{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:VHTUWRXOTLAX6BYFW3ZF67VSA4","short_pith_number":"pith:VHTUWRXO","canonical_record":{"source":{"id":"2310.16402","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-25T06:38:42Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e2a573c8073db0a4cf53d31309361937cc4f78dc525dbaa9c95d2ac6dc08bbf4","abstract_canon_sha256":"80e6afa93a1d4fcbbaed76df51fab445f8e26b13dda26046171042489a861805"},"schema_version":"1.0"},"canonical_sha256":"a9e74b46ee9ac17f0705b6f25f7eb2073221f57e88983034112291db66591c91","source":{"kind":"arxiv","id":"2310.16402","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.16402","created_at":"2026-07-05T07:04:56Z"},{"alias_kind":"arxiv_version","alias_value":"2310.16402v1","created_at":"2026-07-05T07:04:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16402","created_at":"2026-07-05T07:04:56Z"},{"alias_kind":"pith_short_12","alias_value":"VHTUWRXOTLAX","created_at":"2026-07-05T07:04:56Z"},{"alias_kind":"pith_short_16","alias_value":"VHTUWRXOTLAX6BYF","created_at":"2026-07-05T07:04:56Z"},{"alias_kind":"pith_short_8","alias_value":"VHTUWRXO","created_at":"2026-07-05T07:04:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:VHTUWRXOTLAX6BYFW3ZF67VSA4","target":"record","payload":{"canonical_record":{"source":{"id":"2310.16402","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-25T06:38:42Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e2a573c8073db0a4cf53d31309361937cc4f78dc525dbaa9c95d2ac6dc08bbf4","abstract_canon_sha256":"80e6afa93a1d4fcbbaed76df51fab445f8e26b13dda26046171042489a861805"},"schema_version":"1.0"},"canonical_sha256":"a9e74b46ee9ac17f0705b6f25f7eb2073221f57e88983034112291db66591c91","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:56.982625Z","signature_b64":"iKUTh9fwgsrfYQlr57mtvlTIzyAJ51BYn8w17VRl+J6alJD2RbZbhdkSauMaWartT2goKWoOJkRMELERYwkSCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9e74b46ee9ac17f0705b6f25f7eb2073221f57e88983034112291db66591c91","last_reissued_at":"2026-07-05T07:04:56.982212Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:56.982212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.16402","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":"2026-07-05T07:04:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8Az+frbgrrVTL4p/9bx2p4A60jxxAh/vP8XXxHq5eGnSIoEoh/PTVqIpM6n5nj9FAGJehPFhzLrMZMCj7KtbDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T15:47:57.196068Z"},"content_sha256":"ffcca32ff817edc29532d54415f0d4be0c6add12c6636670c1f5d12ae6610ad1","schema_version":"1.0","event_id":"sha256:ffcca32ff817edc29532d54415f0d4be0c6add12c6636670c1f5d12ae6610ad1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:VHTUWRXOTLAX6BYFW3ZF67VSA4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Video Referring Expression Comprehension via Transformer with Content-conditioned Query","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Ji Jiang, Long Chen, Meng Cao, Tengtao Song, Yi Wang, Yuexian Zou","submitted_at":"2023-10-25T06:38:42Z","abstract_excerpt":"Video Referring Expression Comprehension (REC) aims to localize a target object in videos based on the queried natural language. Recent improvements in video REC have been made using Transformer-based methods with learnable queries. However, we contend that this naive query design is not ideal given the open-world nature of video REC brought by text supervision. With numerous potential semantic categories, relying on only a few slow-updated queries is insufficient to characterize them. Our solution to this problem is to create dynamic queries that are conditioned on both the input video and la"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16402","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/2310.16402/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":"2026-07-05T07:04:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Sh6wUQrgMrR0UZUQF9zgwIOiSTfXDO8XOOCa3Dav8ksvoeFgY4Rhu3wJ8QvxJQmBoZRbWHabyzr0/ULoU4SgDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T15:47:57.196710Z"},"content_sha256":"18de69d013c64decc9aea6a06eb3571a0ddbf0abaac81adedc3feb0627c445db","schema_version":"1.0","event_id":"sha256:18de69d013c64decc9aea6a06eb3571a0ddbf0abaac81adedc3feb0627c445db"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VHTUWRXOTLAX6BYFW3ZF67VSA4/bundle.json","state_url":"https://pith.science/pith/VHTUWRXOTLAX6BYFW3ZF67VSA4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VHTUWRXOTLAX6BYFW3ZF67VSA4/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":"2026-07-05T15:47:57Z","links":{"resolver":"https://pith.science/pith/VHTUWRXOTLAX6BYFW3ZF67VSA4","bundle":"https://pith.science/pith/VHTUWRXOTLAX6BYFW3ZF67VSA4/bundle.json","state":"https://pith.science/pith/VHTUWRXOTLAX6BYFW3ZF67VSA4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VHTUWRXOTLAX6BYFW3ZF67VSA4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VHTUWRXOTLAX6BYFW3ZF67VSA4","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":"80e6afa93a1d4fcbbaed76df51fab445f8e26b13dda26046171042489a861805","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-25T06:38:42Z","title_canon_sha256":"e2a573c8073db0a4cf53d31309361937cc4f78dc525dbaa9c95d2ac6dc08bbf4"},"schema_version":"1.0","source":{"id":"2310.16402","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.16402","created_at":"2026-07-05T07:04:56Z"},{"alias_kind":"arxiv_version","alias_value":"2310.16402v1","created_at":"2026-07-05T07:04:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16402","created_at":"2026-07-05T07:04:56Z"},{"alias_kind":"pith_short_12","alias_value":"VHTUWRXOTLAX","created_at":"2026-07-05T07:04:56Z"},{"alias_kind":"pith_short_16","alias_value":"VHTUWRXOTLAX6BYF","created_at":"2026-07-05T07:04:56Z"},{"alias_kind":"pith_short_8","alias_value":"VHTUWRXO","created_at":"2026-07-05T07:04:56Z"}],"graph_snapshots":[{"event_id":"sha256:18de69d013c64decc9aea6a06eb3571a0ddbf0abaac81adedc3feb0627c445db","target":"graph","created_at":"2026-07-05T07:04:56Z","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/2310.16402/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video Referring Expression Comprehension (REC) aims to localize a target object in videos based on the queried natural language. Recent improvements in video REC have been made using Transformer-based methods with learnable queries. However, we contend that this naive query design is not ideal given the open-world nature of video REC brought by text supervision. With numerous potential semantic categories, relying on only a few slow-updated queries is insufficient to characterize them. Our solution to this problem is to create dynamic queries that are conditioned on both the input video and la","authors_text":"Ji Jiang, Long Chen, Meng Cao, Tengtao Song, Yi Wang, Yuexian Zou","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-25T06:38:42Z","title":"Video Referring Expression Comprehension via Transformer with Content-conditioned Query"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16402","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:ffcca32ff817edc29532d54415f0d4be0c6add12c6636670c1f5d12ae6610ad1","target":"record","created_at":"2026-07-05T07:04:56Z","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":"80e6afa93a1d4fcbbaed76df51fab445f8e26b13dda26046171042489a861805","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-25T06:38:42Z","title_canon_sha256":"e2a573c8073db0a4cf53d31309361937cc4f78dc525dbaa9c95d2ac6dc08bbf4"},"schema_version":"1.0","source":{"id":"2310.16402","kind":"arxiv","version":1}},"canonical_sha256":"a9e74b46ee9ac17f0705b6f25f7eb2073221f57e88983034112291db66591c91","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a9e74b46ee9ac17f0705b6f25f7eb2073221f57e88983034112291db66591c91","first_computed_at":"2026-07-05T07:04:56.982212Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:04:56.982212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iKUTh9fwgsrfYQlr57mtvlTIzyAJ51BYn8w17VRl+J6alJD2RbZbhdkSauMaWartT2goKWoOJkRMELERYwkSCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:04:56.982625Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.16402","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ffcca32ff817edc29532d54415f0d4be0c6add12c6636670c1f5d12ae6610ad1","sha256:18de69d013c64decc9aea6a06eb3571a0ddbf0abaac81adedc3feb0627c445db"],"state_sha256":"f2db20df3e1e8cf5958bd2eac37bfbaf11f244124ec8c765e334da79634d32fb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8avokK9XNuio0Ape1e9KwAiGFFnV/7j7tTEiIkvpok2RKy5uerH3dZMjQvKlUFUeDumwCn03Vc4VQPG2RDATBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T15:47:57.200622Z","bundle_sha256":"57f72dfad78ed2380b57693911c41fbfeaf9fea758f149c6875453b0aebf3065"}}