{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:IGVHLU2TE6AD6O3EVLYOFVBRNY","short_pith_number":"pith:IGVHLU2T","canonical_record":{"source":{"id":"2311.13194","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-22T06:46:37Z","cross_cats_sorted":[],"title_canon_sha256":"4c874b41fe6a57ad41caba039c3cf145c83fc26d025755c2badcfd67617c277d","abstract_canon_sha256":"1e97f13ce34e3fd9d82199f5e037f9c0603d270a3ffd1fb3ae92a27e4a517ca9"},"schema_version":"1.0"},"canonical_sha256":"41aa75d35327803f3b64aaf0e2d4316e30ad129251d4205bac2232a327a41e9e","source":{"kind":"arxiv","id":"2311.13194","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.13194","created_at":"2026-07-05T07:24:21Z"},{"alias_kind":"arxiv_version","alias_value":"2311.13194v2","created_at":"2026-07-05T07:24:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.13194","created_at":"2026-07-05T07:24:21Z"},{"alias_kind":"pith_short_12","alias_value":"IGVHLU2TE6AD","created_at":"2026-07-05T07:24:21Z"},{"alias_kind":"pith_short_16","alias_value":"IGVHLU2TE6AD6O3E","created_at":"2026-07-05T07:24:21Z"},{"alias_kind":"pith_short_8","alias_value":"IGVHLU2T","created_at":"2026-07-05T07:24:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:IGVHLU2TE6AD6O3EVLYOFVBRNY","target":"record","payload":{"canonical_record":{"source":{"id":"2311.13194","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-22T06:46:37Z","cross_cats_sorted":[],"title_canon_sha256":"4c874b41fe6a57ad41caba039c3cf145c83fc26d025755c2badcfd67617c277d","abstract_canon_sha256":"1e97f13ce34e3fd9d82199f5e037f9c0603d270a3ffd1fb3ae92a27e4a517ca9"},"schema_version":"1.0"},"canonical_sha256":"41aa75d35327803f3b64aaf0e2d4316e30ad129251d4205bac2232a327a41e9e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:24:21.380366Z","signature_b64":"KRIcfR3Vd6Cj//k1Wmc1PdbSNADS6a1zJuyugJj+xX2CdSQuHusfRYP842+YJ9tn5iKqGArOVfhGK5pc72waDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41aa75d35327803f3b64aaf0e2d4316e30ad129251d4205bac2232a327a41e9e","last_reissued_at":"2026-07-05T07:24:21.379872Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:24:21.379872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.13194","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":"2026-07-05T07:24:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lefj/HNT9t+H8D9lv8CBg3LSRNoP20m4a54vcW30MCFNm/bV98fehRvxbXlwa15eTLCjA8lkv0hgudyPlfiiDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:24:26.918829Z"},"content_sha256":"3c3a3b28289d77631b636b33a489622f7d932d8a0f5f339a4d43692877606adf","schema_version":"1.0","event_id":"sha256:3c3a3b28289d77631b636b33a489622f7d932d8a0f5f339a4d43692877606adf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:IGVHLU2TE6AD6O3EVLYOFVBRNY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Improving Document Understanding: An Exploration on Text-Grounding via MLLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Feng, Houqiang Li, Keyi Zhou, Wengang Zhou, Yonghui Wang","submitted_at":"2023-11-22T06:46:37Z","abstract_excerpt":"In the field of document understanding, significant advances have been made in the fine-tuning of Multimodal Large Language Models (MLLMs) with instruction-following data. Nevertheless, the potential of text-grounding capability within text-rich scenarios remains underexplored. In this paper, we present a text-grounding document understanding model, termed TGDoc, which addresses this deficiency by enhancing MLLMs with the ability to discern the spatial positioning of text within images. Empirical evidence suggests that text-grounding improves the model's interpretation of textual content, ther"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.13194","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/2311.13194/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":"2026-07-05T07:24:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YNk272pwuhEdo8vtZgJwpbluIgpuXEvsSOZXszGB/8/CPFp0WRoYyxVb+VdMqoHzRaRAmFbbTqDJi413Ic/SBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:24:26.919158Z"},"content_sha256":"8bc8bdb3f9dab032454040cae5db63738be397ec77413c739d4bd0ae512c4cea","schema_version":"1.0","event_id":"sha256:8bc8bdb3f9dab032454040cae5db63738be397ec77413c739d4bd0ae512c4cea"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IGVHLU2TE6AD6O3EVLYOFVBRNY/bundle.json","state_url":"https://pith.science/pith/IGVHLU2TE6AD6O3EVLYOFVBRNY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IGVHLU2TE6AD6O3EVLYOFVBRNY/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":"2026-08-14T19:24:26Z","links":{"resolver":"https://pith.science/pith/IGVHLU2TE6AD6O3EVLYOFVBRNY","bundle":"https://pith.science/pith/IGVHLU2TE6AD6O3EVLYOFVBRNY/bundle.json","state":"https://pith.science/pith/IGVHLU2TE6AD6O3EVLYOFVBRNY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IGVHLU2TE6AD6O3EVLYOFVBRNY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IGVHLU2TE6AD6O3EVLYOFVBRNY","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":"1e97f13ce34e3fd9d82199f5e037f9c0603d270a3ffd1fb3ae92a27e4a517ca9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-22T06:46:37Z","title_canon_sha256":"4c874b41fe6a57ad41caba039c3cf145c83fc26d025755c2badcfd67617c277d"},"schema_version":"1.0","source":{"id":"2311.13194","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.13194","created_at":"2026-07-05T07:24:21Z"},{"alias_kind":"arxiv_version","alias_value":"2311.13194v2","created_at":"2026-07-05T07:24:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.13194","created_at":"2026-07-05T07:24:21Z"},{"alias_kind":"pith_short_12","alias_value":"IGVHLU2TE6AD","created_at":"2026-07-05T07:24:21Z"},{"alias_kind":"pith_short_16","alias_value":"IGVHLU2TE6AD6O3E","created_at":"2026-07-05T07:24:21Z"},{"alias_kind":"pith_short_8","alias_value":"IGVHLU2T","created_at":"2026-07-05T07:24:21Z"}],"graph_snapshots":[{"event_id":"sha256:8bc8bdb3f9dab032454040cae5db63738be397ec77413c739d4bd0ae512c4cea","target":"graph","created_at":"2026-07-05T07:24:21Z","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/2311.13194/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the field of document understanding, significant advances have been made in the fine-tuning of Multimodal Large Language Models (MLLMs) with instruction-following data. Nevertheless, the potential of text-grounding capability within text-rich scenarios remains underexplored. In this paper, we present a text-grounding document understanding model, termed TGDoc, which addresses this deficiency by enhancing MLLMs with the ability to discern the spatial positioning of text within images. Empirical evidence suggests that text-grounding improves the model's interpretation of textual content, ther","authors_text":"Hao Feng, Houqiang Li, Keyi Zhou, Wengang Zhou, Yonghui Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-22T06:46:37Z","title":"Towards Improving Document Understanding: An Exploration on Text-Grounding via MLLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.13194","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":"sha256:3c3a3b28289d77631b636b33a489622f7d932d8a0f5f339a4d43692877606adf","target":"record","created_at":"2026-07-05T07:24:21Z","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":"1e97f13ce34e3fd9d82199f5e037f9c0603d270a3ffd1fb3ae92a27e4a517ca9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-22T06:46:37Z","title_canon_sha256":"4c874b41fe6a57ad41caba039c3cf145c83fc26d025755c2badcfd67617c277d"},"schema_version":"1.0","source":{"id":"2311.13194","kind":"arxiv","version":2}},"canonical_sha256":"41aa75d35327803f3b64aaf0e2d4316e30ad129251d4205bac2232a327a41e9e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"41aa75d35327803f3b64aaf0e2d4316e30ad129251d4205bac2232a327a41e9e","first_computed_at":"2026-07-05T07:24:21.379872Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:24:21.379872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KRIcfR3Vd6Cj//k1Wmc1PdbSNADS6a1zJuyugJj+xX2CdSQuHusfRYP842+YJ9tn5iKqGArOVfhGK5pc72waDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:24:21.380366Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.13194","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3c3a3b28289d77631b636b33a489622f7d932d8a0f5f339a4d43692877606adf","sha256:8bc8bdb3f9dab032454040cae5db63738be397ec77413c739d4bd0ae512c4cea"],"state_sha256":"142fa4695b777da59b091329496f721bf6ca55b8ddc78241b51ebff4ddb5bda1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PiL8W8/5CYdGcvK5tJLeUCjmxeGpcZ5tPIzIlF5nWHUGICxH1ynfmGAtIgHpLbFlLBkgqgKRYhfGmyBeaGf8CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T19:24:26.922696Z","bundle_sha256":"3b36c617cb1ecbfecfe46c4d070d17a6d3145a96a7a85a2cd7daac031d6986ef"}}