{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ALHHKS3LZFSVXGAUAMBK6PVOMI","short_pith_number":"pith:ALHHKS3L","schema_version":"1.0","canonical_sha256":"02ce754b6bc9655b98140302af3eae620c9655561568dd813104263311d19553","source":{"kind":"arxiv","id":"2508.15439","version":2},"attestation_state":"computed","paper":{"title":"Aligning Moments in Time using Video Queries","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anand Mishra, Manish Gupta, Uday Agarwal, Yogesh Kumar","submitted_at":"2025-08-21T11:01:13Z","abstract_excerpt":"Video-to-video moment retrieval (Vid2VidMR) is the task of localizing unseen events or moments in a target video using a query video. This task poses several challenges, such as the need for semantic frame-level alignment and modeling complex dependencies between query and target videos. To tackle this challenging problem, we introduce MATR (Moment Alignment TRansformer), a transformer-based model designed to capture semantic context as well as the temporal details necessary for precise moment localization. MATR conditions target video representations on query video features using dual-stage s"},"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":"2508.15439","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-21T11:01:13Z","cross_cats_sorted":[],"title_canon_sha256":"ebea3a24db463cb79ad898ba0ae471275fe193607e47541621eb1c27f58270e6","abstract_canon_sha256":"d2426803a8ec42953e99add5b7cdba96527baae35c645bbb50c6868b7d4ef5a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:50.696925Z","signature_b64":"Msb/G6+gFcLy7kljiCDcVqZGP8W6y4XdTD2GEoD90Yu7VpdKVqGke9iRiCsaA9J5kYZRl7k1MpeXEMsD+mQnBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02ce754b6bc9655b98140302af3eae620c9655561568dd813104263311d19553","last_reissued_at":"2026-07-05T12:02:50.696415Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:50.696415Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Aligning Moments in Time using Video Queries","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anand Mishra, Manish Gupta, Uday Agarwal, Yogesh Kumar","submitted_at":"2025-08-21T11:01:13Z","abstract_excerpt":"Video-to-video moment retrieval (Vid2VidMR) is the task of localizing unseen events or moments in a target video using a query video. This task poses several challenges, such as the need for semantic frame-level alignment and modeling complex dependencies between query and target videos. To tackle this challenging problem, we introduce MATR (Moment Alignment TRansformer), a transformer-based model designed to capture semantic context as well as the temporal details necessary for precise moment localization. MATR conditions target video representations on query video features using dual-stage s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.15439","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/2508.15439/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":"2508.15439","created_at":"2026-07-05T12:02:50.696474+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.15439v2","created_at":"2026-07-05T12:02:50.696474+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.15439","created_at":"2026-07-05T12:02:50.696474+00:00"},{"alias_kind":"pith_short_12","alias_value":"ALHHKS3LZFSV","created_at":"2026-07-05T12:02:50.696474+00:00"},{"alias_kind":"pith_short_16","alias_value":"ALHHKS3LZFSVXGAU","created_at":"2026-07-05T12:02:50.696474+00:00"},{"alias_kind":"pith_short_8","alias_value":"ALHHKS3L","created_at":"2026-07-05T12:02:50.696474+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ALHHKS3LZFSVXGAUAMBK6PVOMI","json":"https://pith.science/pith/ALHHKS3LZFSVXGAUAMBK6PVOMI.json","graph_json":"https://pith.science/api/pith-number/ALHHKS3LZFSVXGAUAMBK6PVOMI/graph.json","events_json":"https://pith.science/api/pith-number/ALHHKS3LZFSVXGAUAMBK6PVOMI/events.json","paper":"https://pith.science/paper/ALHHKS3L"},"agent_actions":{"view_html":"https://pith.science/pith/ALHHKS3LZFSVXGAUAMBK6PVOMI","download_json":"https://pith.science/pith/ALHHKS3LZFSVXGAUAMBK6PVOMI.json","view_paper":"https://pith.science/paper/ALHHKS3L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.15439&json=true","fetch_graph":"https://pith.science/api/pith-number/ALHHKS3LZFSVXGAUAMBK6PVOMI/graph.json","fetch_events":"https://pith.science/api/pith-number/ALHHKS3LZFSVXGAUAMBK6PVOMI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ALHHKS3LZFSVXGAUAMBK6PVOMI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ALHHKS3LZFSVXGAUAMBK6PVOMI/action/storage_attestation","attest_author":"https://pith.science/pith/ALHHKS3LZFSVXGAUAMBK6PVOMI/action/author_attestation","sign_citation":"https://pith.science/pith/ALHHKS3LZFSVXGAUAMBK6PVOMI/action/citation_signature","submit_replication":"https://pith.science/pith/ALHHKS3LZFSVXGAUAMBK6PVOMI/action/replication_record"}},"created_at":"2026-07-05T12:02:50.696474+00:00","updated_at":"2026-07-05T12:02:50.696474+00:00"}