07-05T06:07:22Z"}],"graph_snapshots":[{"event_id":"sha256:cb4351eb8b16cf82e84c066802952b9da786cafb19c7852ea12db0620c1fa874","target":"graph","created_at":"2026-07-05T06:07:22Z","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/2305.03393/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Extracting tables from documents is a crucial task in any document conversion pipeline. Recently, transformer-based models have demonstrated that table-structure can be recognized with impressive accuracy using Image-to-Markup-Sequence (Im2Seq) approaches. Taking only the image of a table, such models predict a sequence of tokens (e.g. in HTML, LaTeX) which represent the structure of the table. Since the token representation of the table structure has a significant impact on the accuracy and run-time performance of any Im2Seq model, we investigate in this paper how table-structure representati","authors_text":"Ahmed Nassar, Christoph Auer, Maksym Lysak, Nikolaos Livathinos, Peter Staar","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-05T09:38:47Z","title":"Optimized Table Tokenization for Table Structure Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.03393","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:eda1f71eb60b960705c5708f10c9446872dc38272e32062eb0007b18d232d806","target":"record","created_at":"2026-07-05T06:07:22Z","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":"a5ec6e2ad6857edb52ffcbb54c6af49565505bd2488d73211c06d5c2f782eeeb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-05T09:38:47Z","title_canon_sha256":"562920172433b37e895f72a00368c0113ae3bb326c29e8d1fd2d25deee5bbc76"},"schema_version":"1.0","source":{"id":"2305.03393","kind":"arxiv","version":1}},"canonical_sha256":"a253575faaaada4bdfa0d3cac7eee95a22edf2cb6493585c33fdfb9d4c921ce1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a253575faaaada4bdfa0d3cac7eee95a22edf2cb6493585c33fdfb9d4c921ce1","first_computed_at":"2026-07-05T06:07:22.871473Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:07:22.871473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JOzn+1G6tygCDB808JYhIf90saeArrayq7qbyJJ2GJlPe7O+2Hw9ELDd6TGReEvZcXyBOFhtBsios7uoWEwaCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:07:22.872113Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.03393","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eda1f71eb60b960705c5708f10c9446872dc38272e32062eb0007b18d232d806","sha256:cb4351eb8b16cf82e84c066802952b9da786cafb19c7852ea12db0620c1fa874"],"state_sha256":"e4867f7c50fb9b2e14efabe0c5e6e4f540c49054c7328e3ccf65b73362bb4dc6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ui8MWH7PIfRskXa43l7xnHKjcpKXUnbfV/tSYkZET3eaISOlUQo0vcnFn26rm+q8JFdATqXaIoKdyRxrBdbCCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-28T23:49:22.563150Z","bundle_sha256":"1020961e80d0b377cb0921d76d1590c6e1c25b18253a9fbe0d99f9078bb3d462"}}