{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:OKPHR3GG2TSZHIJA7ORHU2OSH3","short_pith_number":"pith:OKPHR3GG","canonical_record":{"source":{"id":"2305.13267","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-22T17:33:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"248237524a3228f38b4bb10482ad3b47ccd166f6519215abe45e97176a5797a8","abstract_canon_sha256":"189881eafb69eb2c7c4c39d68dcad2ab35ea69fc52e360d31b70a8e05ea57639"},"schema_version":"1.0"},"canonical_sha256":"729e78ecc6d4e593a120fba27a69d23ec3a1629b88e65bb244b4b055e3423796","source":{"kind":"arxiv","id":"2305.13267","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13267","created_at":"2026-07-05T06:12:28Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13267v1","created_at":"2026-07-05T06:12:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13267","created_at":"2026-07-05T06:12:28Z"},{"alias_kind":"pith_short_12","alias_value":"OKPHR3GG2TSZ","created_at":"2026-07-05T06:12:28Z"},{"alias_kind":"pith_short_16","alias_value":"OKPHR3GG2TSZHIJA","created_at":"2026-07-05T06:12:28Z"},{"alias_kind":"pith_short_8","alias_value":"OKPHR3GG","created_at":"2026-07-05T06:12:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:OKPHR3GG2TSZHIJA7ORHU2OSH3","target":"record","payload":{"canonical_record":{"source":{"id":"2305.13267","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-22T17:33:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"248237524a3228f38b4bb10482ad3b47ccd166f6519215abe45e97176a5797a8","abstract_canon_sha256":"189881eafb69eb2c7c4c39d68dcad2ab35ea69fc52e360d31b70a8e05ea57639"},"schema_version":"1.0"},"canonical_sha256":"729e78ecc6d4e593a120fba27a69d23ec3a1629b88e65bb244b4b055e3423796","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:28.480954Z","signature_b64":"vfV9lBbBUhYl7+T66BJ9ZthYHJ1e0HeBNs3KX+lboGL599dFFxa5bS/tkUG64+bH+TOGG9moK9MTPkobB/YvDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"729e78ecc6d4e593a120fba27a69d23ec3a1629b88e65bb244b4b055e3423796","last_reissued_at":"2026-07-05T06:12:28.480526Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:28.480526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.13267","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":"2026-07-05T06:12:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jxcDHFygyBH+iajFhCK+yF1mFY+f0aoA9aIbsKoT/nAO5Q4wJZhMMOCOYvYq3Unl+VEtEoxXk/15phnyxrcCDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T14:56:07.264468Z"},"content_sha256":"68c88fa52121ab70412d6c12861daff64e59724e415f17b0fc54d930b65da4da","schema_version":"1.0","event_id":"sha256:68c88fa52121ab70412d6c12861daff64e59724e415f17b0fc54d930b65da4da"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:OKPHR3GG2TSZHIJA7ORHU2OSH3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhance Reasoning Ability of Visual-Language Models via Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Wenjuan Han, Xintong Zhang, Yueting Yang","submitted_at":"2023-05-22T17:33:44Z","abstract_excerpt":"Pre-trained visual language models (VLM) have shown excellent performance in image caption tasks. However, it sometimes shows insufficient reasoning ability. In contrast, large language models (LLMs) emerge with powerful reasoning capabilities. Therefore, we propose a method called TReE, which transfers the reasoning ability of a large language model to a visual language model in zero-shot scenarios. TReE contains three stages: observation, thinking, and re-thinking. Observation stage indicates that VLM obtains the overall information of the relative image. Thinking stage combines the image in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13267","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/2305.13267/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":"2026-07-05T06:12:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bjc4GEzR3h7d6fhCs0QvENaFI8l19GDEM6m/E/xVX4aa7E+nmaaleS5j4NmyUeWyImywIO7JEfb/c8PbL+A8Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T14:56:07.265399Z"},"content_sha256":"608f907904bf8bcd9e962df0bf27cdbdf2096166cdc35103e4e4bfd0b0d64920","schema_version":"1.0","event_id":"sha256:608f907904bf8bcd9e962df0bf27cdbdf2096166cdc35103e4e4bfd0b0d64920"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OKPHR3GG2TSZHIJA7ORHU2OSH3/bundle.json","state_url":"https://pith.science/pith/OKPHR3GG2TSZHIJA7ORHU2OSH3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OKPHR3GG2TSZHIJA7ORHU2OSH3/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":"2026-08-14T14:56:07Z","links":{"resolver":"https://pith.science/pith/OKPHR3GG2TSZHIJA7ORHU2OSH3","bundle":"https://pith.science/pith/OKPHR3GG2TSZHIJA7ORHU2OSH3/bundle.json","state":"https://pith.science/pith/OKPHR3GG2TSZHIJA7ORHU2OSH3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OKPHR3GG2TSZHIJA7ORHU2OSH3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OKPHR3GG2TSZHIJA7ORHU2OSH3","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":"189881eafb69eb2c7c4c39d68dcad2ab35ea69fc52e360d31b70a8e05ea57639","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-22T17:33:44Z","title_canon_sha256":"248237524a3228f38b4bb10482ad3b47ccd166f6519215abe45e97176a5797a8"},"schema_version":"1.0","source":{"id":"2305.13267","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13267","created_at":"2026-07-05T06:12:28Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13267v1","created_at":"2026-07-05T06:12:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13267","created_at":"2026-07-05T06:12:28Z"},{"alias_kind":"pith_short_12","alias_value":"OKPHR3GG2TSZ","created_at":"2026-07-05T06:12:28Z"},{"alias_kind":"pith_short_16","alias_value":"OKPHR3GG2TSZHIJA","created_at":"2026-07-05T06:12:28Z"},{"alias_kind":"pith_short_8","alias_value":"OKPHR3GG","created_at":"2026-07-05T06:12:28Z"}],"graph_snapshots":[{"event_id":"sha256:608f907904bf8bcd9e962df0bf27cdbdf2096166cdc35103e4e4bfd0b0d64920","target":"graph","created_at":"2026-07-05T06:12:28Z","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/2305.13267/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained visual language models (VLM) have shown excellent performance in image caption tasks. However, it sometimes shows insufficient reasoning ability. In contrast, large language models (LLMs) emerge with powerful reasoning capabilities. Therefore, we propose a method called TReE, which transfers the reasoning ability of a large language model to a visual language model in zero-shot scenarios. TReE contains three stages: observation, thinking, and re-thinking. Observation stage indicates that VLM obtains the overall information of the relative image. Thinking stage combines the image in","authors_text":"Wenjuan Han, Xintong Zhang, Yueting Yang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-22T17:33:44Z","title":"Enhance Reasoning Ability of Visual-Language Models via Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13267","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":"sha256:68c88fa52121ab70412d6c12861daff64e59724e415f17b0fc54d930b65da4da","target":"record","created_at":"2026-07-05T06:12:28Z","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":"189881eafb69eb2c7c4c39d68dcad2ab35ea69fc52e360d31b70a8e05ea57639","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-22T17:33:44Z","title_canon_sha256":"248237524a3228f38b4bb10482ad3b47ccd166f6519215abe45e97176a5797a8"},"schema_version":"1.0","source":{"id":"2305.13267","kind":"arxiv","version":1}},"canonical_sha256":"729e78ecc6d4e593a120fba27a69d23ec3a1629b88e65bb244b4b055e3423796","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"729e78ecc6d4e593a120fba27a69d23ec3a1629b88e65bb244b4b055e3423796","first_computed_at":"2026-07-05T06:12:28.480526Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:12:28.480526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vfV9lBbBUhYl7+T66BJ9ZthYHJ1e0HeBNs3KX+lboGL599dFFxa5bS/tkUG64+bH+TOGG9moK9MTPkobB/YvDg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:12:28.480954Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.13267","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:68c88fa52121ab70412d6c12861daff64e59724e415f17b0fc54d930b65da4da","sha256:608f907904bf8bcd9e962df0bf27cdbdf2096166cdc35103e4e4bfd0b0d64920"],"state_sha256":"a6d0ddf878ee576452bc09d23a3e6c1fc68dd80346839b8c771865b2734d01d4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CAqVeLyACAO0t/aXjqwYJeZqBEr48tMY9w9UhExvUW3fdcZAlvhcB3MkkxaBlJvyRcQnYmASsYrrs0Njkv3TDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T14:56:07.277499Z","bundle_sha256":"195442ec35ece7538dae7d4a620975568bb6c8516778d82118336f1608d543a3"}}