{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YIKPG3DR7LRHJO2T6HQE43O6CP","short_pith_number":"pith:YIKPG3DR","canonical_record":{"source":{"id":"2506.06006","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-06T11:50:18Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"ff8184da166c039c099917624887bed74af006e032f9ac1741e88760492c80b1","abstract_canon_sha256":"362d33ebf1cf5c60d8a1979271481f5e18ca39453dc66b8a7529705c122ce523"},"schema_version":"1.0"},"canonical_sha256":"c214f36c71fae274bb53f1e04e6dde13e7269e499ef70a6385ebc17331adb0fb","source":{"kind":"arxiv","id":"2506.06006","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.06006","created_at":"2026-06-04T01:08:29Z"},{"alias_kind":"arxiv_version","alias_value":"2506.06006v3","created_at":"2026-06-04T01:08:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06006","created_at":"2026-06-04T01:08:29Z"},{"alias_kind":"pith_short_12","alias_value":"YIKPG3DR7LRH","created_at":"2026-06-04T01:08:29Z"},{"alias_kind":"pith_short_16","alias_value":"YIKPG3DR7LRHJO2T","created_at":"2026-06-04T01:08:29Z"},{"alias_kind":"pith_short_8","alias_value":"YIKPG3DR","created_at":"2026-06-04T01:08:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YIKPG3DR7LRHJO2T6HQE43O6CP","target":"record","payload":{"canonical_record":{"source":{"id":"2506.06006","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-06T11:50:18Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"ff8184da166c039c099917624887bed74af006e032f9ac1741e88760492c80b1","abstract_canon_sha256":"362d33ebf1cf5c60d8a1979271481f5e18ca39453dc66b8a7529705c122ce523"},"schema_version":"1.0"},"canonical_sha256":"c214f36c71fae274bb53f1e04e6dde13e7269e499ef70a6385ebc17331adb0fb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:08:29.571813Z","signature_b64":"AZCLoMRgwo4vAT2MjrLCicMgREmG6US7fBN354CDh5WeyHnVPC+JFIu/2eya8ZBQ6I3vXGRvSKUT3rtfuqBSCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c214f36c71fae274bb53f1e04e6dde13e7269e499ef70a6385ebc17331adb0fb","last_reissued_at":"2026-06-04T01:08:29.571185Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:08:29.571185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.06006","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-04T01:08:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F340CnFW5pjXtfHgVDS5Llg9PURc0nmhaGkb7a8sNFb9Erue19mRDMW7J74ga99iBrDkrZDNQGR5WhPX+KOoDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T14:15:57.640820Z"},"content_sha256":"2cdfb799607ea23b008f1f36ffc8d81e747b17da21036aed7ccadf83e88a036f","schema_version":"1.0","event_id":"sha256:2cdfb799607ea23b008f1f36ffc8d81e747b17da21036aed7ccadf83e88a036f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YIKPG3DR7LRHJO2T6HQE43O6CP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Can VLMs Predict Future States? Bootstrapping World Models from Inverse Dynamics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Anna Korhonen, Edoardo M. Ponti, Shay B. Cohen, Yftah Ziser, Yifu Qiu","submitted_at":"2025-06-06T11:50:18Z","abstract_excerpt":"Can unified vision-language models (VLMs) perform forward dynamics prediction (FDP), i.e., predicting the future state (in image form) given the previous observation and an action (in language form)? We find that VLMs struggle to generate physically plausible transitions between frames from instructions. Nevertheless, we identify a crucial asymmetry in multimodal grounding: fine-tuning a VLM to learn inverse dynamics prediction (IDP)-effectively captioning the action between frames-is significantly easier than learning FDP. In turn, IDP can be used to bootstrap FDP through two main strategies:"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06006","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/2506.06006/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":"2026-06-04T01:08:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3wffB/0j5NH21AindiSvxYCEO0f805Il81bBH3aC86at7eroHkDevazPAQC6unOxLIASEEWMz9yUl8keTV4vDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T14:15:57.641592Z"},"content_sha256":"65e9415b0f15232d22ef6149dcf8fb5ededf870af008938041b28bef0673c563","schema_version":"1.0","event_id":"sha256:65e9415b0f15232d22ef6149dcf8fb5ededf870af008938041b28bef0673c563"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YIKPG3DR7LRHJO2T6HQE43O6CP/bundle.json","state_url":"https://pith.science/pith/YIKPG3DR7LRHJO2T6HQE43O6CP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YIKPG3DR7LRHJO2T6HQE43O6CP/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":"2026-06-06T14:15:57Z","links":{"resolver":"https://pith.science/pith/YIKPG3DR7LRHJO2T6HQE43O6CP","bundle":"https://pith.science/pith/YIKPG3DR7LRHJO2T6HQE43O6CP/bundle.json","state":"https://pith.science/pith/YIKPG3DR7LRHJO2T6HQE43O6CP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YIKPG3DR7LRHJO2T6HQE43O6CP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YIKPG3DR7LRHJO2T6HQE43O6CP","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":"362d33ebf1cf5c60d8a1979271481f5e18ca39453dc66b8a7529705c122ce523","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-06T11:50:18Z","title_canon_sha256":"ff8184da166c039c099917624887bed74af006e032f9ac1741e88760492c80b1"},"schema_version":"1.0","source":{"id":"2506.06006","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.06006","created_at":"2026-06-04T01:08:29Z"},{"alias_kind":"arxiv_version","alias_value":"2506.06006v3","created_at":"2026-06-04T01:08:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06006","created_at":"2026-06-04T01:08:29Z"},{"alias_kind":"pith_short_12","alias_value":"YIKPG3DR7LRH","created_at":"2026-06-04T01:08:29Z"},{"alias_kind":"pith_short_16","alias_value":"YIKPG3DR7LRHJO2T","created_at":"2026-06-04T01:08:29Z"},{"alias_kind":"pith_short_8","alias_value":"YIKPG3DR","created_at":"2026-06-04T01:08:29Z"}],"graph_snapshots":[{"event_id":"sha256:65e9415b0f15232d22ef6149dcf8fb5ededf870af008938041b28bef0673c563","target":"graph","created_at":"2026-06-04T01:08:29Z","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/2506.06006/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Can unified vision-language models (VLMs) perform forward dynamics prediction (FDP), i.e., predicting the future state (in image form) given the previous observation and an action (in language form)? We find that VLMs struggle to generate physically plausible transitions between frames from instructions. Nevertheless, we identify a crucial asymmetry in multimodal grounding: fine-tuning a VLM to learn inverse dynamics prediction (IDP)-effectively captioning the action between frames-is significantly easier than learning FDP. In turn, IDP can be used to bootstrap FDP through two main strategies:","authors_text":"Anna Korhonen, Edoardo M. Ponti, Shay B. Cohen, Yftah Ziser, Yifu Qiu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-06T11:50:18Z","title":"Can VLMs Predict Future States? Bootstrapping World Models from Inverse Dynamics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06006","kind":"arxiv","version":3},"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":"sha256:2cdfb799607ea23b008f1f36ffc8d81e747b17da21036aed7ccadf83e88a036f","target":"record","created_at":"2026-06-04T01:08:29Z","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":"362d33ebf1cf5c60d8a1979271481f5e18ca39453dc66b8a7529705c122ce523","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-06T11:50:18Z","title_canon_sha256":"ff8184da166c039c099917624887bed74af006e032f9ac1741e88760492c80b1"},"schema_version":"1.0","source":{"id":"2506.06006","kind":"arxiv","version":3}},"canonical_sha256":"c214f36c71fae274bb53f1e04e6dde13e7269e499ef70a6385ebc17331adb0fb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c214f36c71fae274bb53f1e04e6dde13e7269e499ef70a6385ebc17331adb0fb","first_computed_at":"2026-06-04T01:08:29.571185Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:08:29.571185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AZCLoMRgwo4vAT2MjrLCicMgREmG6US7fBN354CDh5WeyHnVPC+JFIu/2eya8ZBQ6I3vXGRvSKUT3rtfuqBSCw==","signature_status":"signed_v1","signed_at":"2026-06-04T01:08:29.571813Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.06006","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2cdfb799607ea23b008f1f36ffc8d81e747b17da21036aed7ccadf83e88a036f","sha256:65e9415b0f15232d22ef6149dcf8fb5ededf870af008938041b28bef0673c563"],"state_sha256":"69efcb9a329d1278ec8120935c13a3d365cc715361559f84c2b308d26749ed23"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HVzPnwsngeLZnrRL+MnUqrTa/tyS1m8QO2WP/IeqvZ2e8Dxz5viOsf74De5xC5unHWMb6FHMKGjGQ8hn3FY2BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T14:15:57.645264Z","bundle_sha256":"0dc5924268a56b742ac9f2be570ad858397e07b7fee50d4ae3e09921514c8bb2"}}