{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7JADN4IUMOGCU3P4KFLQUYJJO2","short_pith_number":"pith:7JADN4IU","schema_version":"1.0","canonical_sha256":"fa4036f114638c2a6dfc51570a61297690569e17d7d7a82c16d78c7339b2c6b9","source":{"kind":"arxiv","id":"2607.04079","version":1},"attestation_state":"computed","paper":{"title":"Seeing Once is Enough? Online Geometry-Aware Token Pruning for 3D Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bolivar Solarte, Chin-Hsuan Wu, Min Sun, Ruei-Chi Lai, Yi-Hsuan Tsai","submitted_at":"2026-07-05T02:00:54Z","abstract_excerpt":"Recent Multi-modal Large Language Models (MLLMs) have demonstrated remarkable performance on 2D question answering tasks. However, extending these models to the 3D question answering remains challenging, as they typically require multiple views of the scene, which incurs substantial computational cost at inference. To mitigate this issue, existing solutions rely on strategic frame selection or token-merging algorithms that require preprocessing in advance all frames of the scene, i.e., an offline fashion. In contrast, we propose the first online token-pruning method that can be integrated seam"},"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":"2607.04079","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-05T02:00:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"83c97a35c9acb5af1fd04f9d8833f6dfe872ffdda3707bbe851c5e2b02eab21c","abstract_canon_sha256":"7ecab0f9cc797158e97e7fabfc9b02a1ee125978dac550faf1a8b13086b2b888"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:18:56.333879Z","signature_b64":"UfZCRiXAab/Ib/AhE/4aIK1CQ6QilDKGZKO3ovatzmxoktmU65g9Z1YTCyLEmAGKip5lSeDmdpluz6S4Ded3Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa4036f114638c2a6dfc51570a61297690569e17d7d7a82c16d78c7339b2c6b9","last_reissued_at":"2026-07-07T02:18:56.332796Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:18:56.332796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Seeing Once is Enough? Online Geometry-Aware Token Pruning for 3D Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bolivar Solarte, Chin-Hsuan Wu, Min Sun, Ruei-Chi Lai, Yi-Hsuan Tsai","submitted_at":"2026-07-05T02:00:54Z","abstract_excerpt":"Recent Multi-modal Large Language Models (MLLMs) have demonstrated remarkable performance on 2D question answering tasks. However, extending these models to the 3D question answering remains challenging, as they typically require multiple views of the scene, which incurs substantial computational cost at inference. To mitigate this issue, existing solutions rely on strategic frame selection or token-merging algorithms that require preprocessing in advance all frames of the scene, i.e., an offline fashion. In contrast, we propose the first online token-pruning method that can be integrated seam"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04079","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/2607.04079/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":"2607.04079","created_at":"2026-07-07T02:18:56.332987+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.04079v1","created_at":"2026-07-07T02:18:56.332987+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04079","created_at":"2026-07-07T02:18:56.332987+00:00"},{"alias_kind":"pith_short_12","alias_value":"7JADN4IUMOGC","created_at":"2026-07-07T02:18:56.332987+00:00"},{"alias_kind":"pith_short_16","alias_value":"7JADN4IUMOGCU3P4","created_at":"2026-07-07T02:18:56.332987+00:00"},{"alias_kind":"pith_short_8","alias_value":"7JADN4IU","created_at":"2026-07-07T02:18:56.332987+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/7JADN4IUMOGCU3P4KFLQUYJJO2","json":"https://pith.science/pith/7JADN4IUMOGCU3P4KFLQUYJJO2.json","graph_json":"https://pith.science/api/pith-number/7JADN4IUMOGCU3P4KFLQUYJJO2/graph.json","events_json":"https://pith.science/api/pith-number/7JADN4IUMOGCU3P4KFLQUYJJO2/events.json","paper":"https://pith.science/paper/7JADN4IU"},"agent_actions":{"view_html":"https://pith.science/pith/7JADN4IUMOGCU3P4KFLQUYJJO2","download_json":"https://pith.science/pith/7JADN4IUMOGCU3P4KFLQUYJJO2.json","view_paper":"https://pith.science/paper/7JADN4IU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.04079&json=true","fetch_graph":"https://pith.science/api/pith-number/7JADN4IUMOGCU3P4KFLQUYJJO2/graph.json","fetch_events":"https://pith.science/api/pith-number/7JADN4IUMOGCU3P4KFLQUYJJO2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7JADN4IUMOGCU3P4KFLQUYJJO2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7JADN4IUMOGCU3P4KFLQUYJJO2/action/storage_attestation","attest_author":"https://pith.science/pith/7JADN4IUMOGCU3P4KFLQUYJJO2/action/author_attestation","sign_citation":"https://pith.science/pith/7JADN4IUMOGCU3P4KFLQUYJJO2/action/citation_signature","submit_replication":"https://pith.science/pith/7JADN4IUMOGCU3P4KFLQUYJJO2/action/replication_record"}},"created_at":"2026-07-07T02:18:56.332987+00:00","updated_at":"2026-07-07T02:18:56.332987+00:00"}