{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:RVG4WLYWMHDE6VBE42GPP7AAJP","short_pith_number":"pith:RVG4WLYW","canonical_record":{"source":{"id":"1805.02834","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-08T05:05:56Z","cross_cats_sorted":[],"title_canon_sha256":"15a328ccd43ac2e9ae0344daf4c3d4b41ef98b9b17b52d284b9ffc135bb20212","abstract_canon_sha256":"133cb6d73850fdc36d753faac30583c26854361392d7ea5d77c8743b31b5e1d6"},"schema_version":"1.0"},"canonical_sha256":"8d4dcb2f1661c64f5424e68cf7fc004bcce961e7999b33d22c23f2e337bb2252","source":{"kind":"arxiv","id":"1805.02834","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.02834","created_at":"2026-05-18T00:10:16Z"},{"alias_kind":"arxiv_version","alias_value":"1805.02834v2","created_at":"2026-05-18T00:10:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.02834","created_at":"2026-05-18T00:10:16Z"},{"alias_kind":"pith_short_12","alias_value":"RVG4WLYWMHDE","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RVG4WLYWMHDE6VBE","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RVG4WLYW","created_at":"2026-05-18T12:32:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:RVG4WLYWMHDE6VBE42GPP7AAJP","target":"record","payload":{"canonical_record":{"source":{"id":"1805.02834","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-08T05:05:56Z","cross_cats_sorted":[],"title_canon_sha256":"15a328ccd43ac2e9ae0344daf4c3d4b41ef98b9b17b52d284b9ffc135bb20212","abstract_canon_sha256":"133cb6d73850fdc36d753faac30583c26854361392d7ea5d77c8743b31b5e1d6"},"schema_version":"1.0"},"canonical_sha256":"8d4dcb2f1661c64f5424e68cf7fc004bcce961e7999b33d22c23f2e337bb2252","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:16.795081Z","signature_b64":"JtoCaPSWXbIfZT4f3TKwdqrN/60ceYnNJnIkNuJhlOsYU+sLmqKx9/bTHT5hftDLhej2unE2f68OQcSjhg7XBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d4dcb2f1661c64f5424e68cf7fc004bcce961e7999b33d22c23f2e337bb2252","last_reissued_at":"2026-05-18T00:10:16.794549Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:16.794549Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.02834","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:10:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0YE/1Dpz35NPi+wt5AfPMMY/KlfkFohCt+N4f7KwJDPyhgMtrReYaYz1uZtA/SidvorGBw0CUzTtkd8BppoNCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T02:55:03.797448Z"},"content_sha256":"df546391f704fd852a74ea8e6ea5e04ac4bcbe3943c59b11b5334faad9d982ac","schema_version":"1.0","event_id":"sha256:df546391f704fd852a74ea8e6ea5e04ac4bcbe3943c59b11b5334faad9d982ac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:RVG4WLYWMHDE6VBE42GPP7AAJP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Weakly-Supervised Video Object Grounding from Text by Loss Weighting and Object Interaction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jason J. Corso, Luowei Zhou, Nathan Louis","submitted_at":"2018-05-08T05:05:56Z","abstract_excerpt":"We study weakly-supervised video object grounding: given a video segment and a corresponding descriptive sentence, the goal is to localize objects that are mentioned from the sentence in the video. During training, no object bounding boxes are available, but the set of possible objects to be grounded is known beforehand. Existing approaches in the image domain use Multiple Instance Learning (MIL) to ground objects by enforcing matches between visual and semantic features. A naive extension of this approach to the video domain is to treat the entire segment as a bag of spatial object proposals."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.02834","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-18T00:10:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lFyM/oxiJDs6+rFzGVnVBm6pppLyeFIQWPCK79AZVTCN+AZeIJX1pTs9KvJ4QpWVUEX052mOQ9AmS+HEPy6+AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T02:55:03.798071Z"},"content_sha256":"181867a3d952250fbaf40d7a70973d02522daab0c29e3ab36a1b7c369608e702","schema_version":"1.0","event_id":"sha256:181867a3d952250fbaf40d7a70973d02522daab0c29e3ab36a1b7c369608e702"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RVG4WLYWMHDE6VBE42GPP7AAJP/bundle.json","state_url":"https://pith.science/pith/RVG4WLYWMHDE6VBE42GPP7AAJP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RVG4WLYWMHDE6VBE42GPP7AAJP/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":"2026-05-27T02:55:03Z","links":{"resolver":"https://pith.science/pith/RVG4WLYWMHDE6VBE42GPP7AAJP","bundle":"https://pith.science/pith/RVG4WLYWMHDE6VBE42GPP7AAJP/bundle.json","state":"https://pith.science/pith/RVG4WLYWMHDE6VBE42GPP7AAJP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RVG4WLYWMHDE6VBE42GPP7AAJP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:RVG4WLYWMHDE6VBE42GPP7AAJP","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":"133cb6d73850fdc36d753faac30583c26854361392d7ea5d77c8743b31b5e1d6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-08T05:05:56Z","title_canon_sha256":"15a328ccd43ac2e9ae0344daf4c3d4b41ef98b9b17b52d284b9ffc135bb20212"},"schema_version":"1.0","source":{"id":"1805.02834","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.02834","created_at":"2026-05-18T00:10:16Z"},{"alias_kind":"arxiv_version","alias_value":"1805.02834v2","created_at":"2026-05-18T00:10:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.02834","created_at":"2026-05-18T00:10:16Z"},{"alias_kind":"pith_short_12","alias_value":"RVG4WLYWMHDE","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RVG4WLYWMHDE6VBE","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RVG4WLYW","created_at":"2026-05-18T12:32:50Z"}],"graph_snapshots":[{"event_id":"sha256:181867a3d952250fbaf40d7a70973d02522daab0c29e3ab36a1b7c369608e702","target":"graph","created_at":"2026-05-18T00:10:16Z","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"},"paper":{"abstract_excerpt":"We study weakly-supervised video object grounding: given a video segment and a corresponding descriptive sentence, the goal is to localize objects that are mentioned from the sentence in the video. During training, no object bounding boxes are available, but the set of possible objects to be grounded is known beforehand. Existing approaches in the image domain use Multiple Instance Learning (MIL) to ground objects by enforcing matches between visual and semantic features. A naive extension of this approach to the video domain is to treat the entire segment as a bag of spatial object proposals.","authors_text":"Jason J. Corso, Luowei Zhou, Nathan Louis","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-08T05:05:56Z","title":"Weakly-Supervised Video Object Grounding from Text by Loss Weighting and Object Interaction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.02834","kind":"arxiv","version":2},"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:df546391f704fd852a74ea8e6ea5e04ac4bcbe3943c59b11b5334faad9d982ac","target":"record","created_at":"2026-05-18T00:10:16Z","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":"133cb6d73850fdc36d753faac30583c26854361392d7ea5d77c8743b31b5e1d6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-08T05:05:56Z","title_canon_sha256":"15a328ccd43ac2e9ae0344daf4c3d4b41ef98b9b17b52d284b9ffc135bb20212"},"schema_version":"1.0","source":{"id":"1805.02834","kind":"arxiv","version":2}},"canonical_sha256":"8d4dcb2f1661c64f5424e68cf7fc004bcce961e7999b33d22c23f2e337bb2252","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8d4dcb2f1661c64f5424e68cf7fc004bcce961e7999b33d22c23f2e337bb2252","first_computed_at":"2026-05-18T00:10:16.794549Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:10:16.794549Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JtoCaPSWXbIfZT4f3TKwdqrN/60ceYnNJnIkNuJhlOsYU+sLmqKx9/bTHT5hftDLhej2unE2f68OQcSjhg7XBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:10:16.795081Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.02834","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:df546391f704fd852a74ea8e6ea5e04ac4bcbe3943c59b11b5334faad9d982ac","sha256:181867a3d952250fbaf40d7a70973d02522daab0c29e3ab36a1b7c369608e702"],"state_sha256":"67b57ac1945db92422bf69cf03949174297749ceac76375f6dcd4b9217166104"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GZMr8a9ovDZP9eFyb+/SZQXl8/cZnjdm66bsEMLe/ZFp1BwVYJsIWfvGpLa/6wuiGcZ8+E+Jfw/A1JruzxREDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T02:55:03.801354Z","bundle_sha256":"764d70f136f070e3b3618fef73e47935d417229e323b853229d81fc6d59c1370"}}