{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:XZLAK53GIM3ELO75RCSEVJ3MCS","short_pith_number":"pith:XZLAK53G","canonical_record":{"source":{"id":"2109.07561","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2021-09-15T20:20:04Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"2b7ef0210865f0a7497d65f77bac24181b2e0e5fa0618250bd4fcd64b77be7c3","abstract_canon_sha256":"a3f823f1f8d257f707ecf04e9b02c445907d5b604645bb399464d32adb1fc2e5"},"schema_version":"1.0"},"canonical_sha256":"be56057766433645bbfd88a44aa76c14b1957eee24184ff5e45d241d0e20112e","source":{"kind":"arxiv","id":"2109.07561","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.07561","created_at":"2026-07-05T03:14:58Z"},{"alias_kind":"arxiv_version","alias_value":"2109.07561v1","created_at":"2026-07-05T03:14:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.07561","created_at":"2026-07-05T03:14:58Z"},{"alias_kind":"pith_short_12","alias_value":"XZLAK53GIM3E","created_at":"2026-07-05T03:14:58Z"},{"alias_kind":"pith_short_16","alias_value":"XZLAK53GIM3ELO75","created_at":"2026-07-05T03:14:58Z"},{"alias_kind":"pith_short_8","alias_value":"XZLAK53G","created_at":"2026-07-05T03:14:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:XZLAK53GIM3ELO75RCSEVJ3MCS","target":"record","payload":{"canonical_record":{"source":{"id":"2109.07561","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2021-09-15T20:20:04Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"2b7ef0210865f0a7497d65f77bac24181b2e0e5fa0618250bd4fcd64b77be7c3","abstract_canon_sha256":"a3f823f1f8d257f707ecf04e9b02c445907d5b604645bb399464d32adb1fc2e5"},"schema_version":"1.0"},"canonical_sha256":"be56057766433645bbfd88a44aa76c14b1957eee24184ff5e45d241d0e20112e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:14:58.394023Z","signature_b64":"kEQO0t/lAMWD4ktWkEgkoNU3IwRLfZdX5m/CszAH874LCbiV5pPMoRXumIm1oFu2pVX7gA4uDzWYl+jkKb8/DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be56057766433645bbfd88a44aa76c14b1957eee24184ff5e45d241d0e20112e","last_reissued_at":"2026-07-05T03:14:58.393535Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:14:58.393535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.07561","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:14:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CIjnx8LMtlS7Roej6upqisu5vGO56veZ9SqSClRlDTEe8qdwsYQsodNG45kkLyCUJ0GCIYUKNonlCJEWJNVWCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T15:24:24.992230Z"},"content_sha256":"720408307fcfb99a0ca9b3672f07e29e272107508c25160ec82c1ef35ef91e49","schema_version":"1.0","event_id":"sha256:720408307fcfb99a0ca9b3672f07e29e272107508c25160ec82c1ef35ef91e49"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:XZLAK53GIM3ELO75RCSEVJ3MCS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Framework for Multisensory Foresight for Embodied Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Jivko Sinapov, Karen Panetta, Ramtin Hosseini, Xiaohui Chen","submitted_at":"2021-09-15T20:20:04Z","abstract_excerpt":"Predicting future sensory states is crucial for learning agents such as robots, drones, and autonomous vehicles. In this paper, we couple multiple sensory modalities with exploratory actions and propose a predictive neural network architecture to address this problem. Most existing approaches rely on large, manually annotated datasets, or only use visual data as a single modality. In contrast, the unsupervised method presented here uses multi-modal perceptions for predicting future visual frames. As a result, the proposed model is more comprehensive and can better capture the spatio-temporal d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.07561","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/2109.07561/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":"2026-07-05T03:14:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/X9iu+6t1dyVMApiAQeAew9+zBGBjnPu8cTOaM8UcVhHG3gYIrl+slDi9uD+Wj84QVsP/GNQuHZHZ69xecQ9Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T15:24:24.992596Z"},"content_sha256":"04058a12c5081605bf9a031e40b6825d493e59a7758e108262e523447cf20cc8","schema_version":"1.0","event_id":"sha256:04058a12c5081605bf9a031e40b6825d493e59a7758e108262e523447cf20cc8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XZLAK53GIM3ELO75RCSEVJ3MCS/bundle.json","state_url":"https://pith.science/pith/XZLAK53GIM3ELO75RCSEVJ3MCS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XZLAK53GIM3ELO75RCSEVJ3MCS/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":"2026-07-17T15:24:24Z","links":{"resolver":"https://pith.science/pith/XZLAK53GIM3ELO75RCSEVJ3MCS","bundle":"https://pith.science/pith/XZLAK53GIM3ELO75RCSEVJ3MCS/bundle.json","state":"https://pith.science/pith/XZLAK53GIM3ELO75RCSEVJ3MCS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XZLAK53GIM3ELO75RCSEVJ3MCS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:XZLAK53GIM3ELO75RCSEVJ3MCS","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":"a3f823f1f8d257f707ecf04e9b02c445907d5b604645bb399464d32adb1fc2e5","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2021-09-15T20:20:04Z","title_canon_sha256":"2b7ef0210865f0a7497d65f77bac24181b2e0e5fa0618250bd4fcd64b77be7c3"},"schema_version":"1.0","source":{"id":"2109.07561","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.07561","created_at":"2026-07-05T03:14:58Z"},{"alias_kind":"arxiv_version","alias_value":"2109.07561v1","created_at":"2026-07-05T03:14:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.07561","created_at":"2026-07-05T03:14:58Z"},{"alias_kind":"pith_short_12","alias_value":"XZLAK53GIM3E","created_at":"2026-07-05T03:14:58Z"},{"alias_kind":"pith_short_16","alias_value":"XZLAK53GIM3ELO75","created_at":"2026-07-05T03:14:58Z"},{"alias_kind":"pith_short_8","alias_value":"XZLAK53G","created_at":"2026-07-05T03:14:58Z"}],"graph_snapshots":[{"event_id":"sha256:04058a12c5081605bf9a031e40b6825d493e59a7758e108262e523447cf20cc8","target":"graph","created_at":"2026-07-05T03:14:58Z","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/2109.07561/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Predicting future sensory states is crucial for learning agents such as robots, drones, and autonomous vehicles. In this paper, we couple multiple sensory modalities with exploratory actions and propose a predictive neural network architecture to address this problem. Most existing approaches rely on large, manually annotated datasets, or only use visual data as a single modality. In contrast, the unsupervised method presented here uses multi-modal perceptions for predicting future visual frames. As a result, the proposed model is more comprehensive and can better capture the spatio-temporal d","authors_text":"Jivko Sinapov, Karen Panetta, Ramtin Hosseini, Xiaohui Chen","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2021-09-15T20:20:04Z","title":"A Framework for Multisensory Foresight for Embodied Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.07561","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":"sha256:720408307fcfb99a0ca9b3672f07e29e272107508c25160ec82c1ef35ef91e49","target":"record","created_at":"2026-07-05T03:14:58Z","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":"a3f823f1f8d257f707ecf04e9b02c445907d5b604645bb399464d32adb1fc2e5","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2021-09-15T20:20:04Z","title_canon_sha256":"2b7ef0210865f0a7497d65f77bac24181b2e0e5fa0618250bd4fcd64b77be7c3"},"schema_version":"1.0","source":{"id":"2109.07561","kind":"arxiv","version":1}},"canonical_sha256":"be56057766433645bbfd88a44aa76c14b1957eee24184ff5e45d241d0e20112e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"be56057766433645bbfd88a44aa76c14b1957eee24184ff5e45d241d0e20112e","first_computed_at":"2026-07-05T03:14:58.393535Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:14:58.393535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kEQO0t/lAMWD4ktWkEgkoNU3IwRLfZdX5m/CszAH874LCbiV5pPMoRXumIm1oFu2pVX7gA4uDzWYl+jkKb8/DA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:14:58.394023Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.07561","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:720408307fcfb99a0ca9b3672f07e29e272107508c25160ec82c1ef35ef91e49","sha256:04058a12c5081605bf9a031e40b6825d493e59a7758e108262e523447cf20cc8"],"state_sha256":"5387dbbda7272dedccf67a20d89960d05b0194436c28e48294b50a151bd28bad"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pcg9w8bbRXFtLDOPMGgsOCXrKcWBzjmUsZvH1DY7/soAMz2y7NA8v61Taw7PmdwEOasI3+aERu0OfAkBbaDfDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T15:24:24.995146Z","bundle_sha256":"d68edd3685797bb749cd01200b3716c2f6cc21ae7543c8c16cb34efd24a28935"}}