{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:NK72FEHLHSH4Y6DWH4LFROOFOI","short_pith_number":"pith:NK72FEHL","canonical_record":{"source":{"id":"2109.06085","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-13T16:01:19Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"7f4c8c9cbcd1d7bc310fdc8727766faee29e8dee37e6fe1d6afa362ea1b20e66","abstract_canon_sha256":"900664fdc511fde69137ebd9c1b9e8dd39538d92e3849ade54c1738e344aa755"},"schema_version":"1.0"},"canonical_sha256":"6abfa290eb3c8fcc78763f1658b9c57213d60fe18a81056ae07d63adaf84c38e","source":{"kind":"arxiv","id":"2109.06085","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.06085","created_at":"2026-07-05T04:13:10Z"},{"alias_kind":"arxiv_version","alias_value":"2109.06085v2","created_at":"2026-07-05T04:13:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.06085","created_at":"2026-07-05T04:13:10Z"},{"alias_kind":"pith_short_12","alias_value":"NK72FEHLHSH4","created_at":"2026-07-05T04:13:10Z"},{"alias_kind":"pith_short_16","alias_value":"NK72FEHLHSH4Y6DW","created_at":"2026-07-05T04:13:10Z"},{"alias_kind":"pith_short_8","alias_value":"NK72FEHL","created_at":"2026-07-05T04:13:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:NK72FEHLHSH4Y6DWH4LFROOFOI","target":"record","payload":{"canonical_record":{"source":{"id":"2109.06085","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-13T16:01:19Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"7f4c8c9cbcd1d7bc310fdc8727766faee29e8dee37e6fe1d6afa362ea1b20e66","abstract_canon_sha256":"900664fdc511fde69137ebd9c1b9e8dd39538d92e3849ade54c1738e344aa755"},"schema_version":"1.0"},"canonical_sha256":"6abfa290eb3c8fcc78763f1658b9c57213d60fe18a81056ae07d63adaf84c38e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:13:10.535518Z","signature_b64":"umzuwxtMwSVP08siurZPf+wZb5Ad/BNFSG2B3O966EIhNz4dEZNH9xdF21qWyQu/ucEvUIc89Zzb2mmzQ1IqBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6abfa290eb3c8fcc78763f1658b9c57213d60fe18a81056ae07d63adaf84c38e","last_reissued_at":"2026-07-05T04:13:10.535058Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:13:10.535058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.06085","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":"2026-07-05T04:13:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GpUjUifJ088s57iod/uGJuw8Trr9E/5qC0Mwq/XRzdnN3EqHCLtVIdfZgs/L1T0byYeHTldVexO4dv+ey54TAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T12:56:39.818355Z"},"content_sha256":"09a9fb6bdde494907feefbe54ef07682ab2b4fef0babc5eb6d01e1f22cf3746f","schema_version":"1.0","event_id":"sha256:09a9fb6bdde494907feefbe54ef07682ab2b4fef0babc5eb6d01e1f22cf3746f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:NK72FEHLHSH4Y6DWH4LFROOFOI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On Pursuit of Designing Multi-modal Transformer for Video Grounding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Can Zhang, Long Chen, Meng Cao, Mike Zheng Shou, Yuexian Zou","submitted_at":"2021-09-13T16:01:19Z","abstract_excerpt":"Video grounding aims to localize the temporal segment corresponding to a sentence query from an untrimmed video. Almost all existing video grounding methods fall into two frameworks: 1) Top-down model: It predefines a set of segment candidates and then conducts segment classification and regression. 2) Bottom-up model: It directly predicts frame-wise probabilities of the referential segment boundaries. However, all these methods are not end-to-end, i.e., they always rely on some time-consuming post-processing steps to refine predictions. To this end, we reformulate video grounding as a set pre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.06085","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/2109.06085/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":"2026-07-05T04:13:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SkmhyOKXiFqqnl/rQMFlow4RoXLGycZPAJUixqZsyJ8aM5OhrmAZXyy/WcKdjjVBHELqqNgnfCoxDieCP9enBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T12:56:39.818967Z"},"content_sha256":"6e50f46cfe2af01c93d8f25204a4f6bfedc26fbf816eef7e955559a36297db42","schema_version":"1.0","event_id":"sha256:6e50f46cfe2af01c93d8f25204a4f6bfedc26fbf816eef7e955559a36297db42"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NK72FEHLHSH4Y6DWH4LFROOFOI/bundle.json","state_url":"https://pith.science/pith/NK72FEHLHSH4Y6DWH4LFROOFOI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NK72FEHLHSH4Y6DWH4LFROOFOI/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":"2026-07-05T12:56:39Z","links":{"resolver":"https://pith.science/pith/NK72FEHLHSH4Y6DWH4LFROOFOI","bundle":"https://pith.science/pith/NK72FEHLHSH4Y6DWH4LFROOFOI/bundle.json","state":"https://pith.science/pith/NK72FEHLHSH4Y6DWH4LFROOFOI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NK72FEHLHSH4Y6DWH4LFROOFOI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:NK72FEHLHSH4Y6DWH4LFROOFOI","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":"900664fdc511fde69137ebd9c1b9e8dd39538d92e3849ade54c1738e344aa755","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-13T16:01:19Z","title_canon_sha256":"7f4c8c9cbcd1d7bc310fdc8727766faee29e8dee37e6fe1d6afa362ea1b20e66"},"schema_version":"1.0","source":{"id":"2109.06085","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.06085","created_at":"2026-07-05T04:13:10Z"},{"alias_kind":"arxiv_version","alias_value":"2109.06085v2","created_at":"2026-07-05T04:13:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.06085","created_at":"2026-07-05T04:13:10Z"},{"alias_kind":"pith_short_12","alias_value":"NK72FEHLHSH4","created_at":"2026-07-05T04:13:10Z"},{"alias_kind":"pith_short_16","alias_value":"NK72FEHLHSH4Y6DW","created_at":"2026-07-05T04:13:10Z"},{"alias_kind":"pith_short_8","alias_value":"NK72FEHL","created_at":"2026-07-05T04:13:10Z"}],"graph_snapshots":[{"event_id":"sha256:6e50f46cfe2af01c93d8f25204a4f6bfedc26fbf816eef7e955559a36297db42","target":"graph","created_at":"2026-07-05T04:13:10Z","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/2109.06085/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video grounding aims to localize the temporal segment corresponding to a sentence query from an untrimmed video. Almost all existing video grounding methods fall into two frameworks: 1) Top-down model: It predefines a set of segment candidates and then conducts segment classification and regression. 2) Bottom-up model: It directly predicts frame-wise probabilities of the referential segment boundaries. However, all these methods are not end-to-end, i.e., they always rely on some time-consuming post-processing steps to refine predictions. To this end, we reformulate video grounding as a set pre","authors_text":"Can Zhang, Long Chen, Meng Cao, Mike Zheng Shou, Yuexian Zou","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-13T16:01:19Z","title":"On Pursuit of Designing Multi-modal Transformer for Video Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.06085","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":"sha256:09a9fb6bdde494907feefbe54ef07682ab2b4fef0babc5eb6d01e1f22cf3746f","target":"record","created_at":"2026-07-05T04:13:10Z","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":"900664fdc511fde69137ebd9c1b9e8dd39538d92e3849ade54c1738e344aa755","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-13T16:01:19Z","title_canon_sha256":"7f4c8c9cbcd1d7bc310fdc8727766faee29e8dee37e6fe1d6afa362ea1b20e66"},"schema_version":"1.0","source":{"id":"2109.06085","kind":"arxiv","version":2}},"canonical_sha256":"6abfa290eb3c8fcc78763f1658b9c57213d60fe18a81056ae07d63adaf84c38e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6abfa290eb3c8fcc78763f1658b9c57213d60fe18a81056ae07d63adaf84c38e","first_computed_at":"2026-07-05T04:13:10.535058Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:13:10.535058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"umzuwxtMwSVP08siurZPf+wZb5Ad/BNFSG2B3O966EIhNz4dEZNH9xdF21qWyQu/ucEvUIc89Zzb2mmzQ1IqBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:13:10.535518Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.06085","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:09a9fb6bdde494907feefbe54ef07682ab2b4fef0babc5eb6d01e1f22cf3746f","sha256:6e50f46cfe2af01c93d8f25204a4f6bfedc26fbf816eef7e955559a36297db42"],"state_sha256":"4b79132d08f889b90f30f79b87a165c34b9426d88dd40192f231b8931b0247d8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0/WmNIs8Vd3zMe8n10Uz8/9dd2b1gKM4mXns1YOf62deFYJpvoQYB2f3JfATuPIVSdl3YuwMbyJdbElCdclABQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T12:56:39.822674Z","bundle_sha256":"cee57b07aa6fd3b410a66025a6812fc2e714f275a1150578222ceaa71e3c00ec"}}