{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HEUFK7IGAXA63SNS7HEX3O4LZN","short_pith_number":"pith:HEUFK7IG","schema_version":"1.0","canonical_sha256":"3928557d0605c1edc9b2f9c97dbb8bcb6b4dc6a7e2968bd1066ee22775addcc9","source":{"kind":"arxiv","id":"2501.14210","version":1},"attestation_state":"computed","paper":{"title":"PuzzleGPT: Emulating Human Puzzle-Solving Ability for Time and Location Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hammad Ayyubi, Junzhang Liu, Shih-Fu Chang, Xuande Feng, Xudong Lin, Zhecan Wang","submitted_at":"2025-01-24T03:28:37Z","abstract_excerpt":"The task of predicting time and location from images is challenging and requires complex human-like puzzle-solving ability over different clues. In this work, we formalize this ability into core skills and implement them using different modules in an expert pipeline called PuzzleGPT. PuzzleGPT consists of a perceiver to identify visual clues, a reasoner to deduce prediction candidates, a combiner to combinatorially combine information from different clues, a web retriever to get external knowledge if the task can't be solved locally, and a noise filter for robustness. This results in a zero-sh"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2501.14210","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-24T03:28:37Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e792f6bccfc410722f45f64bedcacf1ed903fb7d7c9f1dc1b1c6cbb8a58314ae","abstract_canon_sha256":"7fb229ba6f84adac9db9b9925dfafbac2e467c15d1edab9a0f3717005916780f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:47.265345Z","signature_b64":"hl9wx6QH3N21SMpPViYmOdTNhbeFl8GRdApe6JumOHOZCCIwoV6mkf/NrvflGXkYTquRhOQtIuf2OLrxpemqAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3928557d0605c1edc9b2f9c97dbb8bcb6b4dc6a7e2968bd1066ee22775addcc9","last_reissued_at":"2026-07-05T10:04:47.264845Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:47.264845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PuzzleGPT: Emulating Human Puzzle-Solving Ability for Time and Location Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hammad Ayyubi, Junzhang Liu, Shih-Fu Chang, Xuande Feng, Xudong Lin, Zhecan Wang","submitted_at":"2025-01-24T03:28:37Z","abstract_excerpt":"The task of predicting time and location from images is challenging and requires complex human-like puzzle-solving ability over different clues. In this work, we formalize this ability into core skills and implement them using different modules in an expert pipeline called PuzzleGPT. PuzzleGPT consists of a perceiver to identify visual clues, a reasoner to deduce prediction candidates, a combiner to combinatorially combine information from different clues, a web retriever to get external knowledge if the task can't be solved locally, and a noise filter for robustness. This results in a zero-sh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14210","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/2501.14210/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2501.14210","created_at":"2026-07-05T10:04:47.264907+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.14210v1","created_at":"2026-07-05T10:04:47.264907+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14210","created_at":"2026-07-05T10:04:47.264907+00:00"},{"alias_kind":"pith_short_12","alias_value":"HEUFK7IGAXA6","created_at":"2026-07-05T10:04:47.264907+00:00"},{"alias_kind":"pith_short_16","alias_value":"HEUFK7IGAXA63SNS","created_at":"2026-07-05T10:04:47.264907+00:00"},{"alias_kind":"pith_short_8","alias_value":"HEUFK7IG","created_at":"2026-07-05T10:04:47.264907+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HEUFK7IGAXA63SNS7HEX3O4LZN","json":"https://pith.science/pith/HEUFK7IGAXA63SNS7HEX3O4LZN.json","graph_json":"https://pith.science/api/pith-number/HEUFK7IGAXA63SNS7HEX3O4LZN/graph.json","events_json":"https://pith.science/api/pith-number/HEUFK7IGAXA63SNS7HEX3O4LZN/events.json","paper":"https://pith.science/paper/HEUFK7IG"},"agent_actions":{"view_html":"https://pith.science/pith/HEUFK7IGAXA63SNS7HEX3O4LZN","download_json":"https://pith.science/pith/HEUFK7IGAXA63SNS7HEX3O4LZN.json","view_paper":"https://pith.science/paper/HEUFK7IG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.14210&json=true","fetch_graph":"https://pith.science/api/pith-number/HEUFK7IGAXA63SNS7HEX3O4LZN/graph.json","fetch_events":"https://pith.science/api/pith-number/HEUFK7IGAXA63SNS7HEX3O4LZN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HEUFK7IGAXA63SNS7HEX3O4LZN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HEUFK7IGAXA63SNS7HEX3O4LZN/action/storage_attestation","attest_author":"https://pith.science/pith/HEUFK7IGAXA63SNS7HEX3O4LZN/action/author_attestation","sign_citation":"https://pith.science/pith/HEUFK7IGAXA63SNS7HEX3O4LZN/action/citation_signature","submit_replication":"https://pith.science/pith/HEUFK7IGAXA63SNS7HEX3O4LZN/action/replication_record"}},"created_at":"2026-07-05T10:04:47.264907+00:00","updated_at":"2026-07-05T10:04:47.264907+00:00"}