{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:NWB7OV24C35KUNU6URVIYLD25V","short_pith_number":"pith:NWB7OV24","canonical_record":{"source":{"id":"2208.04215","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-08T15:39:54Z","cross_cats_sorted":[],"title_canon_sha256":"e6717314382ed0299b0b593fb3d5d402db8c373cda5cd83fed0aa5ce6d86f2b5","abstract_canon_sha256":"ec0ee129032c8574617c97f507472b78ae653d5a5f473c7b1e724a68907f6268"},"schema_version":"1.0"},"canonical_sha256":"6d83f7575c16faaa369ea46a8c2c7aed62fb98fcb889466564d886003f7d9694","source":{"kind":"arxiv","id":"2208.04215","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.04215","created_at":"2026-07-05T04:46:55Z"},{"alias_kind":"arxiv_version","alias_value":"2208.04215v2","created_at":"2026-07-05T04:46:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.04215","created_at":"2026-07-05T04:46:55Z"},{"alias_kind":"pith_short_12","alias_value":"NWB7OV24C35K","created_at":"2026-07-05T04:46:55Z"},{"alias_kind":"pith_short_16","alias_value":"NWB7OV24C35KUNU6","created_at":"2026-07-05T04:46:55Z"},{"alias_kind":"pith_short_8","alias_value":"NWB7OV24","created_at":"2026-07-05T04:46:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:NWB7OV24C35KUNU6URVIYLD25V","target":"record","payload":{"canonical_record":{"source":{"id":"2208.04215","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-08T15:39:54Z","cross_cats_sorted":[],"title_canon_sha256":"e6717314382ed0299b0b593fb3d5d402db8c373cda5cd83fed0aa5ce6d86f2b5","abstract_canon_sha256":"ec0ee129032c8574617c97f507472b78ae653d5a5f473c7b1e724a68907f6268"},"schema_version":"1.0"},"canonical_sha256":"6d83f7575c16faaa369ea46a8c2c7aed62fb98fcb889466564d886003f7d9694","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:46:55.457669Z","signature_b64":"ScOf55gwTKSpNKWCXancr3A0z0icXIm+Zn+SjYOs3n3+w6DWBtUBrCcgHq47La+8++P1Oj08RSX1xQJQ52gWCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d83f7575c16faaa369ea46a8c2c7aed62fb98fcb889466564d886003f7d9694","last_reissued_at":"2026-07-05T04:46:55.457326Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:46:55.457326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2208.04215","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":"2026-07-05T04:46:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RdqPO/k/qZlDZmgbEHJX9i3oB+hGSqxuQfd+xnuLm45V2usUZhfz6Ri03MEdq7yWPPCVOpHY0x5PAii+9clLCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:48:12.440935Z"},"content_sha256":"55c38111c0c4fe271f79f7e25752423a8583d3e48306583da4e5c19eb50be417","schema_version":"1.0","event_id":"sha256:55c38111c0c4fe271f79f7e25752423a8583d3e48306583da4e5c19eb50be417"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:NWB7OV24C35KUNU6URVIYLD25V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Boosting Video-Text Retrieval with Explicit High-Level Semantics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Di Xu, Dongliang He, Errui Ding, Fu Li, Haoran Wang, Jungong Han, Zhong Ji","submitted_at":"2022-08-08T15:39:54Z","abstract_excerpt":"Video-text retrieval (VTR) is an attractive yet challenging task for multi-modal understanding, which aims to search for relevant video (text) given a query (video). Existing methods typically employ completely heterogeneous visual-textual information to align video and text, whilst lacking the awareness of homogeneous high-level semantic information residing in both modalities. To fill this gap, in this work, we propose a novel visual-linguistic aligning model named HiSE for VTR, which improves the cross-modal representation by incorporating explicit high-level semantics. First, we explore th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.04215","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/2208.04215/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":"2026-07-05T04:46:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YIP7jBPsivmC/hn6gEmSkxS/lrugR19QWORnboYkNps/S3ZzWLU5pUSGc8Oxhc9VO5O6tG3FpUKyL8bhpWYRAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:48:12.441414Z"},"content_sha256":"6290e716c8f6fd634bffb0adc5cc1c850af9b12a8bcccdd6f28435eedae856e6","schema_version":"1.0","event_id":"sha256:6290e716c8f6fd634bffb0adc5cc1c850af9b12a8bcccdd6f28435eedae856e6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NWB7OV24C35KUNU6URVIYLD25V/bundle.json","state_url":"https://pith.science/pith/NWB7OV24C35KUNU6URVIYLD25V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NWB7OV24C35KUNU6URVIYLD25V/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":"2026-08-06T05:48:12Z","links":{"resolver":"https://pith.science/pith/NWB7OV24C35KUNU6URVIYLD25V","bundle":"https://pith.science/pith/NWB7OV24C35KUNU6URVIYLD25V/bundle.json","state":"https://pith.science/pith/NWB7OV24C35KUNU6URVIYLD25V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NWB7OV24C35KUNU6URVIYLD25V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:NWB7OV24C35KUNU6URVIYLD25V","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":"ec0ee129032c8574617c97f507472b78ae653d5a5f473c7b1e724a68907f6268","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-08T15:39:54Z","title_canon_sha256":"e6717314382ed0299b0b593fb3d5d402db8c373cda5cd83fed0aa5ce6d86f2b5"},"schema_version":"1.0","source":{"id":"2208.04215","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.04215","created_at":"2026-07-05T04:46:55Z"},{"alias_kind":"arxiv_version","alias_value":"2208.04215v2","created_at":"2026-07-05T04:46:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.04215","created_at":"2026-07-05T04:46:55Z"},{"alias_kind":"pith_short_12","alias_value":"NWB7OV24C35K","created_at":"2026-07-05T04:46:55Z"},{"alias_kind":"pith_short_16","alias_value":"NWB7OV24C35KUNU6","created_at":"2026-07-05T04:46:55Z"},{"alias_kind":"pith_short_8","alias_value":"NWB7OV24","created_at":"2026-07-05T04:46:55Z"}],"graph_snapshots":[{"event_id":"sha256:6290e716c8f6fd634bffb0adc5cc1c850af9b12a8bcccdd6f28435eedae856e6","target":"graph","created_at":"2026-07-05T04:46:55Z","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/2208.04215/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video-text retrieval (VTR) is an attractive yet challenging task for multi-modal understanding, which aims to search for relevant video (text) given a query (video). Existing methods typically employ completely heterogeneous visual-textual information to align video and text, whilst lacking the awareness of homogeneous high-level semantic information residing in both modalities. To fill this gap, in this work, we propose a novel visual-linguistic aligning model named HiSE for VTR, which improves the cross-modal representation by incorporating explicit high-level semantics. First, we explore th","authors_text":"Di Xu, Dongliang He, Errui Ding, Fu Li, Haoran Wang, Jungong Han, Zhong Ji","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-08T15:39:54Z","title":"Boosting Video-Text Retrieval with Explicit High-Level Semantics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.04215","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":"sha256:55c38111c0c4fe271f79f7e25752423a8583d3e48306583da4e5c19eb50be417","target":"record","created_at":"2026-07-05T04:46:55Z","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":"ec0ee129032c8574617c97f507472b78ae653d5a5f473c7b1e724a68907f6268","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-08T15:39:54Z","title_canon_sha256":"e6717314382ed0299b0b593fb3d5d402db8c373cda5cd83fed0aa5ce6d86f2b5"},"schema_version":"1.0","source":{"id":"2208.04215","kind":"arxiv","version":2}},"canonical_sha256":"6d83f7575c16faaa369ea46a8c2c7aed62fb98fcb889466564d886003f7d9694","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6d83f7575c16faaa369ea46a8c2c7aed62fb98fcb889466564d886003f7d9694","first_computed_at":"2026-07-05T04:46:55.457326Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:46:55.457326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ScOf55gwTKSpNKWCXancr3A0z0icXIm+Zn+SjYOs3n3+w6DWBtUBrCcgHq47La+8++P1Oj08RSX1xQJQ52gWCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:46:55.457669Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.04215","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:55c38111c0c4fe271f79f7e25752423a8583d3e48306583da4e5c19eb50be417","sha256:6290e716c8f6fd634bffb0adc5cc1c850af9b12a8bcccdd6f28435eedae856e6"],"state_sha256":"c41a6ed9c12d709c26bdf08a039343e665d92fc88143a802827176b40328f405"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F3ur4Fg4CNsdVuw+FWREU+ZYtiyPDpPt3g6dS4GET71OV+yPREyHRZJtJB1MedcZBrONKJkgTkyeS+GHZd+kDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T05:48:12.445037Z","bundle_sha256":"166d042b3cfd80dfe087ef91777507fc354d9e38859d77e7901ccf5ed25b587b"}}