{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:LTQBMDJLWMCGIGX2NJIOTS5BYY","short_pith_number":"pith:LTQBMDJL","canonical_record":{"source":{"id":"2605.19390","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-19T05:35:13Z","cross_cats_sorted":[],"title_canon_sha256":"2b25a1d3797c9c8cc1639dd74f469c2f7d29e518123f77231e8f00600493c041","abstract_canon_sha256":"281dafd022f7fe0226878ec276661cabef37f243d1f390fec83ce3624ba4aaf8"},"schema_version":"1.0"},"canonical_sha256":"5ce0160d2bb304641afa6a50e9cba1c605c01697ab1352a6e9d9e3e72ead3a72","source":{"kind":"arxiv","id":"2605.19390","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.19390","created_at":"2026-05-20T01:05:43Z"},{"alias_kind":"arxiv_version","alias_value":"2605.19390v1","created_at":"2026-05-20T01:05:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19390","created_at":"2026-05-20T01:05:43Z"},{"alias_kind":"pith_short_12","alias_value":"LTQBMDJLWMCG","created_at":"2026-05-20T01:05:43Z"},{"alias_kind":"pith_short_16","alias_value":"LTQBMDJLWMCGIGX2","created_at":"2026-05-20T01:05:43Z"},{"alias_kind":"pith_short_8","alias_value":"LTQBMDJL","created_at":"2026-05-20T01:05:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:LTQBMDJLWMCGIGX2NJIOTS5BYY","target":"record","payload":{"canonical_record":{"source":{"id":"2605.19390","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-19T05:35:13Z","cross_cats_sorted":[],"title_canon_sha256":"2b25a1d3797c9c8cc1639dd74f469c2f7d29e518123f77231e8f00600493c041","abstract_canon_sha256":"281dafd022f7fe0226878ec276661cabef37f243d1f390fec83ce3624ba4aaf8"},"schema_version":"1.0"},"canonical_sha256":"5ce0160d2bb304641afa6a50e9cba1c605c01697ab1352a6e9d9e3e72ead3a72","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:05:43.320356Z","signature_b64":"/d5MTF90NpVS3UuMJx1EGfm/E32mCWDwunTvGEaw37uklNdRmmgSyeZWvxCLATVUFNydVTgUDj0I1HBt3aMOBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ce0160d2bb304641afa6a50e9cba1c605c01697ab1352a6e9d9e3e72ead3a72","last_reissued_at":"2026-05-20T01:05:43.319530Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:05:43.319530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.19390","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":"2026-05-20T01:05:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3iVe3HZdhUIycvgFkm2ltWikCkEfYY6msFiCQ/QfuKRmUW00SjYyxqUVGoBnWwwTA3Ifb7F9wPimPVdkTGzgDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T02:39:07.699291Z"},"content_sha256":"caa76d01dbfb29c85363a31372e3543f264847fd584204a161bdc308ec35be43","schema_version":"1.0","event_id":"sha256:caa76d01dbfb29c85363a31372e3543f264847fd584204a161bdc308ec35be43"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:LTQBMDJLWMCGIGX2NJIOTS5BYY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LMM-Track4D: Eliciting 4D Dynamic Reasoning in LMMs via Trajectory-Grounded Dialogue","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaoyue Li, Jiayu Ding, Jie Feng, Yongxue Xu","submitted_at":"2026-05-19T05:35:13Z","abstract_excerpt":"Recent large multimodal models (LMMs) have become increasingly capable on image and video understanding, yet still struggle to sustain 4D continuous spatiotemporal dynamic reasoning. To study this capability gap, we formulate trajectory-grounded multi-turn spatiotemporal dialogue, a new task in which a model must answer spatiotemporal queries while returning structured 3D target trajectories over an entire short clip or a specified segment of a longer clip, and introduce Track4D-Bench, a benchmark with 526 clip-level dialogue samples spanning 23.5k frames and 7.5k object annotations, for train"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19390","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/2605.19390/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":"2026-05-20T01:05:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w1zV163EuRwamtwE9DttsCo13PU8TIeuWq6GaVJtEc7aB54WVXQw28dS/BNkKY2t+aWrqS13uHKcpodEm7igAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T02:39:07.699687Z"},"content_sha256":"96f8e71c743401e92caae484dda7efb0288ceb2f1e1523fdf93a781b9cbecc16","schema_version":"1.0","event_id":"sha256:96f8e71c743401e92caae484dda7efb0288ceb2f1e1523fdf93a781b9cbecc16"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LTQBMDJLWMCGIGX2NJIOTS5BYY/bundle.json","state_url":"https://pith.science/pith/LTQBMDJLWMCGIGX2NJIOTS5BYY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LTQBMDJLWMCGIGX2NJIOTS5BYY/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":"2026-05-28T02:39:07Z","links":{"resolver":"https://pith.science/pith/LTQBMDJLWMCGIGX2NJIOTS5BYY","bundle":"https://pith.science/pith/LTQBMDJLWMCGIGX2NJIOTS5BYY/bundle.json","state":"https://pith.science/pith/LTQBMDJLWMCGIGX2NJIOTS5BYY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LTQBMDJLWMCGIGX2NJIOTS5BYY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LTQBMDJLWMCGIGX2NJIOTS5BYY","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":"281dafd022f7fe0226878ec276661cabef37f243d1f390fec83ce3624ba4aaf8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-19T05:35:13Z","title_canon_sha256":"2b25a1d3797c9c8cc1639dd74f469c2f7d29e518123f77231e8f00600493c041"},"schema_version":"1.0","source":{"id":"2605.19390","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.19390","created_at":"2026-05-20T01:05:43Z"},{"alias_kind":"arxiv_version","alias_value":"2605.19390v1","created_at":"2026-05-20T01:05:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19390","created_at":"2026-05-20T01:05:43Z"},{"alias_kind":"pith_short_12","alias_value":"LTQBMDJLWMCG","created_at":"2026-05-20T01:05:43Z"},{"alias_kind":"pith_short_16","alias_value":"LTQBMDJLWMCGIGX2","created_at":"2026-05-20T01:05:43Z"},{"alias_kind":"pith_short_8","alias_value":"LTQBMDJL","created_at":"2026-05-20T01:05:43Z"}],"graph_snapshots":[{"event_id":"sha256:96f8e71c743401e92caae484dda7efb0288ceb2f1e1523fdf93a781b9cbecc16","target":"graph","created_at":"2026-05-20T01:05:43Z","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/2605.19390/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent large multimodal models (LMMs) have become increasingly capable on image and video understanding, yet still struggle to sustain 4D continuous spatiotemporal dynamic reasoning. To study this capability gap, we formulate trajectory-grounded multi-turn spatiotemporal dialogue, a new task in which a model must answer spatiotemporal queries while returning structured 3D target trajectories over an entire short clip or a specified segment of a longer clip, and introduce Track4D-Bench, a benchmark with 526 clip-level dialogue samples spanning 23.5k frames and 7.5k object annotations, for train","authors_text":"Chaoyue Li, Jiayu Ding, Jie Feng, Yongxue Xu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-19T05:35:13Z","title":"LMM-Track4D: Eliciting 4D Dynamic Reasoning in LMMs via Trajectory-Grounded Dialogue"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19390","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:caa76d01dbfb29c85363a31372e3543f264847fd584204a161bdc308ec35be43","target":"record","created_at":"2026-05-20T01:05:43Z","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":"281dafd022f7fe0226878ec276661cabef37f243d1f390fec83ce3624ba4aaf8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-19T05:35:13Z","title_canon_sha256":"2b25a1d3797c9c8cc1639dd74f469c2f7d29e518123f77231e8f00600493c041"},"schema_version":"1.0","source":{"id":"2605.19390","kind":"arxiv","version":1}},"canonical_sha256":"5ce0160d2bb304641afa6a50e9cba1c605c01697ab1352a6e9d9e3e72ead3a72","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5ce0160d2bb304641afa6a50e9cba1c605c01697ab1352a6e9d9e3e72ead3a72","first_computed_at":"2026-05-20T01:05:43.319530Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T01:05:43.319530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/d5MTF90NpVS3UuMJx1EGfm/E32mCWDwunTvGEaw37uklNdRmmgSyeZWvxCLATVUFNydVTgUDj0I1HBt3aMOBA==","signature_status":"signed_v1","signed_at":"2026-05-20T01:05:43.320356Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.19390","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:caa76d01dbfb29c85363a31372e3543f264847fd584204a161bdc308ec35be43","sha256:96f8e71c743401e92caae484dda7efb0288ceb2f1e1523fdf93a781b9cbecc16"],"state_sha256":"dbd07f399ef996d0ac7a1721ad8f743c91fe1eceed0b19f50548c35b26603e3d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/2pR2PDNc/2I7w6vwOHSXeqXCEsSnlPQXS4k7lMaL8H5paJbyQj+YSh71Rtqka6/i9S47vcBN/LCR64z+u7JCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T02:39:07.701724Z","bundle_sha256":"e6cb3e1b661b7254eb5a24ab656edcbd2ac0951bd789d495a01d0ce414e6284c"}}