{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:E4EOFOD5BVMUL37J6UQN4D2YJC","short_pith_number":"pith:E4EOFOD5","canonical_record":{"source":{"id":"2103.12346","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-23T06:42:49Z","cross_cats_sorted":[],"title_canon_sha256":"fb763581614b982ea53318a3d332710af7a86083cb3a1ef3a9b56c2346d3ba60","abstract_canon_sha256":"5dccc272e4b322cc5fcfd9af219fd1a69c64d1ea2e9f5a313e9061e42b0f04a5"},"schema_version":"1.0"},"canonical_sha256":"2708e2b87d0d5945efe9f520de0f5848a3143ce316d4fb5176250856bda3ec20","source":{"kind":"arxiv","id":"2103.12346","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.12346","created_at":"2026-07-05T02:25:45Z"},{"alias_kind":"arxiv_version","alias_value":"2103.12346v1","created_at":"2026-07-05T02:25:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.12346","created_at":"2026-07-05T02:25:45Z"},{"alias_kind":"pith_short_12","alias_value":"E4EOFOD5BVMU","created_at":"2026-07-05T02:25:45Z"},{"alias_kind":"pith_short_16","alias_value":"E4EOFOD5BVMUL37J","created_at":"2026-07-05T02:25:45Z"},{"alias_kind":"pith_short_8","alias_value":"E4EOFOD5","created_at":"2026-07-05T02:25:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:E4EOFOD5BVMUL37J6UQN4D2YJC","target":"record","payload":{"canonical_record":{"source":{"id":"2103.12346","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-23T06:42:49Z","cross_cats_sorted":[],"title_canon_sha256":"fb763581614b982ea53318a3d332710af7a86083cb3a1ef3a9b56c2346d3ba60","abstract_canon_sha256":"5dccc272e4b322cc5fcfd9af219fd1a69c64d1ea2e9f5a313e9061e42b0f04a5"},"schema_version":"1.0"},"canonical_sha256":"2708e2b87d0d5945efe9f520de0f5848a3143ce316d4fb5176250856bda3ec20","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:25:45.736114Z","signature_b64":"gcJ7gGhRARXOpGhi5xTytoCplXiUiT9LQtEYB56fp2USxWJL25merMuyFMsR4MpACukL2BeykCIDrPUKe7cwBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2708e2b87d0d5945efe9f520de0f5848a3143ce316d4fb5176250856bda3ec20","last_reissued_at":"2026-07-05T02:25:45.735534Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:25:45.735534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.12346","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":"2026-07-05T02:25:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BYg8zyFP/0jiizBrd/f19AHsQSPDHALPXIj1TvrL8rfQ6KtUzgrR/dqlUtlmvPGoCSqMyT2Qt1bojbEUMcavCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:43:56.854847Z"},"content_sha256":"26b94f357dd70c0d8d4a2ebda50f4bd277b2eea3903fdcd6220ede599873b7cc","schema_version":"1.0","event_id":"sha256:26b94f357dd70c0d8d4a2ebda50f4bd277b2eea3903fdcd6220ede599873b7cc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:E4EOFOD5BVMUL37J6UQN4D2YJC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Co-Grounding Networks with Semantic Attention for Referring Expression Comprehension in Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiaying Liu, Shih-Fu Chang, Sijie Song, Xudong Lin, Zongming Guo","submitted_at":"2021-03-23T06:42:49Z","abstract_excerpt":"In this paper, we address the problem of referring expression comprehension in videos, which is challenging due to complex expression and scene dynamics. Unlike previous methods which solve the problem in multiple stages (i.e., tracking, proposal-based matching), we tackle the problem from a novel perspective, \\textbf{co-grounding}, with an elegant one-stage framework. We enhance the single-frame grounding accuracy by semantic attention learning and improve the cross-frame grounding consistency with co-grounding feature learning. Semantic attention learning explicitly parses referring cues in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.12346","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/2103.12346/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":"2026-07-05T02:25:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dvihKHktuFprJg1q7no+bNlviKaNfDWdeuvmqSnRFH2mtoqNbX95NTOWhASLK4EJ77tzdBqi3osbdCrwBFXxBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:43:56.855344Z"},"content_sha256":"9ac25f4b95f645b0a2ded2dc1a8b420118c4a68dbf8e776122b7056f9a71eea5","schema_version":"1.0","event_id":"sha256:9ac25f4b95f645b0a2ded2dc1a8b420118c4a68dbf8e776122b7056f9a71eea5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E4EOFOD5BVMUL37J6UQN4D2YJC/bundle.json","state_url":"https://pith.science/pith/E4EOFOD5BVMUL37J6UQN4D2YJC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E4EOFOD5BVMUL37J6UQN4D2YJC/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":"2026-08-05T17:43:56Z","links":{"resolver":"https://pith.science/pith/E4EOFOD5BVMUL37J6UQN4D2YJC","bundle":"https://pith.science/pith/E4EOFOD5BVMUL37J6UQN4D2YJC/bundle.json","state":"https://pith.science/pith/E4EOFOD5BVMUL37J6UQN4D2YJC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E4EOFOD5BVMUL37J6UQN4D2YJC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:E4EOFOD5BVMUL37J6UQN4D2YJC","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":"5dccc272e4b322cc5fcfd9af219fd1a69c64d1ea2e9f5a313e9061e42b0f04a5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-23T06:42:49Z","title_canon_sha256":"fb763581614b982ea53318a3d332710af7a86083cb3a1ef3a9b56c2346d3ba60"},"schema_version":"1.0","source":{"id":"2103.12346","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.12346","created_at":"2026-07-05T02:25:45Z"},{"alias_kind":"arxiv_version","alias_value":"2103.12346v1","created_at":"2026-07-05T02:25:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.12346","created_at":"2026-07-05T02:25:45Z"},{"alias_kind":"pith_short_12","alias_value":"E4EOFOD5BVMU","created_at":"2026-07-05T02:25:45Z"},{"alias_kind":"pith_short_16","alias_value":"E4EOFOD5BVMUL37J","created_at":"2026-07-05T02:25:45Z"},{"alias_kind":"pith_short_8","alias_value":"E4EOFOD5","created_at":"2026-07-05T02:25:45Z"}],"graph_snapshots":[{"event_id":"sha256:9ac25f4b95f645b0a2ded2dc1a8b420118c4a68dbf8e776122b7056f9a71eea5","target":"graph","created_at":"2026-07-05T02:25:45Z","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/2103.12346/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we address the problem of referring expression comprehension in videos, which is challenging due to complex expression and scene dynamics. Unlike previous methods which solve the problem in multiple stages (i.e., tracking, proposal-based matching), we tackle the problem from a novel perspective, \\textbf{co-grounding}, with an elegant one-stage framework. We enhance the single-frame grounding accuracy by semantic attention learning and improve the cross-frame grounding consistency with co-grounding feature learning. Semantic attention learning explicitly parses referring cues in ","authors_text":"Jiaying Liu, Shih-Fu Chang, Sijie Song, Xudong Lin, Zongming Guo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-23T06:42:49Z","title":"Co-Grounding Networks with Semantic Attention for Referring Expression Comprehension in Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.12346","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":"sha256:26b94f357dd70c0d8d4a2ebda50f4bd277b2eea3903fdcd6220ede599873b7cc","target":"record","created_at":"2026-07-05T02:25:45Z","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":"5dccc272e4b322cc5fcfd9af219fd1a69c64d1ea2e9f5a313e9061e42b0f04a5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-23T06:42:49Z","title_canon_sha256":"fb763581614b982ea53318a3d332710af7a86083cb3a1ef3a9b56c2346d3ba60"},"schema_version":"1.0","source":{"id":"2103.12346","kind":"arxiv","version":1}},"canonical_sha256":"2708e2b87d0d5945efe9f520de0f5848a3143ce316d4fb5176250856bda3ec20","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2708e2b87d0d5945efe9f520de0f5848a3143ce316d4fb5176250856bda3ec20","first_computed_at":"2026-07-05T02:25:45.735534Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:25:45.735534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gcJ7gGhRARXOpGhi5xTytoCplXiUiT9LQtEYB56fp2USxWJL25merMuyFMsR4MpACukL2BeykCIDrPUKe7cwBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:25:45.736114Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.12346","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:26b94f357dd70c0d8d4a2ebda50f4bd277b2eea3903fdcd6220ede599873b7cc","sha256:9ac25f4b95f645b0a2ded2dc1a8b420118c4a68dbf8e776122b7056f9a71eea5"],"state_sha256":"ce1acb1cb5cb079071e6f15f6f2d5e5ee4f0508fa644f69286a8d79b7c40488f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jvobi9ARZxuM8rz7zPVJNZcKkbv/Qcjc2UtYlZBaYblBnF6+ZbtEjtES/GG4SXKQ3t9C4HebmAMYTgcJ2RJSBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T17:43:56.860308Z","bundle_sha256":"111105f0d892872f91fe9f0ff99ab22c5492f85cd41dc0637f91aebe192d812d"}}