{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZSVM722EY6NBPTFIJKE5R2F4BE","short_pith_number":"pith:ZSVM722E","canonical_record":{"source":{"id":"2505.12253","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-18T06:18:57Z","cross_cats_sorted":[],"title_canon_sha256":"bc284e7346296a4b752c9e8104c62bf024f20dc453bb232a41489613f36bc9d6","abstract_canon_sha256":"2bcc95d6859152bd2b2dc0bfd3532f11c6623af457acadfcb2ffb452e99a9cbb"},"schema_version":"1.0"},"canonical_sha256":"ccaacfeb44c79a17cca84a89d8e8bc0922efb6727067e080230d4da199550843","source":{"kind":"arxiv","id":"2505.12253","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12253","created_at":"2026-07-05T11:05:00Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12253v1","created_at":"2026-07-05T11:05:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12253","created_at":"2026-07-05T11:05:00Z"},{"alias_kind":"pith_short_12","alias_value":"ZSVM722EY6NB","created_at":"2026-07-05T11:05:00Z"},{"alias_kind":"pith_short_16","alias_value":"ZSVM722EY6NBPTFI","created_at":"2026-07-05T11:05:00Z"},{"alias_kind":"pith_short_8","alias_value":"ZSVM722E","created_at":"2026-07-05T11:05:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZSVM722EY6NBPTFIJKE5R2F4BE","target":"record","payload":{"canonical_record":{"source":{"id":"2505.12253","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-18T06:18:57Z","cross_cats_sorted":[],"title_canon_sha256":"bc284e7346296a4b752c9e8104c62bf024f20dc453bb232a41489613f36bc9d6","abstract_canon_sha256":"2bcc95d6859152bd2b2dc0bfd3532f11c6623af457acadfcb2ffb452e99a9cbb"},"schema_version":"1.0"},"canonical_sha256":"ccaacfeb44c79a17cca84a89d8e8bc0922efb6727067e080230d4da199550843","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:00.976625Z","signature_b64":"K3ld71HBindZADbtiYRq6TEtF7Qag87DxPghQI0239qwBe9LXyWLVDoa4TAYZmBKAKO/Rfhy9ufO67yTQjMMBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ccaacfeb44c79a17cca84a89d8e8bc0922efb6727067e080230d4da199550843","last_reissued_at":"2026-07-05T11:05:00.976187Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:00.976187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.12253","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":"2026-07-05T11:05:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X+ShmeW6Nr51F7Kau2fCN+3lyyZ3lS2bDM9T/GRa9Fkzb5tHJNkcWVZBpWUu4p4dz0KeCWSDUZ7xXJROL7Q5Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T23:56:40.139536Z"},"content_sha256":"97852ff92c5492d5a049237b1b92a953d6123f8019b87aa1ca39b162319853b1","schema_version":"1.0","event_id":"sha256:97852ff92c5492d5a049237b1b92a953d6123f8019b87aa1ca39b162319853b1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZSVM722EY6NBPTFIJKE5R2F4BE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLaVA-4D: Embedding SpatioTemporal Prompt into LMMs for 4D Scene Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gim Hee Lee, Hanyu Zhou","submitted_at":"2025-05-18T06:18:57Z","abstract_excerpt":"Despite achieving significant progress in 2D image understanding, large multimodal models (LMMs) struggle in the physical world due to the lack of spatial representation. Typically, existing 3D LMMs mainly embed 3D positions as fixed spatial prompts within visual features to represent the scene. However, these methods are limited to understanding the static background and fail to capture temporally varying dynamic objects. In this paper, we propose LLaVA-4D, a general LMM framework with a novel spatiotemporal prompt for visual representation in 4D scene understanding. The spatiotemporal prompt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12253","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/2505.12253/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":"2026-07-05T11:05:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1od1gTzkQiDxYhQKJCpLb2ZcASKY8cRLZUQyUMvgb3n1VQeDCNYlVqrVRU7ewwy28vdvRQQ2EsRjK+Bta6DKDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T23:56:40.140646Z"},"content_sha256":"7da08fe3707f5a469e928acb89eb280de03737c16f6985947bd6ed1377ca2db4","schema_version":"1.0","event_id":"sha256:7da08fe3707f5a469e928acb89eb280de03737c16f6985947bd6ed1377ca2db4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZSVM722EY6NBPTFIJKE5R2F4BE/bundle.json","state_url":"https://pith.science/pith/ZSVM722EY6NBPTFIJKE5R2F4BE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZSVM722EY6NBPTFIJKE5R2F4BE/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":"2026-08-08T23:56:40Z","links":{"resolver":"https://pith.science/pith/ZSVM722EY6NBPTFIJKE5R2F4BE","bundle":"https://pith.science/pith/ZSVM722EY6NBPTFIJKE5R2F4BE/bundle.json","state":"https://pith.science/pith/ZSVM722EY6NBPTFIJKE5R2F4BE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZSVM722EY6NBPTFIJKE5R2F4BE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZSVM722EY6NBPTFIJKE5R2F4BE","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":"2bcc95d6859152bd2b2dc0bfd3532f11c6623af457acadfcb2ffb452e99a9cbb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-18T06:18:57Z","title_canon_sha256":"bc284e7346296a4b752c9e8104c62bf024f20dc453bb232a41489613f36bc9d6"},"schema_version":"1.0","source":{"id":"2505.12253","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12253","created_at":"2026-07-05T11:05:00Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12253v1","created_at":"2026-07-05T11:05:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12253","created_at":"2026-07-05T11:05:00Z"},{"alias_kind":"pith_short_12","alias_value":"ZSVM722EY6NB","created_at":"2026-07-05T11:05:00Z"},{"alias_kind":"pith_short_16","alias_value":"ZSVM722EY6NBPTFI","created_at":"2026-07-05T11:05:00Z"},{"alias_kind":"pith_short_8","alias_value":"ZSVM722E","created_at":"2026-07-05T11:05:00Z"}],"graph_snapshots":[{"event_id":"sha256:7da08fe3707f5a469e928acb89eb280de03737c16f6985947bd6ed1377ca2db4","target":"graph","created_at":"2026-07-05T11:05:00Z","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/2505.12253/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite achieving significant progress in 2D image understanding, large multimodal models (LMMs) struggle in the physical world due to the lack of spatial representation. Typically, existing 3D LMMs mainly embed 3D positions as fixed spatial prompts within visual features to represent the scene. However, these methods are limited to understanding the static background and fail to capture temporally varying dynamic objects. In this paper, we propose LLaVA-4D, a general LMM framework with a novel spatiotemporal prompt for visual representation in 4D scene understanding. The spatiotemporal prompt","authors_text":"Gim Hee Lee, Hanyu Zhou","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-18T06:18:57Z","title":"LLaVA-4D: Embedding SpatioTemporal Prompt into LMMs for 4D Scene Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12253","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":"sha256:97852ff92c5492d5a049237b1b92a953d6123f8019b87aa1ca39b162319853b1","target":"record","created_at":"2026-07-05T11:05:00Z","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":"2bcc95d6859152bd2b2dc0bfd3532f11c6623af457acadfcb2ffb452e99a9cbb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-18T06:18:57Z","title_canon_sha256":"bc284e7346296a4b752c9e8104c62bf024f20dc453bb232a41489613f36bc9d6"},"schema_version":"1.0","source":{"id":"2505.12253","kind":"arxiv","version":1}},"canonical_sha256":"ccaacfeb44c79a17cca84a89d8e8bc0922efb6727067e080230d4da199550843","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ccaacfeb44c79a17cca84a89d8e8bc0922efb6727067e080230d4da199550843","first_computed_at":"2026-07-05T11:05:00.976187Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:00.976187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K3ld71HBindZADbtiYRq6TEtF7Qag87DxPghQI0239qwBe9LXyWLVDoa4TAYZmBKAKO/Rfhy9ufO67yTQjMMBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:00.976625Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.12253","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97852ff92c5492d5a049237b1b92a953d6123f8019b87aa1ca39b162319853b1","sha256:7da08fe3707f5a469e928acb89eb280de03737c16f6985947bd6ed1377ca2db4"],"state_sha256":"d80b5a5d29581ef89c444c16ef2bede6d8adac4cedaadcfcb94c580838c582a1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wQJ2JfjgGalpDz7nIVDIGCD4e99UqBgnI7cEXKHTWOMKNF+VqLx9ruR1WJFyQ7MTzJQ0VCy3YDDUsvYQqBkECA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T23:56:40.148381Z","bundle_sha256":"d0d68df2fc22d510d7749663dbd233b55623d5165645dced35aae16aa1bcbe33"}}