{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CIW7I7EPQEQCGZMBIR74IOE4FC","short_pith_number":"pith:CIW7I7EP","canonical_record":{"source":{"id":"2409.19573","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-29T06:21:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"abb6b5b0c52a545944109a18c833a65595566f1f0e7218ad94a2af4695bc513a","abstract_canon_sha256":"08a6683af5690325c635483c815086d46385b50014f0876496017ef6e6b1d237"},"schema_version":"1.0"},"canonical_sha256":"122df47c8f8120236581447fc4389c289e71e469fbd4c9015f257030fa64c148","source":{"kind":"arxiv","id":"2409.19573","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.19573","created_at":"2026-07-05T12:00:44Z"},{"alias_kind":"arxiv_version","alias_value":"2409.19573v2","created_at":"2026-07-05T12:00:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.19573","created_at":"2026-07-05T12:00:44Z"},{"alias_kind":"pith_short_12","alias_value":"CIW7I7EPQEQC","created_at":"2026-07-05T12:00:44Z"},{"alias_kind":"pith_short_16","alias_value":"CIW7I7EPQEQCGZMB","created_at":"2026-07-05T12:00:44Z"},{"alias_kind":"pith_short_8","alias_value":"CIW7I7EP","created_at":"2026-07-05T12:00:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CIW7I7EPQEQCGZMBIR74IOE4FC","target":"record","payload":{"canonical_record":{"source":{"id":"2409.19573","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-29T06:21:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"abb6b5b0c52a545944109a18c833a65595566f1f0e7218ad94a2af4695bc513a","abstract_canon_sha256":"08a6683af5690325c635483c815086d46385b50014f0876496017ef6e6b1d237"},"schema_version":"1.0"},"canonical_sha256":"122df47c8f8120236581447fc4389c289e71e469fbd4c9015f257030fa64c148","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:44.062330Z","signature_b64":"GpIYa793044m8G9dUlf/NkbFN4rzWsfapvYdtO0DJELkYdce/fSJuhdJNMtZqkEoMMcJnj52Hv9yVazv+/FqDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"122df47c8f8120236581447fc4389c289e71e469fbd4c9015f257030fa64c148","last_reissued_at":"2026-07-05T12:00:44.061770Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:44.061770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.19573","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":"2026-07-05T12:00:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ySDLQl2Memw2ZE3bqltXvyY+ZqKWElxg3V9+zRUjH5bpFGhRMm3f3QmbP7VRemudBrZGbVWW6S9kkqLhU08HCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T10:29:16.869258Z"},"content_sha256":"f752e5cf44028bf3fb752b4525c7823483c06a5e50ad32f261dab5e7702fed7b","schema_version":"1.0","event_id":"sha256:f752e5cf44028bf3fb752b4525c7823483c06a5e50ad32f261dab5e7702fed7b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CIW7I7EPQEQCGZMBIR74IOE4FC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"See then Tell: Enhancing Key Information Extraction with Vision Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chenyu Liu, Jianshu Zhang, Jiefeng Ma, Jun Du, Pengfei Hu, Qing Wang, Shuhang Liu, Zhenrong Zhang","submitted_at":"2024-09-29T06:21:05Z","abstract_excerpt":"In the digital era, the ability to understand visually rich documents that integrate text, complex layouts, and imagery is critical. Traditional Key Information Extraction (KIE) methods primarily rely on Optical Character Recognition (OCR), which often introduces significant latency, computational overhead, and errors. Current advanced image-to-text approaches, which bypass OCR, typically yield plain text outputs without corresponding vision grounding. In this paper, we introduce STNet (See then Tell Net), a novel end-to-end model designed to deliver precise answers with relevant vision ground"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.19573","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/2409.19573/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":"2026-07-05T12:00:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U0ASdpLOllI0ZjKNJaMVNb5I21FIbXYq5ssw/IBQN/PIiOWxqsdfn0gmNkhcBtUECePQwm2xUaxwp4eunHtBBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T10:29:16.870211Z"},"content_sha256":"668cdef8168234c0de9496bb92fd1dd3addd91b6b64ea0f3a6e4e7be40c3def3","schema_version":"1.0","event_id":"sha256:668cdef8168234c0de9496bb92fd1dd3addd91b6b64ea0f3a6e4e7be40c3def3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CIW7I7EPQEQCGZMBIR74IOE4FC/bundle.json","state_url":"https://pith.science/pith/CIW7I7EPQEQCGZMBIR74IOE4FC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CIW7I7EPQEQCGZMBIR74IOE4FC/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":"2026-08-19T10:29:16Z","links":{"resolver":"https://pith.science/pith/CIW7I7EPQEQCGZMBIR74IOE4FC","bundle":"https://pith.science/pith/CIW7I7EPQEQCGZMBIR74IOE4FC/bundle.json","state":"https://pith.science/pith/CIW7I7EPQEQCGZMBIR74IOE4FC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CIW7I7EPQEQCGZMBIR74IOE4FC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CIW7I7EPQEQCGZMBIR74IOE4FC","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":"08a6683af5690325c635483c815086d46385b50014f0876496017ef6e6b1d237","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-29T06:21:05Z","title_canon_sha256":"abb6b5b0c52a545944109a18c833a65595566f1f0e7218ad94a2af4695bc513a"},"schema_version":"1.0","source":{"id":"2409.19573","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.19573","created_at":"2026-07-05T12:00:44Z"},{"alias_kind":"arxiv_version","alias_value":"2409.19573v2","created_at":"2026-07-05T12:00:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.19573","created_at":"2026-07-05T12:00:44Z"},{"alias_kind":"pith_short_12","alias_value":"CIW7I7EPQEQC","created_at":"2026-07-05T12:00:44Z"},{"alias_kind":"pith_short_16","alias_value":"CIW7I7EPQEQCGZMB","created_at":"2026-07-05T12:00:44Z"},{"alias_kind":"pith_short_8","alias_value":"CIW7I7EP","created_at":"2026-07-05T12:00:44Z"}],"graph_snapshots":[{"event_id":"sha256:668cdef8168234c0de9496bb92fd1dd3addd91b6b64ea0f3a6e4e7be40c3def3","target":"graph","created_at":"2026-07-05T12:00:44Z","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/2409.19573/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the digital era, the ability to understand visually rich documents that integrate text, complex layouts, and imagery is critical. Traditional Key Information Extraction (KIE) methods primarily rely on Optical Character Recognition (OCR), which often introduces significant latency, computational overhead, and errors. Current advanced image-to-text approaches, which bypass OCR, typically yield plain text outputs without corresponding vision grounding. In this paper, we introduce STNet (See then Tell Net), a novel end-to-end model designed to deliver precise answers with relevant vision ground","authors_text":"Chenyu Liu, Jianshu Zhang, Jiefeng Ma, Jun Du, Pengfei Hu, Qing Wang, Shuhang Liu, Zhenrong Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-29T06:21:05Z","title":"See then Tell: Enhancing Key Information Extraction with Vision Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.19573","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:f752e5cf44028bf3fb752b4525c7823483c06a5e50ad32f261dab5e7702fed7b","target":"record","created_at":"2026-07-05T12:00:44Z","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":"08a6683af5690325c635483c815086d46385b50014f0876496017ef6e6b1d237","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-29T06:21:05Z","title_canon_sha256":"abb6b5b0c52a545944109a18c833a65595566f1f0e7218ad94a2af4695bc513a"},"schema_version":"1.0","source":{"id":"2409.19573","kind":"arxiv","version":2}},"canonical_sha256":"122df47c8f8120236581447fc4389c289e71e469fbd4c9015f257030fa64c148","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"122df47c8f8120236581447fc4389c289e71e469fbd4c9015f257030fa64c148","first_computed_at":"2026-07-05T12:00:44.061770Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:00:44.061770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GpIYa793044m8G9dUlf/NkbFN4rzWsfapvYdtO0DJELkYdce/fSJuhdJNMtZqkEoMMcJnj52Hv9yVazv+/FqDA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:00:44.062330Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.19573","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f752e5cf44028bf3fb752b4525c7823483c06a5e50ad32f261dab5e7702fed7b","sha256:668cdef8168234c0de9496bb92fd1dd3addd91b6b64ea0f3a6e4e7be40c3def3"],"state_sha256":"a503df69ce0bb8dd825fa1c5b11401f336fb1934fa72c2df1d29f4802ff615fd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nRBIn4NNnrDywJd2IUwnrFe94Za6KU5yiKLMmTwTzIg6MmreR2RuV2kwsvdnrReTcf/Aa7PtLHYGA1dhjAwIDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T10:29:16.877748Z","bundle_sha256":"912ef5e94bf798fe25de60e1e104e2a1af1b8c82c271d26b84484974c5b399a1"}}