{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:J3Y4WSDK4OPLE7ORYUGLOUPIMB","short_pith_number":"pith:J3Y4WSDK","canonical_record":{"source":{"id":"1904.03885","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-08T08:28:54Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"2d42c36034fa986e981a8c0d909fdbf7503579cb09a0d0891669c2abf464f342","abstract_canon_sha256":"3e3b42ffa1de590447cad1fe77aa62aba89271868df027616a5ca706d6fe7470"},"schema_version":"1.0"},"canonical_sha256":"4ef1cb486ae39eb27dd1c50cb751e8604049f92f99170626e18be101e0ec714a","source":{"kind":"arxiv","id":"1904.03885","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.03885","created_at":"2026-05-17T23:49:07Z"},{"alias_kind":"arxiv_version","alias_value":"1904.03885v1","created_at":"2026-05-17T23:49:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.03885","created_at":"2026-05-17T23:49:07Z"},{"alias_kind":"pith_short_12","alias_value":"J3Y4WSDK4OPL","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"J3Y4WSDK4OPLE7OR","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"J3Y4WSDK","created_at":"2026-05-18T12:33:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:J3Y4WSDK4OPLE7ORYUGLOUPIMB","target":"record","payload":{"canonical_record":{"source":{"id":"1904.03885","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-08T08:28:54Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"2d42c36034fa986e981a8c0d909fdbf7503579cb09a0d0891669c2abf464f342","abstract_canon_sha256":"3e3b42ffa1de590447cad1fe77aa62aba89271868df027616a5ca706d6fe7470"},"schema_version":"1.0"},"canonical_sha256":"4ef1cb486ae39eb27dd1c50cb751e8604049f92f99170626e18be101e0ec714a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:07.831166Z","signature_b64":"UDYkTdVINRoO0Ur/Jl9XC5Km2eD38xucfOnxUeJmmDyekgcawg3jEv1jZOIkebJ30OOYD4qj6z8OsgGe/R+fBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ef1cb486ae39eb27dd1c50cb751e8604049f92f99170626e18be101e0ec714a","last_reissued_at":"2026-05-17T23:49:07.830637Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:07.830637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.03885","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":"2026-05-17T23:49:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QbZ7w9GpOgPpPm+ggL7Y0ZEMY+2xO7nd78rNIQNBsKRjTL5JpmziY9ID1aIZlA3JwyCymktIBnJxGrtjwwzTAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:00:15.442307Z"},"content_sha256":"02d9637f2f9ade07240b82404bd1333b2c701386e9d496a994b40f0c87a7c8c2","schema_version":"1.0","event_id":"sha256:02d9637f2f9ade07240b82404bd1333b2c701386e9d496a994b40f0c87a7c8c2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:J3Y4WSDK4OPLE7ORYUGLOUPIMB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Referring to Objects in Videos using Spatio-Temporal Identifying Descriptions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Abhinav Shrivastava, Larry S. Davis, Peratham Wiriyathammabhum, Vlad I. Morariu","submitted_at":"2019-04-08T08:28:54Z","abstract_excerpt":"This paper presents a new task, the grounding of spatio-temporal identifying descriptions in videos. Previous work suggests potential bias in existing datasets and emphasizes the need for a new data creation schema to better model linguistic structure. We introduce a new data collection scheme based on grammatical constraints for surface realization to enable us to investigate the problem of grounding spatio-temporal identifying descriptions in videos. We then propose a two-stream modular attention network that learns and grounds spatio-temporal identifying descriptions based on appearance and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.03885","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":""},"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":"2026-05-17T23:49:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/ayxHe0Phti6bHeCYCQUal6u+J82eqAhTyEyNYa4ZVDfxt1CoLTyvV1dY/b6y3nwkgUmvc49OlGIlv0YMFPlBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:00:15.443004Z"},"content_sha256":"cfe6043e0a4b0799af6974991074d739ed1712319e5495537b83b6db130710da","schema_version":"1.0","event_id":"sha256:cfe6043e0a4b0799af6974991074d739ed1712319e5495537b83b6db130710da"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J3Y4WSDK4OPLE7ORYUGLOUPIMB/bundle.json","state_url":"https://pith.science/pith/J3Y4WSDK4OPLE7ORYUGLOUPIMB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J3Y4WSDK4OPLE7ORYUGLOUPIMB/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":"2026-05-25T19:00:15Z","links":{"resolver":"https://pith.science/pith/J3Y4WSDK4OPLE7ORYUGLOUPIMB","bundle":"https://pith.science/pith/J3Y4WSDK4OPLE7ORYUGLOUPIMB/bundle.json","state":"https://pith.science/pith/J3Y4WSDK4OPLE7ORYUGLOUPIMB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J3Y4WSDK4OPLE7ORYUGLOUPIMB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:J3Y4WSDK4OPLE7ORYUGLOUPIMB","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":"3e3b42ffa1de590447cad1fe77aa62aba89271868df027616a5ca706d6fe7470","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-08T08:28:54Z","title_canon_sha256":"2d42c36034fa986e981a8c0d909fdbf7503579cb09a0d0891669c2abf464f342"},"schema_version":"1.0","source":{"id":"1904.03885","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.03885","created_at":"2026-05-17T23:49:07Z"},{"alias_kind":"arxiv_version","alias_value":"1904.03885v1","created_at":"2026-05-17T23:49:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.03885","created_at":"2026-05-17T23:49:07Z"},{"alias_kind":"pith_short_12","alias_value":"J3Y4WSDK4OPL","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"J3Y4WSDK4OPLE7OR","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"J3Y4WSDK","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:cfe6043e0a4b0799af6974991074d739ed1712319e5495537b83b6db130710da","target":"graph","created_at":"2026-05-17T23:49:07Z","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":"This paper presents a new task, the grounding of spatio-temporal identifying descriptions in videos. Previous work suggests potential bias in existing datasets and emphasizes the need for a new data creation schema to better model linguistic structure. We introduce a new data collection scheme based on grammatical constraints for surface realization to enable us to investigate the problem of grounding spatio-temporal identifying descriptions in videos. We then propose a two-stream modular attention network that learns and grounds spatio-temporal identifying descriptions based on appearance and","authors_text":"Abhinav Shrivastava, Larry S. Davis, Peratham Wiriyathammabhum, Vlad I. Morariu","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-08T08:28:54Z","title":"Referring to Objects in Videos using Spatio-Temporal Identifying Descriptions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.03885","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":"sha256:02d9637f2f9ade07240b82404bd1333b2c701386e9d496a994b40f0c87a7c8c2","target":"record","created_at":"2026-05-17T23:49:07Z","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":"3e3b42ffa1de590447cad1fe77aa62aba89271868df027616a5ca706d6fe7470","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-08T08:28:54Z","title_canon_sha256":"2d42c36034fa986e981a8c0d909fdbf7503579cb09a0d0891669c2abf464f342"},"schema_version":"1.0","source":{"id":"1904.03885","kind":"arxiv","version":1}},"canonical_sha256":"4ef1cb486ae39eb27dd1c50cb751e8604049f92f99170626e18be101e0ec714a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4ef1cb486ae39eb27dd1c50cb751e8604049f92f99170626e18be101e0ec714a","first_computed_at":"2026-05-17T23:49:07.830637Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:49:07.830637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UDYkTdVINRoO0Ur/Jl9XC5Km2eD38xucfOnxUeJmmDyekgcawg3jEv1jZOIkebJ30OOYD4qj6z8OsgGe/R+fBA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:49:07.831166Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.03885","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:02d9637f2f9ade07240b82404bd1333b2c701386e9d496a994b40f0c87a7c8c2","sha256:cfe6043e0a4b0799af6974991074d739ed1712319e5495537b83b6db130710da"],"state_sha256":"dffffe8ce06b30c7567c053aa26bf616b28549d7e864e9bee782b24ab96e2ded"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"87b++qL4FmRUFMLi2oLRj85w8r0CC76d9A9xMuwgZFD2yuqDO73og5usfYqdGQVBYf0K94OOy13WUPRi4txpAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T19:00:15.446151Z","bundle_sha256":"a7e24214ff892e6980349ffa271f43972f670bccd72d287c36267d24eaf5fb86"}}