{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:54A4POHLXU4V2RHGCFJZMS6UF2","short_pith_number":"pith:54A4POHL","canonical_record":{"source":{"id":"2509.04469","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-29T09:09:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ffb7a0d7cfda2292c3df5d083fca081a0f4c1ad5480ff453e8a160c05004c188","abstract_canon_sha256":"86970dbf79af12719acf68d7752768935cfa90a464049ff8bcf3fe1ef7e1a911"},"schema_version":"1.0"},"canonical_sha256":"ef01c7b8ebbd395d44e61153964bd42e9efa599e4d66d4c9e93b58efbd498dda","source":{"kind":"arxiv","id":"2509.04469","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.04469","created_at":"2026-07-05T12:05:23Z"},{"alias_kind":"arxiv_version","alias_value":"2509.04469v1","created_at":"2026-07-05T12:05:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.04469","created_at":"2026-07-05T12:05:23Z"},{"alias_kind":"pith_short_12","alias_value":"54A4POHLXU4V","created_at":"2026-07-05T12:05:23Z"},{"alias_kind":"pith_short_16","alias_value":"54A4POHLXU4V2RHG","created_at":"2026-07-05T12:05:23Z"},{"alias_kind":"pith_short_8","alias_value":"54A4POHL","created_at":"2026-07-05T12:05:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:54A4POHLXU4V2RHGCFJZMS6UF2","target":"record","payload":{"canonical_record":{"source":{"id":"2509.04469","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-29T09:09:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ffb7a0d7cfda2292c3df5d083fca081a0f4c1ad5480ff453e8a160c05004c188","abstract_canon_sha256":"86970dbf79af12719acf68d7752768935cfa90a464049ff8bcf3fe1ef7e1a911"},"schema_version":"1.0"},"canonical_sha256":"ef01c7b8ebbd395d44e61153964bd42e9efa599e4d66d4c9e93b58efbd498dda","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:23.620526Z","signature_b64":"H17pPqIV8lGmZIHMYg8439ailmi/WHIm1U6ERltxuCDJOkQ/mQPBU9c4vwR+uCroxsum7LFTCbnjFF8qnJLiCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef01c7b8ebbd395d44e61153964bd42e9efa599e4d66d4c9e93b58efbd498dda","last_reissued_at":"2026-07-05T12:05:23.619892Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:23.619892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.04469","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":"2026-07-05T12:05:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wthlsun997RSR6vEixxnoVCRfnnNoc4dAkB6Z+Tm8PCJ/mXtGMlk+Bqp95u7H3+ROSBnXIdYpnAWaT24AgXIDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:11:25.484554Z"},"content_sha256":"b90da303b479955701e266f1b610a820be9028f44c908d55cda17f2fd77d93db","schema_version":"1.0","event_id":"sha256:b90da303b479955701e266f1b610a820be9028f44c908d55cda17f2fd77d93db"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:54A4POHLXU4V2RHGCFJZMS6UF2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Modal Vision vs. Text-Based Parsing: Benchmarking LLM Strategies for Invoice Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Armin Berger, David Berghaus, Kostadin Cvejoski, Lars Hillebrand, Rafet Sifa","submitted_at":"2025-08-29T09:09:20Z","abstract_excerpt":"This paper benchmarks eight multi-modal large language models from three families (GPT-5, Gemini 2.5, and open-source Gemma 3) on three diverse openly available invoice document datasets using zero-shot prompting. We compare two processing strategies: direct image processing using multi-modal capabilities and a structured parsing approach converting documents to markdown first. Results show native image processing generally outperforms structured approaches, with performance varying across model types and document characteristics. This benchmark provides insights for selecting appropriate mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.04469","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/2509.04469/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":"2026-07-05T12:05:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GTxYYQ83oP9D0SDiJpuTWbhfs7uuRe9xJ0nV+/g4a7E+W6/4swUGP7E31E2UkZJg4ZMPGZtGDZWxJ7AqQDPiCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:11:25.484933Z"},"content_sha256":"3e6144df457e44ae40e668740b5e534071c361a5e221d0b4fbead4cd282f92d6","schema_version":"1.0","event_id":"sha256:3e6144df457e44ae40e668740b5e534071c361a5e221d0b4fbead4cd282f92d6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/54A4POHLXU4V2RHGCFJZMS6UF2/bundle.json","state_url":"https://pith.science/pith/54A4POHLXU4V2RHGCFJZMS6UF2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/54A4POHLXU4V2RHGCFJZMS6UF2/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":"2026-07-07T11:11:25Z","links":{"resolver":"https://pith.science/pith/54A4POHLXU4V2RHGCFJZMS6UF2","bundle":"https://pith.science/pith/54A4POHLXU4V2RHGCFJZMS6UF2/bundle.json","state":"https://pith.science/pith/54A4POHLXU4V2RHGCFJZMS6UF2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/54A4POHLXU4V2RHGCFJZMS6UF2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:54A4POHLXU4V2RHGCFJZMS6UF2","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":"86970dbf79af12719acf68d7752768935cfa90a464049ff8bcf3fe1ef7e1a911","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-29T09:09:20Z","title_canon_sha256":"ffb7a0d7cfda2292c3df5d083fca081a0f4c1ad5480ff453e8a160c05004c188"},"schema_version":"1.0","source":{"id":"2509.04469","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.04469","created_at":"2026-07-05T12:05:23Z"},{"alias_kind":"arxiv_version","alias_value":"2509.04469v1","created_at":"2026-07-05T12:05:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.04469","created_at":"2026-07-05T12:05:23Z"},{"alias_kind":"pith_short_12","alias_value":"54A4POHLXU4V","created_at":"2026-07-05T12:05:23Z"},{"alias_kind":"pith_short_16","alias_value":"54A4POHLXU4V2RHG","created_at":"2026-07-05T12:05:23Z"},{"alias_kind":"pith_short_8","alias_value":"54A4POHL","created_at":"2026-07-05T12:05:23Z"}],"graph_snapshots":[{"event_id":"sha256:3e6144df457e44ae40e668740b5e534071c361a5e221d0b4fbead4cd282f92d6","target":"graph","created_at":"2026-07-05T12:05:23Z","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/2509.04469/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper benchmarks eight multi-modal large language models from three families (GPT-5, Gemini 2.5, and open-source Gemma 3) on three diverse openly available invoice document datasets using zero-shot prompting. We compare two processing strategies: direct image processing using multi-modal capabilities and a structured parsing approach converting documents to markdown first. Results show native image processing generally outperforms structured approaches, with performance varying across model types and document characteristics. This benchmark provides insights for selecting appropriate mode","authors_text":"Armin Berger, David Berghaus, Kostadin Cvejoski, Lars Hillebrand, Rafet Sifa","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-29T09:09:20Z","title":"Multi-Modal Vision vs. Text-Based Parsing: Benchmarking LLM Strategies for Invoice Processing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.04469","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:b90da303b479955701e266f1b610a820be9028f44c908d55cda17f2fd77d93db","target":"record","created_at":"2026-07-05T12:05:23Z","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":"86970dbf79af12719acf68d7752768935cfa90a464049ff8bcf3fe1ef7e1a911","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-29T09:09:20Z","title_canon_sha256":"ffb7a0d7cfda2292c3df5d083fca081a0f4c1ad5480ff453e8a160c05004c188"},"schema_version":"1.0","source":{"id":"2509.04469","kind":"arxiv","version":1}},"canonical_sha256":"ef01c7b8ebbd395d44e61153964bd42e9efa599e4d66d4c9e93b58efbd498dda","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef01c7b8ebbd395d44e61153964bd42e9efa599e4d66d4c9e93b58efbd498dda","first_computed_at":"2026-07-05T12:05:23.619892Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:05:23.619892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H17pPqIV8lGmZIHMYg8439ailmi/WHIm1U6ERltxuCDJOkQ/mQPBU9c4vwR+uCroxsum7LFTCbnjFF8qnJLiCg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:05:23.620526Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.04469","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b90da303b479955701e266f1b610a820be9028f44c908d55cda17f2fd77d93db","sha256:3e6144df457e44ae40e668740b5e534071c361a5e221d0b4fbead4cd282f92d6"],"state_sha256":"d7f2f0f42f01f90f80f1f40299b05a42aa5c9c9427bd5e0ba2f9b9015c040ed4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i3vFlmPgNIrEU4GvCfuxaEwf/ncFA9HfcBNZUonloohqdE1rENXKA+KoxV08aALPB+PvZRqXu/MjF5SVCk4MAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T11:11:25.486908Z","bundle_sha256":"db24dd9cd00303963aeac1e16fbe1595d0a0aeb61a29613c23cbe22c8c44d44a"}}