{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:P3KE55YSZUPNVHHDTXIJD5FUOQ","short_pith_number":"pith:P3KE55YS","canonical_record":{"source":{"id":"2608.13226","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-13T13:29:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9221797af180ffee70b730b7ffd3c0a4be9dd1085c5b72daa468b4ba1be18ea1","abstract_canon_sha256":"c3ecca2155938078da268764508bc5999ea8504999c2ae466f8fcda8ca7b9b47"},"schema_version":"1.0"},"canonical_sha256":"7ed44ef712cd1eda9ce39dd091f4b474399b9404ba20d25a12ca994c1ede1755","source":{"kind":"arxiv","id":"2608.13226","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.13226","created_at":"2026-08-14T01:00:43Z"},{"alias_kind":"arxiv_version","alias_value":"2608.13226v1","created_at":"2026-08-14T01:00:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.13226","created_at":"2026-08-14T01:00:43Z"},{"alias_kind":"pith_short_12","alias_value":"P3KE55YSZUPN","created_at":"2026-08-14T01:00:43Z"},{"alias_kind":"pith_short_16","alias_value":"P3KE55YSZUPNVHHD","created_at":"2026-08-14T01:00:43Z"},{"alias_kind":"pith_short_8","alias_value":"P3KE55YS","created_at":"2026-08-14T01:00:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:P3KE55YSZUPNVHHDTXIJD5FUOQ","target":"record","payload":{"canonical_record":{"source":{"id":"2608.13226","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-13T13:29:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9221797af180ffee70b730b7ffd3c0a4be9dd1085c5b72daa468b4ba1be18ea1","abstract_canon_sha256":"c3ecca2155938078da268764508bc5999ea8504999c2ae466f8fcda8ca7b9b47"},"schema_version":"1.0"},"canonical_sha256":"7ed44ef712cd1eda9ce39dd091f4b474399b9404ba20d25a12ca994c1ede1755","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-14T01:00:43.448384Z","signature_b64":"P46lmJWQltie1ceSGVNgOWJU3m/bieEZSwRS0l7V6z7BO2IqLP9PEq4aHvo9+3950y/xDHLT7TJT4c30294kDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ed44ef712cd1eda9ce39dd091f4b474399b9404ba20d25a12ca994c1ede1755","last_reissued_at":"2026-08-14T01:00:43.446332Z","signature_status":"signed_v1","first_computed_at":"2026-08-14T01:00:43.446332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.13226","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-14T01:00:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RuE//psOSguC0uVM3dD5Nje6xRtLAQYATmZaVlUzHolC2W85H9zvPApVf9du7Me/DLXGv+ERuS4cEH73ALzRAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T02:48:29.945616Z"},"content_sha256":"5b10798550031d4d99600a100304c38b86477be112fedff4b089a9391ee502e8","schema_version":"1.0","event_id":"sha256:5b10798550031d4d99600a100304c38b86477be112fedff4b089a9391ee502e8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:P3KE55YSZUPNVHHDTXIJD5FUOQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CoverPrune: Coverage-Driven Token Pruning for 3D VLMs via Optimal Transport","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Lingting Zhu, Peng Ling, Shengju Qian, Weikai Chen, Wenming Yang, Xin Wang, Yingda Yin, Zeyu Hu","submitted_at":"2026-08-13T13:29:15Z","abstract_excerpt":"While 3D Vision-Language Models (3D VLMs) have demonstrated remarkable spatial reasoning capabilities, they suffer from massive visual token counts that create severe computational bottlenecks during inference. Existing token pruning methods primarily rely on diversity-based selection, discarding similar tokens to maximize dispersion. However, in 3D environments, this approach frequently drops representative prototype tokens in favor of outliers, breaking the multi-view consistencies and geometric structures essential for spatial reasoning. In this paper, we propose a paradigm shift for 3D VLM"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.13226","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/2608.13226/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":"2026-08-14T01:00:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EMgcyRev7ZupO5nRHcPQW3XtGiGJdWrGUJQC3LWsT/u+OjC0eJ3Xcd+okCp/LqKC16YJstnD8mvqpe2JjqEwDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T02:48:29.946384Z"},"content_sha256":"6bade0b18e90143f1c9a5c29629dc753eff1403c58037df92edb1e058d2e19e3","schema_version":"1.0","event_id":"sha256:6bade0b18e90143f1c9a5c29629dc753eff1403c58037df92edb1e058d2e19e3"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:P3KE55YSZUPNVHHDTXIJD5FUOQ","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1007/978-3-030-86514-6_33) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Gurumoorthy, K.S., Jawanpuria, P., Mishra, B.: SPOT: a framework for selection of prototypes using optimal transport. In: Dong, Y., Kourtellis, N., Hammer, B., Lozano, J.A. (eds.) Machine Learning and Knowledge Discovery in Databases. Appli","arxiv_id":"2608.13226","detector":"doi_compliance","evidence":{"ref_index":17,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.1007/978-","reconstructed_doi":"10.1007/978-3-030-86514-6_33"},"severity":"advisory","ref_index":17,"audited_at":"2026-08-14T16:08:08.674901Z","event_type":"pith.integrity.v1","detected_doi":"10.1007/978-3-030-86514-6_33","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"bf33627e47a889171e0314e2fe1d4bd77be6b29a90ab958b6c654963ef682968","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":19746,"payload_sha256":"191e4a6ebef241141818d7f5fa177d4455c4c8c7fbfa230c6eec1282f7dd3ffb","signature_b64":"E16yLap2dO0a4X5c4kHkFBmN4HBrp/dESEasn3m6BeKafO3QzCuI4B6mOBvClxOzVVQ6F5jR40kBQH5zOzCHAA==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-14T16:08:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4AeJqLvTeEdi6rJb0Ibrp4FzMjqXWI//FxVtF5A857Sxkhl8qcoYp8RBWYFIfkmsBOPRiY7grhHAIngBFhB2Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T02:48:29.949407Z"},"content_sha256":"ee7ecd7a8213a1584aa2609bac1ac2c40c1480d50b42e9d950c1790bc753369e","schema_version":"1.0","event_id":"sha256:ee7ecd7a8213a1584aa2609bac1ac2c40c1480d50b42e9d950c1790bc753369e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P3KE55YSZUPNVHHDTXIJD5FUOQ/bundle.json","state_url":"https://pith.science/pith/P3KE55YSZUPNVHHDTXIJD5FUOQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P3KE55YSZUPNVHHDTXIJD5FUOQ/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":"2026-08-20T02:48:29Z","links":{"resolver":"https://pith.science/pith/P3KE55YSZUPNVHHDTXIJD5FUOQ","bundle":"https://pith.science/pith/P3KE55YSZUPNVHHDTXIJD5FUOQ/bundle.json","state":"https://pith.science/pith/P3KE55YSZUPNVHHDTXIJD5FUOQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P3KE55YSZUPNVHHDTXIJD5FUOQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:P3KE55YSZUPNVHHDTXIJD5FUOQ","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c3ecca2155938078da268764508bc5999ea8504999c2ae466f8fcda8ca7b9b47","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-13T13:29:15Z","title_canon_sha256":"9221797af180ffee70b730b7ffd3c0a4be9dd1085c5b72daa468b4ba1be18ea1"},"schema_version":"1.0","source":{"id":"2608.13226","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.13226","created_at":"2026-08-14T01:00:43Z"},{"alias_kind":"arxiv_version","alias_value":"2608.13226v1","created_at":"2026-08-14T01:00:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.13226","created_at":"2026-08-14T01:00:43Z"},{"alias_kind":"pith_short_12","alias_value":"P3KE55YSZUPN","created_at":"2026-08-14T01:00:43Z"},{"alias_kind":"pith_short_16","alias_value":"P3KE55YSZUPNVHHD","created_at":"2026-08-14T01:00:43Z"},{"alias_kind":"pith_short_8","alias_value":"P3KE55YS","created_at":"2026-08-14T01:00:43Z"}],"graph_snapshots":[{"event_id":"sha256:6bade0b18e90143f1c9a5c29629dc753eff1403c58037df92edb1e058d2e19e3","target":"graph","created_at":"2026-08-14T01:00:43Z","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/2608.13226/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While 3D Vision-Language Models (3D VLMs) have demonstrated remarkable spatial reasoning capabilities, they suffer from massive visual token counts that create severe computational bottlenecks during inference. Existing token pruning methods primarily rely on diversity-based selection, discarding similar tokens to maximize dispersion. However, in 3D environments, this approach frequently drops representative prototype tokens in favor of outliers, breaking the multi-view consistencies and geometric structures essential for spatial reasoning. In this paper, we propose a paradigm shift for 3D VLM","authors_text":"Lingting Zhu, Peng Ling, Shengju Qian, Weikai Chen, Wenming Yang, Xin Wang, Yingda Yin, Zeyu Hu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-13T13:29:15Z","title":"CoverPrune: Coverage-Driven Token Pruning for 3D VLMs via Optimal Transport"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.13226","kind":"arxiv","version":1},"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":"sha256:5b10798550031d4d99600a100304c38b86477be112fedff4b089a9391ee502e8","target":"record","created_at":"2026-08-14T01:00:43Z","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":"c3ecca2155938078da268764508bc5999ea8504999c2ae466f8fcda8ca7b9b47","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-13T13:29:15Z","title_canon_sha256":"9221797af180ffee70b730b7ffd3c0a4be9dd1085c5b72daa468b4ba1be18ea1"},"schema_version":"1.0","source":{"id":"2608.13226","kind":"arxiv","version":1}},"canonical_sha256":"7ed44ef712cd1eda9ce39dd091f4b474399b9404ba20d25a12ca994c1ede1755","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ed44ef712cd1eda9ce39dd091f4b474399b9404ba20d25a12ca994c1ede1755","first_computed_at":"2026-08-14T01:00:43.446332Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-14T01:00:43.446332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P46lmJWQltie1ceSGVNgOWJU3m/bieEZSwRS0l7V6z7BO2IqLP9PEq4aHvo9+3950y/xDHLT7TJT4c30294kDg==","signature_status":"signed_v1","signed_at":"2026-08-14T01:00:43.448384Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.13226","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b10798550031d4d99600a100304c38b86477be112fedff4b089a9391ee502e8","sha256:6bade0b18e90143f1c9a5c29629dc753eff1403c58037df92edb1e058d2e19e3","sha256:ee7ecd7a8213a1584aa2609bac1ac2c40c1480d50b42e9d950c1790bc753369e"],"state_sha256":"fe3d405796868650b6092f0fa1fcace812df77e77a1fec68d5032990568260e8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7GjG50ZdBebriXdHO8dBBV59c9SzdvaWGXkEoNYn0qnexQZNqsbR6RPtP/WIe75DF+ShFUCV/lRkmgoJ3NU8CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T02:48:29.951872Z","bundle_sha256":"bb77311f2b8affecd8b76b6d6146483f3a7ade564778db20a46cedeb25bae818"}}