{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JPEG5GFYH7YJJ4SF5OWMTMZXH3","short_pith_number":"pith:JPEG5GFY","canonical_record":{"source":{"id":"2505.12312","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-18T08:55:02Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.RO"],"title_canon_sha256":"2caec775afc9e3095e8f0156ca6a5bcda4739512ad93cc46a2a1da97e9ad839b","abstract_canon_sha256":"7a629ad94e9bb667a78090a47edaf32a7cca0fc71a8ef227c93930dba7dbb468"},"schema_version":"1.0"},"canonical_sha256":"4bc86e98b83ff094f245ebacc9b3373edc4ef463f0236f0d02f46f2859bdbd88","source":{"kind":"arxiv","id":"2505.12312","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12312","created_at":"2026-07-05T12:07:07Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12312v4","created_at":"2026-07-05T12:07:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12312","created_at":"2026-07-05T12:07:07Z"},{"alias_kind":"pith_short_12","alias_value":"JPEG5GFYH7YJ","created_at":"2026-07-05T12:07:07Z"},{"alias_kind":"pith_short_16","alias_value":"JPEG5GFYH7YJJ4SF","created_at":"2026-07-05T12:07:07Z"},{"alias_kind":"pith_short_8","alias_value":"JPEG5GFY","created_at":"2026-07-05T12:07:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JPEG5GFYH7YJJ4SF5OWMTMZXH3","target":"record","payload":{"canonical_record":{"source":{"id":"2505.12312","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-18T08:55:02Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.RO"],"title_canon_sha256":"2caec775afc9e3095e8f0156ca6a5bcda4739512ad93cc46a2a1da97e9ad839b","abstract_canon_sha256":"7a629ad94e9bb667a78090a47edaf32a7cca0fc71a8ef227c93930dba7dbb468"},"schema_version":"1.0"},"canonical_sha256":"4bc86e98b83ff094f245ebacc9b3373edc4ef463f0236f0d02f46f2859bdbd88","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:07:07.281585Z","signature_b64":"M4yHlJBKHWKVcVsZdw7erL8vUgpHtsTYAvM9CcR4AwDUsy59rmnt16lP2j6rg/KeO7T/fi0mBMAEqmfhiLnrAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bc86e98b83ff094f245ebacc9b3373edc4ef463f0236f0d02f46f2859bdbd88","last_reissued_at":"2026-07-05T12:07:07.280987Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:07:07.280987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.12312","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:07:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1cEx/Ll6j4PibHDQ6sGvQwIkyPPAjxsBhkTZj9IGWCe+XHTZp5Q/MWfh/z0/6kQd3LNvoF/VHRA8PIbIk+eJDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:11:55.192637Z"},"content_sha256":"b5e87224fb51ee3e3ac76b0bc5f1706f4a9bdb5943ab54842d1a3cf0e4d955bd","schema_version":"1.0","event_id":"sha256:b5e87224fb51ee3e3ac76b0bc5f1706f4a9bdb5943ab54842d1a3cf0e4d955bd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JPEG5GFYH7YJJ4SF5OWMTMZXH3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Visuospatial Cognitive Assistant","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Qi Feng","submitted_at":"2025-05-18T08:55:02Z","abstract_excerpt":"Video-based spatial cognition is vital for robotics and embodied AI but challenges current Vision-Language Models (VLMs). This paper makes two key contributions. First, we introduce ViCA (Visuospatial Cognitive Assistant)-322K, a diverse dataset of 322,003 QA pairs from real-world indoor videos (ARKitScenes, ScanNet, ScanNet++), offering supervision for 3D metadata-grounded queries and video-based complex reasoning. Second, we develop ViCA-7B, fine-tuned on ViCA-322K, which achieves new state-of-the-art on all eight VSI-Bench tasks, outperforming existing models, including larger ones (e.g., +"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12312","kind":"arxiv","version":4},"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/2505.12312/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":"2026-07-05T12:07:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Uf6AJTl2xIdbKIa9zwqBd2ivtkiy+7U/QZaXmGwztjdHarahSTw2iEX2K693gRBPQm4OnSPLPKZQmokqgPh7Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:11:55.193763Z"},"content_sha256":"f1bdfbff7515382be5124b3b781109f2123c5bb0433da89e929e4a96d69acdb3","schema_version":"1.0","event_id":"sha256:f1bdfbff7515382be5124b3b781109f2123c5bb0433da89e929e4a96d69acdb3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JPEG5GFYH7YJJ4SF5OWMTMZXH3/bundle.json","state_url":"https://pith.science/pith/JPEG5GFYH7YJJ4SF5OWMTMZXH3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JPEG5GFYH7YJJ4SF5OWMTMZXH3/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":"2026-08-06T17:11:55Z","links":{"resolver":"https://pith.science/pith/JPEG5GFYH7YJJ4SF5OWMTMZXH3","bundle":"https://pith.science/pith/JPEG5GFYH7YJJ4SF5OWMTMZXH3/bundle.json","state":"https://pith.science/pith/JPEG5GFYH7YJJ4SF5OWMTMZXH3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JPEG5GFYH7YJJ4SF5OWMTMZXH3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JPEG5GFYH7YJJ4SF5OWMTMZXH3","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7a629ad94e9bb667a78090a47edaf32a7cca0fc71a8ef227c93930dba7dbb468","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-18T08:55:02Z","title_canon_sha256":"2caec775afc9e3095e8f0156ca6a5bcda4739512ad93cc46a2a1da97e9ad839b"},"schema_version":"1.0","source":{"id":"2505.12312","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12312","created_at":"2026-07-05T12:07:07Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12312v4","created_at":"2026-07-05T12:07:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12312","created_at":"2026-07-05T12:07:07Z"},{"alias_kind":"pith_short_12","alias_value":"JPEG5GFYH7YJ","created_at":"2026-07-05T12:07:07Z"},{"alias_kind":"pith_short_16","alias_value":"JPEG5GFYH7YJJ4SF","created_at":"2026-07-05T12:07:07Z"},{"alias_kind":"pith_short_8","alias_value":"JPEG5GFY","created_at":"2026-07-05T12:07:07Z"}],"graph_snapshots":[{"event_id":"sha256:f1bdfbff7515382be5124b3b781109f2123c5bb0433da89e929e4a96d69acdb3","target":"graph","created_at":"2026-07-05T12:07:07Z","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/2505.12312/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video-based spatial cognition is vital for robotics and embodied AI but challenges current Vision-Language Models (VLMs). This paper makes two key contributions. First, we introduce ViCA (Visuospatial Cognitive Assistant)-322K, a diverse dataset of 322,003 QA pairs from real-world indoor videos (ARKitScenes, ScanNet, ScanNet++), offering supervision for 3D metadata-grounded queries and video-based complex reasoning. Second, we develop ViCA-7B, fine-tuned on ViCA-322K, which achieves new state-of-the-art on all eight VSI-Bench tasks, outperforming existing models, including larger ones (e.g., +","authors_text":"Qi Feng","cross_cats":["cs.AI","cs.CL","cs.LG","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-18T08:55:02Z","title":"Visuospatial Cognitive Assistant"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12312","kind":"arxiv","version":4},"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:b5e87224fb51ee3e3ac76b0bc5f1706f4a9bdb5943ab54842d1a3cf0e4d955bd","target":"record","created_at":"2026-07-05T12:07:07Z","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":"7a629ad94e9bb667a78090a47edaf32a7cca0fc71a8ef227c93930dba7dbb468","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-18T08:55:02Z","title_canon_sha256":"2caec775afc9e3095e8f0156ca6a5bcda4739512ad93cc46a2a1da97e9ad839b"},"schema_version":"1.0","source":{"id":"2505.12312","kind":"arxiv","version":4}},"canonical_sha256":"4bc86e98b83ff094f245ebacc9b3373edc4ef463f0236f0d02f46f2859bdbd88","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4bc86e98b83ff094f245ebacc9b3373edc4ef463f0236f0d02f46f2859bdbd88","first_computed_at":"2026-07-05T12:07:07.280987Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:07:07.280987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M4yHlJBKHWKVcVsZdw7erL8vUgpHtsTYAvM9CcR4AwDUsy59rmnt16lP2j6rg/KeO7T/fi0mBMAEqmfhiLnrAg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:07:07.281585Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.12312","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5e87224fb51ee3e3ac76b0bc5f1706f4a9bdb5943ab54842d1a3cf0e4d955bd","sha256:f1bdfbff7515382be5124b3b781109f2123c5bb0433da89e929e4a96d69acdb3"],"state_sha256":"9e88702da5cf20aa974a1b4b25524c5800b22824b6b6607de825b19f682b5446"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SqF4WUghIIID/y+zWLj8T9h24W9C+9BQWuMra19rtoOyP9QM0YDnx6Q66mMfKDYELP0NZF8Rv3rwZF7RIGaFDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T17:11:55.199460Z","bundle_sha256":"08de2dd796312bf75039bf646835a15b23006093bc0fd1925b5137796e7b0b07"}}