{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:GO5KYULI4O5QWLNBRALET3G233","short_pith_number":"pith:GO5KYULI","canonical_record":{"source":{"id":"2301.05226","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-12T18:59:50Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"944b135a5ad532bac29507b25e4760a32c3fa0ee765f9c01df5c39a0f0d37151","abstract_canon_sha256":"07309115178280faa6784da267898a5c7c7dc7b90df6d6a503d2fae6cd21b43f"},"schema_version":"1.0"},"canonical_sha256":"33baac5168e3bb0b2da1881649ecdadeef83afd780940b16c1d1164c9be62b08","source":{"kind":"arxiv","id":"2301.05226","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.05226","created_at":"2026-07-05T05:32:41Z"},{"alias_kind":"arxiv_version","alias_value":"2301.05226v1","created_at":"2026-07-05T05:32:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.05226","created_at":"2026-07-05T05:32:41Z"},{"alias_kind":"pith_short_12","alias_value":"GO5KYULI4O5Q","created_at":"2026-07-05T05:32:41Z"},{"alias_kind":"pith_short_16","alias_value":"GO5KYULI4O5QWLNB","created_at":"2026-07-05T05:32:41Z"},{"alias_kind":"pith_short_8","alias_value":"GO5KYULI","created_at":"2026-07-05T05:32:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:GO5KYULI4O5QWLNBRALET3G233","target":"record","payload":{"canonical_record":{"source":{"id":"2301.05226","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-12T18:59:50Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"944b135a5ad532bac29507b25e4760a32c3fa0ee765f9c01df5c39a0f0d37151","abstract_canon_sha256":"07309115178280faa6784da267898a5c7c7dc7b90df6d6a503d2fae6cd21b43f"},"schema_version":"1.0"},"canonical_sha256":"33baac5168e3bb0b2da1881649ecdadeef83afd780940b16c1d1164c9be62b08","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:32:41.687849Z","signature_b64":"bAua4TY+xF4hjMCBhe/GAwHrE2qxUMQpp3xrWbiIHqTmQECuYB9yYCJTB4V4ZIORj1p7Zf/2e8PSaSC29gPhDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33baac5168e3bb0b2da1881649ecdadeef83afd780940b16c1d1164c9be62b08","last_reissued_at":"2026-07-05T05:32:41.686951Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:32:41.686951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.05226","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":"2026-07-05T05:32:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TiQgxqMLjx9+jE5EqV1OahMveYpq4vLHOTGvuCpvM2uHWrpLbeTPDWkN/WVLm+CGV81EkQozZPcF0AZkWJ9lCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T21:37:13.496846Z"},"content_sha256":"bd06c476d0a430bfb67d37197a9dc2abe3e7aafa986f92aa1cd4c650e28110dc","schema_version":"1.0","event_id":"sha256:bd06c476d0a430bfb67d37197a9dc2abe3e7aafa986f92aa1cd4c650e28110dc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:GO5KYULI4O5QWLNBRALET3G233","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"See, Think, Confirm: Interactive Prompting Between Vision and Language Models for Knowledge-based Visual Reasoning","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chuang Gan, Hao Zhang, Qinhong Zhou, Yikang Shen, Yining Hong, Zhenfang Chen","submitted_at":"2023-01-12T18:59:50Z","abstract_excerpt":"Large pre-trained vision and language models have demonstrated remarkable capacities for various tasks. However, solving the knowledge-based visual reasoning tasks remains challenging, which requires a model to comprehensively understand image content, connect the external world knowledge, and perform step-by-step reasoning to answer the questions correctly. To this end, we propose a novel framework named Interactive Prompting Visual Reasoner (IPVR) for few-shot knowledge-based visual reasoning. IPVR contains three stages, see, think and confirm. The see stage scans the image and grounds the v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.05226","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/2301.05226/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":"2026-07-05T05:32:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KUtjcE+u0kUwZNZCKHOf3LWn+HVXfOnFl4jkrmuH/rCOIu1AzMnLtZsoZQE6LB7ddr5DJ3Wedykv92tGtqyaCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T21:37:13.497519Z"},"content_sha256":"975ce5a5df22fc916f220a59274e69fa796bc2d16b02a65ef4fd49503a69459a","schema_version":"1.0","event_id":"sha256:975ce5a5df22fc916f220a59274e69fa796bc2d16b02a65ef4fd49503a69459a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GO5KYULI4O5QWLNBRALET3G233/bundle.json","state_url":"https://pith.science/pith/GO5KYULI4O5QWLNBRALET3G233/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GO5KYULI4O5QWLNBRALET3G233/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":"2026-08-17T21:37:13Z","links":{"resolver":"https://pith.science/pith/GO5KYULI4O5QWLNBRALET3G233","bundle":"https://pith.science/pith/GO5KYULI4O5QWLNBRALET3G233/bundle.json","state":"https://pith.science/pith/GO5KYULI4O5QWLNBRALET3G233/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GO5KYULI4O5QWLNBRALET3G233/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GO5KYULI4O5QWLNBRALET3G233","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":"07309115178280faa6784da267898a5c7c7dc7b90df6d6a503d2fae6cd21b43f","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-12T18:59:50Z","title_canon_sha256":"944b135a5ad532bac29507b25e4760a32c3fa0ee765f9c01df5c39a0f0d37151"},"schema_version":"1.0","source":{"id":"2301.05226","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.05226","created_at":"2026-07-05T05:32:41Z"},{"alias_kind":"arxiv_version","alias_value":"2301.05226v1","created_at":"2026-07-05T05:32:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.05226","created_at":"2026-07-05T05:32:41Z"},{"alias_kind":"pith_short_12","alias_value":"GO5KYULI4O5Q","created_at":"2026-07-05T05:32:41Z"},{"alias_kind":"pith_short_16","alias_value":"GO5KYULI4O5QWLNB","created_at":"2026-07-05T05:32:41Z"},{"alias_kind":"pith_short_8","alias_value":"GO5KYULI","created_at":"2026-07-05T05:32:41Z"}],"graph_snapshots":[{"event_id":"sha256:975ce5a5df22fc916f220a59274e69fa796bc2d16b02a65ef4fd49503a69459a","target":"graph","created_at":"2026-07-05T05:32:41Z","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/2301.05226/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large pre-trained vision and language models have demonstrated remarkable capacities for various tasks. However, solving the knowledge-based visual reasoning tasks remains challenging, which requires a model to comprehensively understand image content, connect the external world knowledge, and perform step-by-step reasoning to answer the questions correctly. To this end, we propose a novel framework named Interactive Prompting Visual Reasoner (IPVR) for few-shot knowledge-based visual reasoning. IPVR contains three stages, see, think and confirm. The see stage scans the image and grounds the v","authors_text":"Chuang Gan, Hao Zhang, Qinhong Zhou, Yikang Shen, Yining Hong, Zhenfang Chen","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-12T18:59:50Z","title":"See, Think, Confirm: Interactive Prompting Between Vision and Language Models for Knowledge-based Visual Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.05226","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:bd06c476d0a430bfb67d37197a9dc2abe3e7aafa986f92aa1cd4c650e28110dc","target":"record","created_at":"2026-07-05T05:32:41Z","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":"07309115178280faa6784da267898a5c7c7dc7b90df6d6a503d2fae6cd21b43f","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-12T18:59:50Z","title_canon_sha256":"944b135a5ad532bac29507b25e4760a32c3fa0ee765f9c01df5c39a0f0d37151"},"schema_version":"1.0","source":{"id":"2301.05226","kind":"arxiv","version":1}},"canonical_sha256":"33baac5168e3bb0b2da1881649ecdadeef83afd780940b16c1d1164c9be62b08","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"33baac5168e3bb0b2da1881649ecdadeef83afd780940b16c1d1164c9be62b08","first_computed_at":"2026-07-05T05:32:41.686951Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:32:41.686951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bAua4TY+xF4hjMCBhe/GAwHrE2qxUMQpp3xrWbiIHqTmQECuYB9yYCJTB4V4ZIORj1p7Zf/2e8PSaSC29gPhDA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:32:41.687849Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.05226","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd06c476d0a430bfb67d37197a9dc2abe3e7aafa986f92aa1cd4c650e28110dc","sha256:975ce5a5df22fc916f220a59274e69fa796bc2d16b02a65ef4fd49503a69459a"],"state_sha256":"d051b274ca3c6b332c1f3643ce7deb488b254abf074dda99aec0664b88521a26"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PI8vqwtK4JCQMM64YLe8lKkKOY4w2r2FxWQpqB9Gz30MJ6TJLruWeR33WO929us22gyboLx7S23QTn5r4C6VBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T21:37:13.516707Z","bundle_sha256":"8e4d8412db674b5ec9ae07f815d80999b3f099e8ab14182a481f8d85ee69e288"}}