{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:TUQOF2F74KPVAQFQBJ4LYNO2ID","short_pith_number":"pith:TUQOF2F7","canonical_record":{"source":{"id":"2301.09209","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-22T21:30:12Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c16d199ff54c1cd9c3033ecf4f5a4696a0cd554d272ecd97f31bd43b1727b53e","abstract_canon_sha256":"31293a495c5ac2ee4ef0b1e3cdd4ff8086d3ff01375b016c0d446120e77012fe"},"schema_version":"1.0"},"canonical_sha256":"9d20e2e8bfe29f5040b00a78bc35da40e087edfd572e1a79aa454cd32c336dea","source":{"kind":"arxiv","id":"2301.09209","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.09209","created_at":"2026-07-05T07:53:59Z"},{"alias_kind":"arxiv_version","alias_value":"2301.09209v4","created_at":"2026-07-05T07:53:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.09209","created_at":"2026-07-05T07:53:59Z"},{"alias_kind":"pith_short_12","alias_value":"TUQOF2F74KPV","created_at":"2026-07-05T07:53:59Z"},{"alias_kind":"pith_short_16","alias_value":"TUQOF2F74KPVAQFQ","created_at":"2026-07-05T07:53:59Z"},{"alias_kind":"pith_short_8","alias_value":"TUQOF2F7","created_at":"2026-07-05T07:53:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:TUQOF2F74KPVAQFQBJ4LYNO2ID","target":"record","payload":{"canonical_record":{"source":{"id":"2301.09209","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-22T21:30:12Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c16d199ff54c1cd9c3033ecf4f5a4696a0cd554d272ecd97f31bd43b1727b53e","abstract_canon_sha256":"31293a495c5ac2ee4ef0b1e3cdd4ff8086d3ff01375b016c0d446120e77012fe"},"schema_version":"1.0"},"canonical_sha256":"9d20e2e8bfe29f5040b00a78bc35da40e087edfd572e1a79aa454cd32c336dea","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:53:59.136842Z","signature_b64":"NJJ9NvCEpXlnItDq0Rt+QsKIgDK2AKBrwe3A6GnhA19rKDdpUYbPSgoe3t3VJVu3Okw2EfAF7RRYj4OtpA8dDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d20e2e8bfe29f5040b00a78bc35da40e087edfd572e1a79aa454cd32c336dea","last_reissued_at":"2026-07-05T07:53:59.136351Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:53:59.136351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.09209","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:53:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bDJ1dhVlaHfpSZ3gLkQyxvzXqFF6ex+m55yXydzX/GfASTRJOWhxF1I5nlvhwVOxRirmO91gncGes6bO3/pUDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T06:46:11.669187Z"},"content_sha256":"72a9d5b9d56ed459f623259b72e8b260b92390173ebe9bdf53e3d8452b64b5b2","schema_version":"1.0","event_id":"sha256:72a9d5b9d56ed459f623259b72e8b260b92390173ebe9bdf53e3d8452b64b5b2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:TUQOF2F74KPVAQFQBJ4LYNO2ID","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Summarize the Past to Predict the Future: Natural Language Descriptions of Context Boost Multimodal Object Interaction Anticipation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Alexey Gavryushin, Kaichun Mo, Luc Van Gool, Muhammad Hamza, Otmar Hilliges, Razvan-George Pasca, Xi Wang, Yen-Ling Kuo","submitted_at":"2023-01-22T21:30:12Z","abstract_excerpt":"We study object interaction anticipation in egocentric videos. This task requires an understanding of the spatio-temporal context formed by past actions on objects, coined action context. We propose TransFusion, a multimodal transformer-based architecture. It exploits the representational power of language by summarizing the action context. TransFusion leverages pre-trained image captioning and vision-language models to extract the action context from past video frames. This action context together with the next video frame is processed by the multimodal fusion module to forecast the next obje"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.09209","kind":"arxiv","version":4},"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/2301.09209/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":"2026-07-05T07:53:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M7rLqw4c5iDdvdoyhULrNyKJJtmymrPrDEJ234u3jDdcG+99RLRCg/YOjqWCLK+KjbYTE6Q5IVbePxEQYNpnDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T06:46:11.669594Z"},"content_sha256":"80d226f2e94aa2d964862040a7be6fa6a9f1b10be0c4ec59f7cf3b446ac3c985","schema_version":"1.0","event_id":"sha256:80d226f2e94aa2d964862040a7be6fa6a9f1b10be0c4ec59f7cf3b446ac3c985"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TUQOF2F74KPVAQFQBJ4LYNO2ID/bundle.json","state_url":"https://pith.science/pith/TUQOF2F74KPVAQFQBJ4LYNO2ID/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TUQOF2F74KPVAQFQBJ4LYNO2ID/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":"2026-07-25T06:46:11Z","links":{"resolver":"https://pith.science/pith/TUQOF2F74KPVAQFQBJ4LYNO2ID","bundle":"https://pith.science/pith/TUQOF2F74KPVAQFQBJ4LYNO2ID/bundle.json","state":"https://pith.science/pith/TUQOF2F74KPVAQFQBJ4LYNO2ID/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TUQOF2F74KPVAQFQBJ4LYNO2ID/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TUQOF2F74KPVAQFQBJ4LYNO2ID","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":"31293a495c5ac2ee4ef0b1e3cdd4ff8086d3ff01375b016c0d446120e77012fe","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-22T21:30:12Z","title_canon_sha256":"c16d199ff54c1cd9c3033ecf4f5a4696a0cd554d272ecd97f31bd43b1727b53e"},"schema_version":"1.0","source":{"id":"2301.09209","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.09209","created_at":"2026-07-05T07:53:59Z"},{"alias_kind":"arxiv_version","alias_value":"2301.09209v4","created_at":"2026-07-05T07:53:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.09209","created_at":"2026-07-05T07:53:59Z"},{"alias_kind":"pith_short_12","alias_value":"TUQOF2F74KPV","created_at":"2026-07-05T07:53:59Z"},{"alias_kind":"pith_short_16","alias_value":"TUQOF2F74KPVAQFQ","created_at":"2026-07-05T07:53:59Z"},{"alias_kind":"pith_short_8","alias_value":"TUQOF2F7","created_at":"2026-07-05T07:53:59Z"}],"graph_snapshots":[{"event_id":"sha256:80d226f2e94aa2d964862040a7be6fa6a9f1b10be0c4ec59f7cf3b446ac3c985","target":"graph","created_at":"2026-07-05T07:53:59Z","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/2301.09209/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study object interaction anticipation in egocentric videos. This task requires an understanding of the spatio-temporal context formed by past actions on objects, coined action context. We propose TransFusion, a multimodal transformer-based architecture. It exploits the representational power of language by summarizing the action context. TransFusion leverages pre-trained image captioning and vision-language models to extract the action context from past video frames. This action context together with the next video frame is processed by the multimodal fusion module to forecast the next obje","authors_text":"Alexey Gavryushin, Kaichun Mo, Luc Van Gool, Muhammad Hamza, Otmar Hilliges, Razvan-George Pasca, Xi Wang, Yen-Ling Kuo","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-22T21:30:12Z","title":"Summarize the Past to Predict the Future: Natural Language Descriptions of Context Boost Multimodal Object Interaction Anticipation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.09209","kind":"arxiv","version":4},"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":"sha256:72a9d5b9d56ed459f623259b72e8b260b92390173ebe9bdf53e3d8452b64b5b2","target":"record","created_at":"2026-07-05T07:53:59Z","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":"31293a495c5ac2ee4ef0b1e3cdd4ff8086d3ff01375b016c0d446120e77012fe","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-22T21:30:12Z","title_canon_sha256":"c16d199ff54c1cd9c3033ecf4f5a4696a0cd554d272ecd97f31bd43b1727b53e"},"schema_version":"1.0","source":{"id":"2301.09209","kind":"arxiv","version":4}},"canonical_sha256":"9d20e2e8bfe29f5040b00a78bc35da40e087edfd572e1a79aa454cd32c336dea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d20e2e8bfe29f5040b00a78bc35da40e087edfd572e1a79aa454cd32c336dea","first_computed_at":"2026-07-05T07:53:59.136351Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:53:59.136351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NJJ9NvCEpXlnItDq0Rt+QsKIgDK2AKBrwe3A6GnhA19rKDdpUYbPSgoe3t3VJVu3Okw2EfAF7RRYj4OtpA8dDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:53:59.136842Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.09209","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:72a9d5b9d56ed459f623259b72e8b260b92390173ebe9bdf53e3d8452b64b5b2","sha256:80d226f2e94aa2d964862040a7be6fa6a9f1b10be0c4ec59f7cf3b446ac3c985"],"state_sha256":"28a30cf1911376f29e26826d4d4a1f69f2c18a66eb9403f4893dd4271da6de7a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KG5gmSd5SrRNKKiMRbysxXUowQzmYMq7fHTNkoF+qpCbriUiA5CSyrsf0SOIRKHkFKAIapxxlNRfh57U0MQZBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-25T06:46:11.672256Z","bundle_sha256":"6ce698e280fe1fd06f1be1658761d4c4e54b8eaf7bc4224393cd7900647b6672"}}