{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:FNGCTSYUKOADZR5VEOM2C25HVZ","short_pith_number":"pith:FNGCTSYU","canonical_record":{"source":{"id":"2203.08013","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-15T15:50:45Z","cross_cats_sorted":[],"title_canon_sha256":"3646259b7efcedcb355c8bcdc48c4217179ab57f98f6cadf72049a6585de2826","abstract_canon_sha256":"7ac48d7480a942daaa2d13378d4795c243e1a67bcc93da851f8094882726f638"},"schema_version":"1.0"},"canonical_sha256":"2b4c29cb1453803cc7b52399a16ba7ae76de15c60c85af6f78e9c9a8758b44cc","source":{"kind":"arxiv","id":"2203.08013","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.08013","created_at":"2026-07-05T04:25:16Z"},{"alias_kind":"arxiv_version","alias_value":"2203.08013v2","created_at":"2026-07-05T04:25:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.08013","created_at":"2026-07-05T04:25:16Z"},{"alias_kind":"pith_short_12","alias_value":"FNGCTSYUKOAD","created_at":"2026-07-05T04:25:16Z"},{"alias_kind":"pith_short_16","alias_value":"FNGCTSYUKOADZR5V","created_at":"2026-07-05T04:25:16Z"},{"alias_kind":"pith_short_8","alias_value":"FNGCTSYU","created_at":"2026-07-05T04:25:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:FNGCTSYUKOADZR5VEOM2C25HVZ","target":"record","payload":{"canonical_record":{"source":{"id":"2203.08013","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-15T15:50:45Z","cross_cats_sorted":[],"title_canon_sha256":"3646259b7efcedcb355c8bcdc48c4217179ab57f98f6cadf72049a6585de2826","abstract_canon_sha256":"7ac48d7480a942daaa2d13378d4795c243e1a67bcc93da851f8094882726f638"},"schema_version":"1.0"},"canonical_sha256":"2b4c29cb1453803cc7b52399a16ba7ae76de15c60c85af6f78e9c9a8758b44cc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:25:16.428343Z","signature_b64":"RLY971rfLpvO8NluxWgZ3GiU4eU3Ae/ZrfthkjWL591DwMZZ5Cu50k8UrSEnqws937neqkPLMwoSf2N3Mgn9Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b4c29cb1453803cc7b52399a16ba7ae76de15c60c85af6f78e9c9a8758b44cc","last_reissued_at":"2026-07-05T04:25:16.427928Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:25:16.427928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.08013","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":"2026-07-05T04:25:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uMNgqfW3fhjvtl+ymHjQ/D5B7GHRA0btuIMd2d035KFjWTQPNR+5ZS0xOtctN98Qi0dj2hsiMzBErKra+Jb6AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T00:42:17.691372Z"},"content_sha256":"cd019af0e472069a9ad7c83655b3383e6d67d6a669267dd95c11b60fa294d9df","schema_version":"1.0","event_id":"sha256:cd019af0e472069a9ad7c83655b3383e6d67d6a669267dd95c11b60fa294d9df"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:FNGCTSYUKOADZR5VEOM2C25HVZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"End-to-End Modeling via Information Tree for One-Shot Natural Language Spatial Video Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fei Wu, Haoyu Zhang, Jiaxu Miao, Jin Wang, Mengze Li, Peng Wang, Shengyu Zhang, Shiliang Pu, Tianbao Wang, Wenming Tan, Wenqiao Zhang, Zhou Zhao","submitted_at":"2022-03-15T15:50:45Z","abstract_excerpt":"Natural language spatial video grounding aims to detect the relevant objects in video frames with descriptive sentences as the query. In spite of the great advances, most existing methods rely on dense video frame annotations, which require a tremendous amount of human effort. To achieve effective grounding under a limited annotation budget, we investigate one-shot video grounding, and learn to ground natural language in all video frames with solely one frame labeled, in an end-to-end manner. One major challenge of end-to-end one-shot video grounding is the existence of videos frames that are "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.08013","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2203.08013/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":"2026-07-05T04:25:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hm6WSF3m1CjrZtbuOURPIlEUYGW1xOix/1/0PxXAV5tRmzt61mQvGMOC6SIS+BkgJUk//ij32rbkWeoGOgpKCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T00:42:17.692210Z"},"content_sha256":"50fd4813c8161756008a53339be4aea05108c89d468f701f280bebbfd65faca3","schema_version":"1.0","event_id":"sha256:50fd4813c8161756008a53339be4aea05108c89d468f701f280bebbfd65faca3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FNGCTSYUKOADZR5VEOM2C25HVZ/bundle.json","state_url":"https://pith.science/pith/FNGCTSYUKOADZR5VEOM2C25HVZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FNGCTSYUKOADZR5VEOM2C25HVZ/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":"2026-08-08T00:42:17Z","links":{"resolver":"https://pith.science/pith/FNGCTSYUKOADZR5VEOM2C25HVZ","bundle":"https://pith.science/pith/FNGCTSYUKOADZR5VEOM2C25HVZ/bundle.json","state":"https://pith.science/pith/FNGCTSYUKOADZR5VEOM2C25HVZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FNGCTSYUKOADZR5VEOM2C25HVZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:FNGCTSYUKOADZR5VEOM2C25HVZ","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":"7ac48d7480a942daaa2d13378d4795c243e1a67bcc93da851f8094882726f638","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-15T15:50:45Z","title_canon_sha256":"3646259b7efcedcb355c8bcdc48c4217179ab57f98f6cadf72049a6585de2826"},"schema_version":"1.0","source":{"id":"2203.08013","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.08013","created_at":"2026-07-05T04:25:16Z"},{"alias_kind":"arxiv_version","alias_value":"2203.08013v2","created_at":"2026-07-05T04:25:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.08013","created_at":"2026-07-05T04:25:16Z"},{"alias_kind":"pith_short_12","alias_value":"FNGCTSYUKOAD","created_at":"2026-07-05T04:25:16Z"},{"alias_kind":"pith_short_16","alias_value":"FNGCTSYUKOADZR5V","created_at":"2026-07-05T04:25:16Z"},{"alias_kind":"pith_short_8","alias_value":"FNGCTSYU","created_at":"2026-07-05T04:25:16Z"}],"graph_snapshots":[{"event_id":"sha256:50fd4813c8161756008a53339be4aea05108c89d468f701f280bebbfd65faca3","target":"graph","created_at":"2026-07-05T04:25:16Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2203.08013/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Natural language spatial video grounding aims to detect the relevant objects in video frames with descriptive sentences as the query. In spite of the great advances, most existing methods rely on dense video frame annotations, which require a tremendous amount of human effort. To achieve effective grounding under a limited annotation budget, we investigate one-shot video grounding, and learn to ground natural language in all video frames with solely one frame labeled, in an end-to-end manner. One major challenge of end-to-end one-shot video grounding is the existence of videos frames that are ","authors_text":"Fei Wu, Haoyu Zhang, Jiaxu Miao, Jin Wang, Mengze Li, Peng Wang, Shengyu Zhang, Shiliang Pu, Tianbao Wang, Wenming Tan, Wenqiao Zhang, Zhou Zhao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-15T15:50:45Z","title":"End-to-End Modeling via Information Tree for One-Shot Natural Language Spatial Video Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.08013","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:cd019af0e472069a9ad7c83655b3383e6d67d6a669267dd95c11b60fa294d9df","target":"record","created_at":"2026-07-05T04:25:16Z","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":"7ac48d7480a942daaa2d13378d4795c243e1a67bcc93da851f8094882726f638","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-15T15:50:45Z","title_canon_sha256":"3646259b7efcedcb355c8bcdc48c4217179ab57f98f6cadf72049a6585de2826"},"schema_version":"1.0","source":{"id":"2203.08013","kind":"arxiv","version":2}},"canonical_sha256":"2b4c29cb1453803cc7b52399a16ba7ae76de15c60c85af6f78e9c9a8758b44cc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b4c29cb1453803cc7b52399a16ba7ae76de15c60c85af6f78e9c9a8758b44cc","first_computed_at":"2026-07-05T04:25:16.427928Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:25:16.427928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RLY971rfLpvO8NluxWgZ3GiU4eU3Ae/ZrfthkjWL591DwMZZ5Cu50k8UrSEnqws937neqkPLMwoSf2N3Mgn9Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:25:16.428343Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.08013","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cd019af0e472069a9ad7c83655b3383e6d67d6a669267dd95c11b60fa294d9df","sha256:50fd4813c8161756008a53339be4aea05108c89d468f701f280bebbfd65faca3"],"state_sha256":"77120910d6313f1c64b4e5b662e883d60e4961066be0df710c185ede1648ad90"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OmwnzpmchKeGjvKLNb17Uuk+c6xL9iwwEJMg35B1pcey92klxACjf4JIaOqyWJ95kaxg0OARefuk9sHNtBqJBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T00:42:17.697908Z","bundle_sha256":"ce96c832a0620abfbe18903f9c83e51cb1494ef333a957fc64fe71d95339dd1c"}}