{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LZUYXTNFOD7NAAK2NC2OPVC6RO","short_pith_number":"pith:LZUYXTNF","canonical_record":{"source":{"id":"2509.07538","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-09T09:16:25Z","cross_cats_sorted":[],"title_canon_sha256":"bdac867f66838267630ac8f9180ca0e3b78402a18fbb208ff499a9cd8c2d7d70","abstract_canon_sha256":"6d5419abfc7836420a78833942ae3732a3d82ec0ed9c9fe5b6e7d7849843a23f"},"schema_version":"1.0"},"canonical_sha256":"5e698bcda570fed0015a68b4e7d45e8baf4552be19cd732f8f9ac3e979655dbb","source":{"kind":"arxiv","id":"2509.07538","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.07538","created_at":"2026-07-05T12:08:08Z"},{"alias_kind":"arxiv_version","alias_value":"2509.07538v2","created_at":"2026-07-05T12:08:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.07538","created_at":"2026-07-05T12:08:08Z"},{"alias_kind":"pith_short_12","alias_value":"LZUYXTNFOD7N","created_at":"2026-07-05T12:08:08Z"},{"alias_kind":"pith_short_16","alias_value":"LZUYXTNFOD7NAAK2","created_at":"2026-07-05T12:08:08Z"},{"alias_kind":"pith_short_8","alias_value":"LZUYXTNF","created_at":"2026-07-05T12:08:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LZUYXTNFOD7NAAK2NC2OPVC6RO","target":"record","payload":{"canonical_record":{"source":{"id":"2509.07538","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-09T09:16:25Z","cross_cats_sorted":[],"title_canon_sha256":"bdac867f66838267630ac8f9180ca0e3b78402a18fbb208ff499a9cd8c2d7d70","abstract_canon_sha256":"6d5419abfc7836420a78833942ae3732a3d82ec0ed9c9fe5b6e7d7849843a23f"},"schema_version":"1.0"},"canonical_sha256":"5e698bcda570fed0015a68b4e7d45e8baf4552be19cd732f8f9ac3e979655dbb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:08:08.831895Z","signature_b64":"T2CL5J0nFXvSqu2LO09Wuze5YHUJDraRydzOkpSBE0H+CdkrV3Cm44tncrkbC9pnsn4eWURkBHR+j/xGUkWnAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e698bcda570fed0015a68b4e7d45e8baf4552be19cd732f8f9ac3e979655dbb","last_reissued_at":"2026-07-05T12:08:08.831306Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:08:08.831306Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.07538","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":"2026-07-05T12:08:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kuwNsk7wxzy1tiXOsnJcE3UcJNdYYTvCGKyWwoBOjLrUU4d9YXN1dBeEpWl/NZA8N1yOi4QRP7j7sNTlvYUzCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:24:39.975172Z"},"content_sha256":"7c6cfd2bf0438b8fd9cd3c4b020da01e7776525817ec6ab307bbcaae8144414e","schema_version":"1.0","event_id":"sha256:7c6cfd2bf0438b8fd9cd3c4b020da01e7776525817ec6ab307bbcaae8144414e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LZUYXTNFOD7NAAK2NC2OPVC6RO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TextlessRAG: End-to-End Visual Document RAG by Speech Without Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingquan Liu, Dexin Wang, Lin Sun, Peijin Xie, Shun Qian, Xiangzheng Zhang","submitted_at":"2025-09-09T09:16:25Z","abstract_excerpt":"Document images encapsulate a wealth of knowledge, while the portability of spoken queries enables broader and flexible application scenarios. Yet, no prior work has explored knowledge base question answering over visual document images with queries provided directly in speech. We propose TextlessRAG, the first end-to-end framework for speech-based question answering over large-scale document images. Unlike prior methods, TextlessRAG eliminates ASR, TTS and OCR, directly interpreting speech, retrieving relevant visual knowledge, and generating answers in a fully textless pipeline. To further b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.07538","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/2509.07538/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":"2026-07-05T12:08:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kNT7WHo732HKV2JX/Tg1AgLHD3+t2dNbar7UK4AZgDwHesX8Uw5zQCzL2wzoZifvadOOzsdldWvwNe0d3bIbAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:24:39.975874Z"},"content_sha256":"2a345dddc425bd4cee570027bb10e5dcb68ae0405e930fa69230370c058aa324","schema_version":"1.0","event_id":"sha256:2a345dddc425bd4cee570027bb10e5dcb68ae0405e930fa69230370c058aa324"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LZUYXTNFOD7NAAK2NC2OPVC6RO/bundle.json","state_url":"https://pith.science/pith/LZUYXTNFOD7NAAK2NC2OPVC6RO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LZUYXTNFOD7NAAK2NC2OPVC6RO/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":"2026-08-05T10:24:39Z","links":{"resolver":"https://pith.science/pith/LZUYXTNFOD7NAAK2NC2OPVC6RO","bundle":"https://pith.science/pith/LZUYXTNFOD7NAAK2NC2OPVC6RO/bundle.json","state":"https://pith.science/pith/LZUYXTNFOD7NAAK2NC2OPVC6RO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LZUYXTNFOD7NAAK2NC2OPVC6RO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LZUYXTNFOD7NAAK2NC2OPVC6RO","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":"6d5419abfc7836420a78833942ae3732a3d82ec0ed9c9fe5b6e7d7849843a23f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-09T09:16:25Z","title_canon_sha256":"bdac867f66838267630ac8f9180ca0e3b78402a18fbb208ff499a9cd8c2d7d70"},"schema_version":"1.0","source":{"id":"2509.07538","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.07538","created_at":"2026-07-05T12:08:08Z"},{"alias_kind":"arxiv_version","alias_value":"2509.07538v2","created_at":"2026-07-05T12:08:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.07538","created_at":"2026-07-05T12:08:08Z"},{"alias_kind":"pith_short_12","alias_value":"LZUYXTNFOD7N","created_at":"2026-07-05T12:08:08Z"},{"alias_kind":"pith_short_16","alias_value":"LZUYXTNFOD7NAAK2","created_at":"2026-07-05T12:08:08Z"},{"alias_kind":"pith_short_8","alias_value":"LZUYXTNF","created_at":"2026-07-05T12:08:08Z"}],"graph_snapshots":[{"event_id":"sha256:2a345dddc425bd4cee570027bb10e5dcb68ae0405e930fa69230370c058aa324","target":"graph","created_at":"2026-07-05T12:08:08Z","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/2509.07538/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Document images encapsulate a wealth of knowledge, while the portability of spoken queries enables broader and flexible application scenarios. Yet, no prior work has explored knowledge base question answering over visual document images with queries provided directly in speech. We propose TextlessRAG, the first end-to-end framework for speech-based question answering over large-scale document images. Unlike prior methods, TextlessRAG eliminates ASR, TTS and OCR, directly interpreting speech, retrieving relevant visual knowledge, and generating answers in a fully textless pipeline. To further b","authors_text":"Bingquan Liu, Dexin Wang, Lin Sun, Peijin Xie, Shun Qian, Xiangzheng Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-09T09:16:25Z","title":"TextlessRAG: End-to-End Visual Document RAG by Speech Without Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.07538","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":"sha256:7c6cfd2bf0438b8fd9cd3c4b020da01e7776525817ec6ab307bbcaae8144414e","target":"record","created_at":"2026-07-05T12:08:08Z","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":"6d5419abfc7836420a78833942ae3732a3d82ec0ed9c9fe5b6e7d7849843a23f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-09T09:16:25Z","title_canon_sha256":"bdac867f66838267630ac8f9180ca0e3b78402a18fbb208ff499a9cd8c2d7d70"},"schema_version":"1.0","source":{"id":"2509.07538","kind":"arxiv","version":2}},"canonical_sha256":"5e698bcda570fed0015a68b4e7d45e8baf4552be19cd732f8f9ac3e979655dbb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e698bcda570fed0015a68b4e7d45e8baf4552be19cd732f8f9ac3e979655dbb","first_computed_at":"2026-07-05T12:08:08.831306Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:08:08.831306Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T2CL5J0nFXvSqu2LO09Wuze5YHUJDraRydzOkpSBE0H+CdkrV3Cm44tncrkbC9pnsn4eWURkBHR+j/xGUkWnAg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:08:08.831895Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.07538","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7c6cfd2bf0438b8fd9cd3c4b020da01e7776525817ec6ab307bbcaae8144414e","sha256:2a345dddc425bd4cee570027bb10e5dcb68ae0405e930fa69230370c058aa324"],"state_sha256":"768e23277bec4349a8a599dfe6ba9933f1030c8a9af7e36a950a537f6d3f22cb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6XFB1dUZZPxsUUD9V2fByknfzHAknsIphjOGBXu+BtMrVnq1KKdtt/NahnmSP4ngI/VLjHwwasZ9BTGd7d5KCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T10:24:39.981615Z","bundle_sha256":"7823242ed6064f7d74651bc72656391e78742785970a0478c7b6580fce3becc9"}}