{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:GZD66KTYVSDAZJSIQEBLAE5VOY","short_pith_number":"pith:GZD66KTY","canonical_record":{"source":{"id":"2307.06166","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-12T13:46:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d14e0452c8a92546123c1ccabae1142cb3228dd3a239bfe2f19d7dd427c2ad63","abstract_canon_sha256":"bd90630f6d230d82a80c67c3f3ad2bf0198a34d93863209f70cbfdcbb6f8a884"},"schema_version":"1.0"},"canonical_sha256":"3647ef2a78ac860ca6488102b013b57634c32f7e55c0098a2674e0a4eb248ad7","source":{"kind":"arxiv","id":"2307.06166","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.06166","created_at":"2026-07-05T07:28:45Z"},{"alias_kind":"arxiv_version","alias_value":"2307.06166v2","created_at":"2026-07-05T07:28:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.06166","created_at":"2026-07-05T07:28:45Z"},{"alias_kind":"pith_short_12","alias_value":"GZD66KTYVSDA","created_at":"2026-07-05T07:28:45Z"},{"alias_kind":"pith_short_16","alias_value":"GZD66KTYVSDAZJSI","created_at":"2026-07-05T07:28:45Z"},{"alias_kind":"pith_short_8","alias_value":"GZD66KTY","created_at":"2026-07-05T07:28:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:GZD66KTYVSDAZJSIQEBLAE5VOY","target":"record","payload":{"canonical_record":{"source":{"id":"2307.06166","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-12T13:46:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d14e0452c8a92546123c1ccabae1142cb3228dd3a239bfe2f19d7dd427c2ad63","abstract_canon_sha256":"bd90630f6d230d82a80c67c3f3ad2bf0198a34d93863209f70cbfdcbb6f8a884"},"schema_version":"1.0"},"canonical_sha256":"3647ef2a78ac860ca6488102b013b57634c32f7e55c0098a2674e0a4eb248ad7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:28:45.014326Z","signature_b64":"KL6P+bykyWPE211UfaAk2T8w64sGZWSE4Pc7lVZbR5EhsaEzg7Iisgc/0izB+nfnTli+HFbX1gzvF9rrcKgPAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3647ef2a78ac860ca6488102b013b57634c32f7e55c0098a2674e0a4eb248ad7","last_reissued_at":"2026-07-05T07:28:45.013751Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:28:45.013751Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.06166","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":"2026-07-05T07:28:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NsYwHPp1NKn8O2AuVMsF45uEGyP98nDhawk9MjNtmRe123f6gtpDIM7DkMqpteZglLA9J28SaglxHvb7JN5XBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:21:16.243953Z"},"content_sha256":"5465a846799637a3838e8cfa8d2aa13aca159cafb57371a8af12e1e6d425f4f6","schema_version":"1.0","event_id":"sha256:5465a846799637a3838e8cfa8d2aa13aca159cafb57371a8af12e1e6d425f4f6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:GZD66KTYVSDAZJSIQEBLAE5VOY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Can Vision-Language Models be a Good Guesser? Exploring VLMs for Times and Location Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Gengyuan Zhang, Kerui Zhang, Volker Tresp, Yurui Zhang","submitted_at":"2023-07-12T13:46:28Z","abstract_excerpt":"Vision-Language Models (VLMs) are expected to be capable of reasoning with commonsense knowledge as human beings. One example is that humans can reason where and when an image is taken based on their knowledge. This makes us wonder if, based on visual cues, Vision-Language Models that are pre-trained with large-scale image-text resources can achieve and even outperform human's capability in reasoning times and location. To address this question, we propose a two-stage \\recognition\\space and \\reasoning\\space probing task, applied to discriminative and generative VLMs to uncover whether VLMs can"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.06166","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/2307.06166/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":"2026-07-05T07:28:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0SxuU4qnITzUVEJ38LVtqTAX/H3s6h7ZL5UcmhfuxwoU3hUnT5JwwPc+sq7O03yR8T6wnnm+oFaWQzGq1kT9BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:21:16.244333Z"},"content_sha256":"9e9c2e5df0c3cccca2c6fb3be59c027632011647292e687007c290b409802619","schema_version":"1.0","event_id":"sha256:9e9c2e5df0c3cccca2c6fb3be59c027632011647292e687007c290b409802619"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GZD66KTYVSDAZJSIQEBLAE5VOY/bundle.json","state_url":"https://pith.science/pith/GZD66KTYVSDAZJSIQEBLAE5VOY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GZD66KTYVSDAZJSIQEBLAE5VOY/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":"2026-08-05T02:21:16Z","links":{"resolver":"https://pith.science/pith/GZD66KTYVSDAZJSIQEBLAE5VOY","bundle":"https://pith.science/pith/GZD66KTYVSDAZJSIQEBLAE5VOY/bundle.json","state":"https://pith.science/pith/GZD66KTYVSDAZJSIQEBLAE5VOY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GZD66KTYVSDAZJSIQEBLAE5VOY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GZD66KTYVSDAZJSIQEBLAE5VOY","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":"bd90630f6d230d82a80c67c3f3ad2bf0198a34d93863209f70cbfdcbb6f8a884","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-12T13:46:28Z","title_canon_sha256":"d14e0452c8a92546123c1ccabae1142cb3228dd3a239bfe2f19d7dd427c2ad63"},"schema_version":"1.0","source":{"id":"2307.06166","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.06166","created_at":"2026-07-05T07:28:45Z"},{"alias_kind":"arxiv_version","alias_value":"2307.06166v2","created_at":"2026-07-05T07:28:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.06166","created_at":"2026-07-05T07:28:45Z"},{"alias_kind":"pith_short_12","alias_value":"GZD66KTYVSDA","created_at":"2026-07-05T07:28:45Z"},{"alias_kind":"pith_short_16","alias_value":"GZD66KTYVSDAZJSI","created_at":"2026-07-05T07:28:45Z"},{"alias_kind":"pith_short_8","alias_value":"GZD66KTY","created_at":"2026-07-05T07:28:45Z"}],"graph_snapshots":[{"event_id":"sha256:9e9c2e5df0c3cccca2c6fb3be59c027632011647292e687007c290b409802619","target":"graph","created_at":"2026-07-05T07:28:45Z","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/2307.06166/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Models (VLMs) are expected to be capable of reasoning with commonsense knowledge as human beings. One example is that humans can reason where and when an image is taken based on their knowledge. This makes us wonder if, based on visual cues, Vision-Language Models that are pre-trained with large-scale image-text resources can achieve and even outperform human's capability in reasoning times and location. To address this question, we propose a two-stage \\recognition\\space and \\reasoning\\space probing task, applied to discriminative and generative VLMs to uncover whether VLMs can","authors_text":"Gengyuan Zhang, Kerui Zhang, Volker Tresp, Yurui Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-12T13:46:28Z","title":"Can Vision-Language Models be a Good Guesser? Exploring VLMs for Times and Location Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.06166","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":"sha256:5465a846799637a3838e8cfa8d2aa13aca159cafb57371a8af12e1e6d425f4f6","target":"record","created_at":"2026-07-05T07:28:45Z","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":"bd90630f6d230d82a80c67c3f3ad2bf0198a34d93863209f70cbfdcbb6f8a884","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-12T13:46:28Z","title_canon_sha256":"d14e0452c8a92546123c1ccabae1142cb3228dd3a239bfe2f19d7dd427c2ad63"},"schema_version":"1.0","source":{"id":"2307.06166","kind":"arxiv","version":2}},"canonical_sha256":"3647ef2a78ac860ca6488102b013b57634c32f7e55c0098a2674e0a4eb248ad7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3647ef2a78ac860ca6488102b013b57634c32f7e55c0098a2674e0a4eb248ad7","first_computed_at":"2026-07-05T07:28:45.013751Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:28:45.013751Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KL6P+bykyWPE211UfaAk2T8w64sGZWSE4Pc7lVZbR5EhsaEzg7Iisgc/0izB+nfnTli+HFbX1gzvF9rrcKgPAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:28:45.014326Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.06166","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5465a846799637a3838e8cfa8d2aa13aca159cafb57371a8af12e1e6d425f4f6","sha256:9e9c2e5df0c3cccca2c6fb3be59c027632011647292e687007c290b409802619"],"state_sha256":"1848c5b1ebe50927f544c54551fe87440452b17d2ab2fe19a604f70b78a41679"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4AL40PHdYNk1rIZZmcd/GgGAyxUGGEjT4OrvpPuGg1b/yWQfKa8LxIFmy2dUCv9ohowPP+GKN30ZvjUvwo16CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T02:21:16.246590Z","bundle_sha256":"01ca062fd3dc7e94b9643f205b9f48cfc698cc75b05adb11b81ef6b1e773887c"}}