{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:X3VXN4MXJJ4MM7UVFSJ67QXVTL","short_pith_number":"pith:X3VXN4MX","schema_version":"1.0","canonical_sha256":"beeb76f1974a78c67e952c93efc2f59aef1014b6275082e32035d410fc5b8a92","source":{"kind":"arxiv","id":"2606.06294","version":1},"attestation_state":"computed","paper":{"title":"Towards One-to-Many Temporal Grounding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Anna Wang, Hao Fei, Jason Li, Jiahao Meng, Qi Xu, Shihao Chen, Shunping Ji, Yue Tan","submitted_at":"2026-06-04T15:31:22Z","abstract_excerpt":"Temporal Grounding (TG) aims to localize video segments corresponding to a textual query. Prior research predominantly focuses on single-segment retrieval. Real-world scenarios, however, often require localizing multiple disjoint segments for a single query -- a setting we term One-to-Many Temporal Grounding (OMTG). Previous state-of-the-art MLLMs, optimized for one-to-one settings, struggle in this context, often yielding near-zero scores due to a lack of event cardinality perception. To bridge this gap, we present a systematic solution with three key contributions. First, we establish the fi"},"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":"2606.06294","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-04T15:31:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ed80ca87922cc12fac50ee397e39adf203bc620a65ef7babbbe9ee2b8a97ccd2","abstract_canon_sha256":"2eaa65c4fb7f6656bc9d933f39862cf3d6e2416dfdf9d5468b9dbf4a2017198a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:40.818185Z","signature_b64":"aXv0031zbBc+jIecZH/UtMMW9wga9T9EqOUblOxg103l5w0KHPgKVwVjpK9iodZ/hmL9mD5MSxjdnyJAoNLOBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"beeb76f1974a78c67e952c93efc2f59aef1014b6275082e32035d410fc5b8a92","last_reissued_at":"2026-06-05T01:15:40.817792Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:40.817792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards One-to-Many Temporal Grounding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Anna Wang, Hao Fei, Jason Li, Jiahao Meng, Qi Xu, Shihao Chen, Shunping Ji, Yue Tan","submitted_at":"2026-06-04T15:31:22Z","abstract_excerpt":"Temporal Grounding (TG) aims to localize video segments corresponding to a textual query. Prior research predominantly focuses on single-segment retrieval. Real-world scenarios, however, often require localizing multiple disjoint segments for a single query -- a setting we term One-to-Many Temporal Grounding (OMTG). Previous state-of-the-art MLLMs, optimized for one-to-one settings, struggle in this context, often yielding near-zero scores due to a lack of event cardinality perception. To bridge this gap, we present a systematic solution with three key contributions. First, we establish the fi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06294","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/2606.06294/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":"2606.06294","created_at":"2026-06-05T01:15:40.817852+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.06294v1","created_at":"2026-06-05T01:15:40.817852+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06294","created_at":"2026-06-05T01:15:40.817852+00:00"},{"alias_kind":"pith_short_12","alias_value":"X3VXN4MXJJ4M","created_at":"2026-06-05T01:15:40.817852+00:00"},{"alias_kind":"pith_short_16","alias_value":"X3VXN4MXJJ4MM7UV","created_at":"2026-06-05T01:15:40.817852+00:00"},{"alias_kind":"pith_short_8","alias_value":"X3VXN4MX","created_at":"2026-06-05T01:15:40.817852+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/X3VXN4MXJJ4MM7UVFSJ67QXVTL","json":"https://pith.science/pith/X3VXN4MXJJ4MM7UVFSJ67QXVTL.json","graph_json":"https://pith.science/api/pith-number/X3VXN4MXJJ4MM7UVFSJ67QXVTL/graph.json","events_json":"https://pith.science/api/pith-number/X3VXN4MXJJ4MM7UVFSJ67QXVTL/events.json","paper":"https://pith.science/paper/X3VXN4MX"},"agent_actions":{"view_html":"https://pith.science/pith/X3VXN4MXJJ4MM7UVFSJ67QXVTL","download_json":"https://pith.science/pith/X3VXN4MXJJ4MM7UVFSJ67QXVTL.json","view_paper":"https://pith.science/paper/X3VXN4MX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.06294&json=true","fetch_graph":"https://pith.science/api/pith-number/X3VXN4MXJJ4MM7UVFSJ67QXVTL/graph.json","fetch_events":"https://pith.science/api/pith-number/X3VXN4MXJJ4MM7UVFSJ67QXVTL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X3VXN4MXJJ4MM7UVFSJ67QXVTL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X3VXN4MXJJ4MM7UVFSJ67QXVTL/action/storage_attestation","attest_author":"https://pith.science/pith/X3VXN4MXJJ4MM7UVFSJ67QXVTL/action/author_attestation","sign_citation":"https://pith.science/pith/X3VXN4MXJJ4MM7UVFSJ67QXVTL/action/citation_signature","submit_replication":"https://pith.science/pith/X3VXN4MXJJ4MM7UVFSJ67QXVTL/action/replication_record"}},"created_at":"2026-06-05T01:15:40.817852+00:00","updated_at":"2026-06-05T01:15:40.817852+00:00"}