{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SF6542GAXZ25NLDD5UKYREK77E","short_pith_number":"pith:SF6542GA","schema_version":"1.0","canonical_sha256":"917dde68c0be75d6ac63ed1588915ff90f11918f6810ea7ba2292cfea2fc2d46","source":{"kind":"arxiv","id":"2303.16406","version":1},"attestation_state":"computed","paper":{"title":"Hierarchical Video-Moment Retrieval and Step-Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Abhay Zala, Barlas O\\u{g}uz, Jaemin Cho, Mohit Bansal, Satwik Kottur, Xilun Chen, Yasher Mehdad","submitted_at":"2023-03-29T02:33:54Z","abstract_excerpt":"There is growing interest in searching for information from large video corpora. Prior works have studied relevant tasks, such as text-based video retrieval, moment retrieval, video summarization, and video captioning in isolation, without an end-to-end setup that can jointly search from video corpora and generate summaries. Such an end-to-end setup would allow for many interesting applications, e.g., a text-based search that finds a relevant video from a video corpus, extracts the most relevant moment from that video, and segments the moment into important steps with captions. To address this"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2303.16406","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-29T02:33:54Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"d6b4b8582b6a8389a13d2e17b9f216900330e6165230c58892e74ef53172e699","abstract_canon_sha256":"e1c1a9f21dae1acd5d5d59e2382583b38e96044ca3eb739a1abd79bf19b85e4c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:56:06.466628Z","signature_b64":"UZ4hN2vZF/+YPhgCDgpc45TF6WB4ZSyEsHqivznlFIHekr/xdLSqbFqLn2++BE8h8stMw1r5ruFclU14xUuSAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"917dde68c0be75d6ac63ed1588915ff90f11918f6810ea7ba2292cfea2fc2d46","last_reissued_at":"2026-07-05T05:56:06.466091Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:56:06.466091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Video-Moment Retrieval and Step-Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Abhay Zala, Barlas O\\u{g}uz, Jaemin Cho, Mohit Bansal, Satwik Kottur, Xilun Chen, Yasher Mehdad","submitted_at":"2023-03-29T02:33:54Z","abstract_excerpt":"There is growing interest in searching for information from large video corpora. Prior works have studied relevant tasks, such as text-based video retrieval, moment retrieval, video summarization, and video captioning in isolation, without an end-to-end setup that can jointly search from video corpora and generate summaries. Such an end-to-end setup would allow for many interesting applications, e.g., a text-based search that finds a relevant video from a video corpus, extracts the most relevant moment from that video, and segments the moment into important steps with captions. To address this"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.16406","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/2303.16406/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2303.16406","created_at":"2026-07-05T05:56:06.466167+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.16406v1","created_at":"2026-07-05T05:56:06.466167+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.16406","created_at":"2026-07-05T05:56:06.466167+00:00"},{"alias_kind":"pith_short_12","alias_value":"SF6542GAXZ25","created_at":"2026-07-05T05:56:06.466167+00:00"},{"alias_kind":"pith_short_16","alias_value":"SF6542GAXZ25NLDD","created_at":"2026-07-05T05:56:06.466167+00:00"},{"alias_kind":"pith_short_8","alias_value":"SF6542GA","created_at":"2026-07-05T05:56:06.466167+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08615","citing_title":"Harnessing Streaming Video in the Wild","ref_index":67,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SF6542GAXZ25NLDD5UKYREK77E","json":"https://pith.science/pith/SF6542GAXZ25NLDD5UKYREK77E.json","graph_json":"https://pith.science/api/pith-number/SF6542GAXZ25NLDD5UKYREK77E/graph.json","events_json":"https://pith.science/api/pith-number/SF6542GAXZ25NLDD5UKYREK77E/events.json","paper":"https://pith.science/paper/SF6542GA"},"agent_actions":{"view_html":"https://pith.science/pith/SF6542GAXZ25NLDD5UKYREK77E","download_json":"https://pith.science/pith/SF6542GAXZ25NLDD5UKYREK77E.json","view_paper":"https://pith.science/paper/SF6542GA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.16406&json=true","fetch_graph":"https://pith.science/api/pith-number/SF6542GAXZ25NLDD5UKYREK77E/graph.json","fetch_events":"https://pith.science/api/pith-number/SF6542GAXZ25NLDD5UKYREK77E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SF6542GAXZ25NLDD5UKYREK77E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SF6542GAXZ25NLDD5UKYREK77E/action/storage_attestation","attest_author":"https://pith.science/pith/SF6542GAXZ25NLDD5UKYREK77E/action/author_attestation","sign_citation":"https://pith.science/pith/SF6542GAXZ25NLDD5UKYREK77E/action/citation_signature","submit_replication":"https://pith.science/pith/SF6542GAXZ25NLDD5UKYREK77E/action/replication_record"}},"created_at":"2026-07-05T05:56:06.466167+00:00","updated_at":"2026-07-05T05:56:06.466167+00:00"}