{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UGLI4NHI2WMOYYGJ2LO35PSYOC","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":"e7c8096f20a7f9400239de4a3d45f88d9b811478e717f0bab4d9503287de3cf6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-16T17:22:18Z","title_canon_sha256":"97e4b009e5152f1364d1b5969d551fe13b175b54b0c2263c865df83642de333e"},"schema_version":"1.0","source":{"id":"2409.10488","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.10488","created_at":"2026-07-05T09:07:40Z"},{"alias_kind":"arxiv_version","alias_value":"2409.10488v1","created_at":"2026-07-05T09:07:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.10488","created_at":"2026-07-05T09:07:40Z"},{"alias_kind":"pith_short_12","alias_value":"UGLI4NHI2WMO","created_at":"2026-07-05T09:07:40Z"},{"alias_kind":"pith_short_16","alias_value":"UGLI4NHI2WMOYYGJ","created_at":"2026-07-05T09:07:40Z"},{"alias_kind":"pith_short_8","alias_value":"UGLI4NHI","created_at":"2026-07-05T09:07:40Z"}],"graph_snapshots":[{"event_id":"sha256:c0f7ded50d5f733fb24d6e582fec636e3374797c2213568a4817b164a2d444ac","target":"graph","created_at":"2026-07-05T09:07:40Z","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/2409.10488/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"For a vision-language model (VLM) to understand the physical world, such as cause and effect, a first step is to capture the temporal dynamics of the visual world, for example how the physical states of objects evolve over time (e.g. a whole apple into a sliced apple). Our paper aims to investigate if VLMs pre-trained on web-scale data learn to encode object states, which can be extracted with zero-shot text prompts. We curate an object state recognition dataset ChangeIt-Frames, and evaluate nine open-source VLMs, including models trained with contrastive and generative objectives. We observe ","authors_text":"Chen Sun, David Heffren, Kaleb Newman, Shijie Wang, Yuan Zang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-16T17:22:18Z","title":"Do Pre-trained Vision-Language Models Encode Object States?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.10488","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":"sha256:539b83220f6294683cd7720d8cf4854428496f2248972ad3c3bdef377da1dda6","target":"record","created_at":"2026-07-05T09:07:40Z","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":"e7c8096f20a7f9400239de4a3d45f88d9b811478e717f0bab4d9503287de3cf6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-16T17:22:18Z","title_canon_sha256":"97e4b009e5152f1364d1b5969d551fe13b175b54b0c2263c865df83642de333e"},"schema_version":"1.0","source":{"id":"2409.10488","kind":"arxiv","version":1}},"canonical_sha256":"a1968e34e8d598ec60c9d2ddbebe5870a19e93903ee857a3dea41a3071f9aa7c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a1968e34e8d598ec60c9d2ddbebe5870a19e93903ee857a3dea41a3071f9aa7c","first_computed_at":"2026-07-05T09:07:40.953666Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:07:40.953666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ony9bpUHqojDWptiDl/ZqCZ6V1MU3vYoKRcm+79uOfr/pLsuwAjB0zsvo7QD4bolSadmBUzMHqeGDPgbdlPMDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:07:40.954078Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.10488","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:539b83220f6294683cd7720d8cf4854428496f2248972ad3c3bdef377da1dda6","sha256:c0f7ded50d5f733fb24d6e582fec636e3374797c2213568a4817b164a2d444ac"],"state_sha256":"fb4477115b9e0ee58bc850a1e1634683087ea3415099a7b2b74bbdef22549c52"}