{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:SQB6J3ZP6YNZLJDK5VBSOAC6Z7","short_pith_number":"pith:SQB6J3ZP","schema_version":"1.0","canonical_sha256":"9403e4ef2ff61b95a46aed4327005ecfe2b1fcc125fcecf9f3367a6b716a22b1","source":{"kind":"arxiv","id":"2004.10796","version":3},"attestation_state":"computed","paper":{"title":"VisualCOMET: Reasoning about the Dynamic Context of a Still Image","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Ali Farhadi, Chandra Bhagavatula, Jae Sung Park, Roozbeh Mottaghi, Yejin Choi","submitted_at":"2020-04-22T19:02:20Z","abstract_excerpt":"Even from a single frame of a still image, people can reason about the dynamic story of the image before, after, and beyond the frame. For example, given an image of a man struggling to stay afloat in water, we can reason that the man fell into the water sometime in the past, the intent of that man at the moment is to stay alive, and he will need help in the near future or else he will get washed away. We propose VisualComet, the novel framework of visual commonsense reasoning tasks to predict events that might have happened before, events that might happen next, and the intents of the people "},"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":"2004.10796","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-04-22T19:02:20Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"1127d43338a93d91247244e51e7c4f2c89d084134840bbdb1effe924b7086b23","abstract_canon_sha256":"db4c3fac686f9fa77c913de24a2579ca8fd7519a08541df5f93b74ff5e10bd64"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:23:59.382930Z","signature_b64":"enB9/gLJtj6btRmXowV2rrn20tieQeEM7yFU7qjt6oUjDDBWcu2mawjVWzujhvFoUljrSSc9gWnsqiTFLCMuBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9403e4ef2ff61b95a46aed4327005ecfe2b1fcc125fcecf9f3367a6b716a22b1","last_reissued_at":"2026-07-05T01:23:59.382487Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:23:59.382487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VisualCOMET: Reasoning about the Dynamic Context of a Still Image","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Ali Farhadi, Chandra Bhagavatula, Jae Sung Park, Roozbeh Mottaghi, Yejin Choi","submitted_at":"2020-04-22T19:02:20Z","abstract_excerpt":"Even from a single frame of a still image, people can reason about the dynamic story of the image before, after, and beyond the frame. For example, given an image of a man struggling to stay afloat in water, we can reason that the man fell into the water sometime in the past, the intent of that man at the moment is to stay alive, and he will need help in the near future or else he will get washed away. We propose VisualComet, the novel framework of visual commonsense reasoning tasks to predict events that might have happened before, events that might happen next, and the intents of the people "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.10796","kind":"arxiv","version":3},"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/2004.10796/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":"2004.10796","created_at":"2026-07-05T01:23:59.382542+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.10796v3","created_at":"2026-07-05T01:23:59.382542+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.10796","created_at":"2026-07-05T01:23:59.382542+00:00"},{"alias_kind":"pith_short_12","alias_value":"SQB6J3ZP6YNZ","created_at":"2026-07-05T01:23:59.382542+00:00"},{"alias_kind":"pith_short_16","alias_value":"SQB6J3ZP6YNZLJDK","created_at":"2026-07-05T01:23:59.382542+00:00"},{"alias_kind":"pith_short_8","alias_value":"SQB6J3ZP","created_at":"2026-07-05T01:23:59.382542+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/SQB6J3ZP6YNZLJDK5VBSOAC6Z7","json":"https://pith.science/pith/SQB6J3ZP6YNZLJDK5VBSOAC6Z7.json","graph_json":"https://pith.science/api/pith-number/SQB6J3ZP6YNZLJDK5VBSOAC6Z7/graph.json","events_json":"https://pith.science/api/pith-number/SQB6J3ZP6YNZLJDK5VBSOAC6Z7/events.json","paper":"https://pith.science/paper/SQB6J3ZP"},"agent_actions":{"view_html":"https://pith.science/pith/SQB6J3ZP6YNZLJDK5VBSOAC6Z7","download_json":"https://pith.science/pith/SQB6J3ZP6YNZLJDK5VBSOAC6Z7.json","view_paper":"https://pith.science/paper/SQB6J3ZP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.10796&json=true","fetch_graph":"https://pith.science/api/pith-number/SQB6J3ZP6YNZLJDK5VBSOAC6Z7/graph.json","fetch_events":"https://pith.science/api/pith-number/SQB6J3ZP6YNZLJDK5VBSOAC6Z7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SQB6J3ZP6YNZLJDK5VBSOAC6Z7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SQB6J3ZP6YNZLJDK5VBSOAC6Z7/action/storage_attestation","attest_author":"https://pith.science/pith/SQB6J3ZP6YNZLJDK5VBSOAC6Z7/action/author_attestation","sign_citation":"https://pith.science/pith/SQB6J3ZP6YNZLJDK5VBSOAC6Z7/action/citation_signature","submit_replication":"https://pith.science/pith/SQB6J3ZP6YNZLJDK5VBSOAC6Z7/action/replication_record"}},"created_at":"2026-07-05T01:23:59.382542+00:00","updated_at":"2026-07-05T01:23:59.382542+00:00"}