{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:RM4TIIU7LKCHEVO3B2VLNSBXI6","short_pith_number":"pith:RM4TIIU7","canonical_record":{"source":{"id":"2310.02804","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-04T13:29:47Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"f655437c37fd31d94dda4397fa76b8d77e16eefbcf1b332dcd7fcfdc7e4ffe6f","abstract_canon_sha256":"b9c73abfa49b8ab88b9acca2334caeccf68b3c5553dee5dd6a77c0fb3d216b6e"},"schema_version":"1.0"},"canonical_sha256":"8b3934229f5a847255db0eaab6c83747900e3e77165026421f3de63ba79a827f","source":{"kind":"arxiv","id":"2310.02804","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.02804","created_at":"2026-07-05T06:57:14Z"},{"alias_kind":"arxiv_version","alias_value":"2310.02804v1","created_at":"2026-07-05T06:57:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.02804","created_at":"2026-07-05T06:57:14Z"},{"alias_kind":"pith_short_12","alias_value":"RM4TIIU7LKCH","created_at":"2026-07-05T06:57:14Z"},{"alias_kind":"pith_short_16","alias_value":"RM4TIIU7LKCHEVO3","created_at":"2026-07-05T06:57:14Z"},{"alias_kind":"pith_short_8","alias_value":"RM4TIIU7","created_at":"2026-07-05T06:57:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:RM4TIIU7LKCHEVO3B2VLNSBXI6","target":"record","payload":{"canonical_record":{"source":{"id":"2310.02804","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-04T13:29:47Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"f655437c37fd31d94dda4397fa76b8d77e16eefbcf1b332dcd7fcfdc7e4ffe6f","abstract_canon_sha256":"b9c73abfa49b8ab88b9acca2334caeccf68b3c5553dee5dd6a77c0fb3d216b6e"},"schema_version":"1.0"},"canonical_sha256":"8b3934229f5a847255db0eaab6c83747900e3e77165026421f3de63ba79a827f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:57:14.144976Z","signature_b64":"6UCH9gV0i9T3pPsXVrRcvB93vds8VSDBtiiiGPW9GeCyofw8UITQ/7VNplTAe7/QjQ5RIoyPCIC8byX9gGHCDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b3934229f5a847255db0eaab6c83747900e3e77165026421f3de63ba79a827f","last_reissued_at":"2026-07-05T06:57:14.144419Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:57:14.144419Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.02804","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":"2026-07-05T06:57:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KVjAAzaUuMfzOqA0QOP0P16JGnZyzIssAfbCbI8/+gJVbpqpkBqeTubiwf52AK8gBCXHenEuvhu3dbU/r4lhCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:11:01.360649Z"},"content_sha256":"052010f51dece483af52ced740f9827b8a95a7f4426321ce331e377d75bf7179","schema_version":"1.0","event_id":"sha256:052010f51dece483af52ced740f9827b8a95a7f4426321ce331e377d75bf7179"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:RM4TIIU7LKCHEVO3B2VLNSBXI6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DOMINO: A Dual-System for Multi-step Visual Language Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Armen Aghajanyan, Asli Celikyilmaz, Maryam Fazel-Zarandi, Muhao Chen, Olga Golovneva, Peifang Wang, Xiang Ren","submitted_at":"2023-10-04T13:29:47Z","abstract_excerpt":"Visual language reasoning requires a system to extract text or numbers from information-dense images like charts or plots and perform logical or arithmetic reasoning to arrive at an answer. To tackle this task, existing work relies on either (1) an end-to-end vision-language model trained on a large amount of data, or (2) a two-stage pipeline where a captioning model converts the image into text that is further read by another large language model to deduce the answer. However, the former approach forces the model to answer a complex question with one single step, and the latter approach is pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.02804","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/2310.02804/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":"2026-07-05T06:57:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Csf8ox/rEX18p5BDqT2ogyU4BAuVNFXBMbXkZrieId/6Orr0/DNBUSzac03uAemNYgvk3wnICf9mYcwOLeb7Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:11:01.361835Z"},"content_sha256":"f06692bca4ad152d98f35c23ab40ac4fe13673f7c220fc9295293cd079685d8d","schema_version":"1.0","event_id":"sha256:f06692bca4ad152d98f35c23ab40ac4fe13673f7c220fc9295293cd079685d8d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RM4TIIU7LKCHEVO3B2VLNSBXI6/bundle.json","state_url":"https://pith.science/pith/RM4TIIU7LKCHEVO3B2VLNSBXI6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RM4TIIU7LKCHEVO3B2VLNSBXI6/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":"2026-08-06T19:11:01Z","links":{"resolver":"https://pith.science/pith/RM4TIIU7LKCHEVO3B2VLNSBXI6","bundle":"https://pith.science/pith/RM4TIIU7LKCHEVO3B2VLNSBXI6/bundle.json","state":"https://pith.science/pith/RM4TIIU7LKCHEVO3B2VLNSBXI6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RM4TIIU7LKCHEVO3B2VLNSBXI6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RM4TIIU7LKCHEVO3B2VLNSBXI6","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":"b9c73abfa49b8ab88b9acca2334caeccf68b3c5553dee5dd6a77c0fb3d216b6e","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-04T13:29:47Z","title_canon_sha256":"f655437c37fd31d94dda4397fa76b8d77e16eefbcf1b332dcd7fcfdc7e4ffe6f"},"schema_version":"1.0","source":{"id":"2310.02804","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.02804","created_at":"2026-07-05T06:57:14Z"},{"alias_kind":"arxiv_version","alias_value":"2310.02804v1","created_at":"2026-07-05T06:57:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.02804","created_at":"2026-07-05T06:57:14Z"},{"alias_kind":"pith_short_12","alias_value":"RM4TIIU7LKCH","created_at":"2026-07-05T06:57:14Z"},{"alias_kind":"pith_short_16","alias_value":"RM4TIIU7LKCHEVO3","created_at":"2026-07-05T06:57:14Z"},{"alias_kind":"pith_short_8","alias_value":"RM4TIIU7","created_at":"2026-07-05T06:57:14Z"}],"graph_snapshots":[{"event_id":"sha256:f06692bca4ad152d98f35c23ab40ac4fe13673f7c220fc9295293cd079685d8d","target":"graph","created_at":"2026-07-05T06:57:14Z","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/2310.02804/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual language reasoning requires a system to extract text or numbers from information-dense images like charts or plots and perform logical or arithmetic reasoning to arrive at an answer. To tackle this task, existing work relies on either (1) an end-to-end vision-language model trained on a large amount of data, or (2) a two-stage pipeline where a captioning model converts the image into text that is further read by another large language model to deduce the answer. However, the former approach forces the model to answer a complex question with one single step, and the latter approach is pr","authors_text":"Armen Aghajanyan, Asli Celikyilmaz, Maryam Fazel-Zarandi, Muhao Chen, Olga Golovneva, Peifang Wang, Xiang Ren","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-04T13:29:47Z","title":"DOMINO: A Dual-System for Multi-step Visual Language Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.02804","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":"sha256:052010f51dece483af52ced740f9827b8a95a7f4426321ce331e377d75bf7179","target":"record","created_at":"2026-07-05T06:57:14Z","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":"b9c73abfa49b8ab88b9acca2334caeccf68b3c5553dee5dd6a77c0fb3d216b6e","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-04T13:29:47Z","title_canon_sha256":"f655437c37fd31d94dda4397fa76b8d77e16eefbcf1b332dcd7fcfdc7e4ffe6f"},"schema_version":"1.0","source":{"id":"2310.02804","kind":"arxiv","version":1}},"canonical_sha256":"8b3934229f5a847255db0eaab6c83747900e3e77165026421f3de63ba79a827f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8b3934229f5a847255db0eaab6c83747900e3e77165026421f3de63ba79a827f","first_computed_at":"2026-07-05T06:57:14.144419Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:57:14.144419Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6UCH9gV0i9T3pPsXVrRcvB93vds8VSDBtiiiGPW9GeCyofw8UITQ/7VNplTAe7/QjQ5RIoyPCIC8byX9gGHCDA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:57:14.144976Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.02804","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:052010f51dece483af52ced740f9827b8a95a7f4426321ce331e377d75bf7179","sha256:f06692bca4ad152d98f35c23ab40ac4fe13673f7c220fc9295293cd079685d8d"],"state_sha256":"3e57883a441b4d30c7cc0b4b72ff8c960453f70a86006830f10cb273c46d333c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2EJU/n/UUQrm7CHv9VeavakUpFjehjC2Dr91gdRW7uuSGnYxrsTj6Jdm0iL8ZJA1e9FZ7Wr7ENcEju+5qua9CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T19:11:01.376721Z","bundle_sha256":"b025e6303965d660d0a98df94e0e0f8b371f4e26f241bb1577a32a26c510b442"}}