{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:6RGA64QSGP6PQRR5G7OMOUF5SF","short_pith_number":"pith:6RGA64QS","canonical_record":{"source":{"id":"2302.01451","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-02T22:38:23Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"2d3408fb2b2572dc8906d436beded90e5313c9c68b4b1684b02c6445ca9dc41e","abstract_canon_sha256":"a162a864c4dc1c65b48e9626db665efff72ec89fd6cddb01a86573aed5df7444"},"schema_version":"1.0"},"canonical_sha256":"f44c0f721233fcf8463d37dcc750bd91539440b15867af78a94c83f727b8567c","source":{"kind":"arxiv","id":"2302.01451","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.01451","created_at":"2026-07-05T05:41:11Z"},{"alias_kind":"arxiv_version","alias_value":"2302.01451v2","created_at":"2026-07-05T05:41:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.01451","created_at":"2026-07-05T05:41:11Z"},{"alias_kind":"pith_short_12","alias_value":"6RGA64QSGP6P","created_at":"2026-07-05T05:41:11Z"},{"alias_kind":"pith_short_16","alias_value":"6RGA64QSGP6PQRR5","created_at":"2026-07-05T05:41:11Z"},{"alias_kind":"pith_short_8","alias_value":"6RGA64QS","created_at":"2026-07-05T05:41:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:6RGA64QSGP6PQRR5G7OMOUF5SF","target":"record","payload":{"canonical_record":{"source":{"id":"2302.01451","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-02T22:38:23Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"2d3408fb2b2572dc8906d436beded90e5313c9c68b4b1684b02c6445ca9dc41e","abstract_canon_sha256":"a162a864c4dc1c65b48e9626db665efff72ec89fd6cddb01a86573aed5df7444"},"schema_version":"1.0"},"canonical_sha256":"f44c0f721233fcf8463d37dcc750bd91539440b15867af78a94c83f727b8567c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:41:11.634019Z","signature_b64":"7l4Gikjbjft6g8XAY7NFPsim9H7SkA/r4MZiPVnDvEynOaSYGvAdVCIxLvxI7M7vS0qP21rAQ6+BbCc7WY0+CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f44c0f721233fcf8463d37dcc750bd91539440b15867af78a94c83f727b8567c","last_reissued_at":"2026-07-05T05:41:11.633515Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:41:11.633515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.01451","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":"2026-07-05T05:41:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I1JVdqN+aSmmWi+/+zHVaMsTojkhn2CjNhelZSkEjybCOnnu9vEDYP+dmuomK/ON8U3Dp2Pzzpk28XKMh03QCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:17:19.339153Z"},"content_sha256":"999d999bb40e50f411d26119b4d1bd7208aebeaab65ab58f5ba80f18ffda2bec","schema_version":"1.0","event_id":"sha256:999d999bb40e50f411d26119b4d1bd7208aebeaab65ab58f5ba80f18ffda2bec"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:6RGA64QSGP6PQRR5G7OMOUF5SF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CTE: A Dataset for Contextualized Table Extraction","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Andrea Gemelli, Emanuele Vivoli, Simone Marinai","submitted_at":"2023-02-02T22:38:23Z","abstract_excerpt":"Relevant information in documents is often summarized in tables, helping the reader to identify useful facts. Most benchmark datasets support either document layout analysis or table understanding, but lack in providing data to apply both tasks in a unified way. We define the task of Contextualized Table Extraction (CTE), which aims to extract and define the structure of tables considering the textual context of the document. The dataset comprises 75k fully annotated pages of scientific papers, including more than 35k tables. Data are gathered from PubMed Central, merging the information provi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.01451","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/2302.01451/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":"2026-07-05T05:41:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xoTvFGq4+4k3OSsieqHTqC72isaAvizHEt65ydxGg7LwGI+oIkVW7Vmv9HCKiUoqLhgMZdGEm7/gy110AUvRCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:17:19.339647Z"},"content_sha256":"7df9d5894629362b3acbe0f8883cc2b325d6ec20ba7005c20d0831ebc9656b90","schema_version":"1.0","event_id":"sha256:7df9d5894629362b3acbe0f8883cc2b325d6ec20ba7005c20d0831ebc9656b90"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6RGA64QSGP6PQRR5G7OMOUF5SF/bundle.json","state_url":"https://pith.science/pith/6RGA64QSGP6PQRR5G7OMOUF5SF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6RGA64QSGP6PQRR5G7OMOUF5SF/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":"2026-08-04T04:17:19Z","links":{"resolver":"https://pith.science/pith/6RGA64QSGP6PQRR5G7OMOUF5SF","bundle":"https://pith.science/pith/6RGA64QSGP6PQRR5G7OMOUF5SF/bundle.json","state":"https://pith.science/pith/6RGA64QSGP6PQRR5G7OMOUF5SF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6RGA64QSGP6PQRR5G7OMOUF5SF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6RGA64QSGP6PQRR5G7OMOUF5SF","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":"a162a864c4dc1c65b48e9626db665efff72ec89fd6cddb01a86573aed5df7444","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-02T22:38:23Z","title_canon_sha256":"2d3408fb2b2572dc8906d436beded90e5313c9c68b4b1684b02c6445ca9dc41e"},"schema_version":"1.0","source":{"id":"2302.01451","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.01451","created_at":"2026-07-05T05:41:11Z"},{"alias_kind":"arxiv_version","alias_value":"2302.01451v2","created_at":"2026-07-05T05:41:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.01451","created_at":"2026-07-05T05:41:11Z"},{"alias_kind":"pith_short_12","alias_value":"6RGA64QSGP6P","created_at":"2026-07-05T05:41:11Z"},{"alias_kind":"pith_short_16","alias_value":"6RGA64QSGP6PQRR5","created_at":"2026-07-05T05:41:11Z"},{"alias_kind":"pith_short_8","alias_value":"6RGA64QS","created_at":"2026-07-05T05:41:11Z"}],"graph_snapshots":[{"event_id":"sha256:7df9d5894629362b3acbe0f8883cc2b325d6ec20ba7005c20d0831ebc9656b90","target":"graph","created_at":"2026-07-05T05:41:11Z","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/2302.01451/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Relevant information in documents is often summarized in tables, helping the reader to identify useful facts. Most benchmark datasets support either document layout analysis or table understanding, but lack in providing data to apply both tasks in a unified way. We define the task of Contextualized Table Extraction (CTE), which aims to extract and define the structure of tables considering the textual context of the document. The dataset comprises 75k fully annotated pages of scientific papers, including more than 35k tables. Data are gathered from PubMed Central, merging the information provi","authors_text":"Andrea Gemelli, Emanuele Vivoli, Simone Marinai","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-02T22:38:23Z","title":"CTE: A Dataset for Contextualized Table Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.01451","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":"sha256:999d999bb40e50f411d26119b4d1bd7208aebeaab65ab58f5ba80f18ffda2bec","target":"record","created_at":"2026-07-05T05:41:11Z","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":"a162a864c4dc1c65b48e9626db665efff72ec89fd6cddb01a86573aed5df7444","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-02T22:38:23Z","title_canon_sha256":"2d3408fb2b2572dc8906d436beded90e5313c9c68b4b1684b02c6445ca9dc41e"},"schema_version":"1.0","source":{"id":"2302.01451","kind":"arxiv","version":2}},"canonical_sha256":"f44c0f721233fcf8463d37dcc750bd91539440b15867af78a94c83f727b8567c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f44c0f721233fcf8463d37dcc750bd91539440b15867af78a94c83f727b8567c","first_computed_at":"2026-07-05T05:41:11.633515Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:41:11.633515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7l4Gikjbjft6g8XAY7NFPsim9H7SkA/r4MZiPVnDvEynOaSYGvAdVCIxLvxI7M7vS0qP21rAQ6+BbCc7WY0+CA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:41:11.634019Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.01451","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:999d999bb40e50f411d26119b4d1bd7208aebeaab65ab58f5ba80f18ffda2bec","sha256:7df9d5894629362b3acbe0f8883cc2b325d6ec20ba7005c20d0831ebc9656b90"],"state_sha256":"873acbea9624529104b59d4f65c03405834a19ec92a321d268687f0878a48bb3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NGr9Lh0jMIYm3TuGGs+dDfgcnAOOrffQ9NiMk37oiVEYZ9V/pMMkv3A3UgFUBc9OgDZ+OzhAL2wTenrRMPCNDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T04:17:19.344329Z","bundle_sha256":"715145c6762b9a4a4e4d9ff3af3ab49aaee32128e3b03f851cfdb3cb62fed246"}}