{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NQKTODVE2ULDO4HXGHEWW5GQUR","short_pith_number":"pith:NQKTODVE","canonical_record":{"source":{"id":"2512.10607","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-11T13:03:03Z","cross_cats_sorted":[],"title_canon_sha256":"3390b7db1402f8f227c358924864b8e8ef63b7af3211dab077ac5768532c9eb9","abstract_canon_sha256":"4decd5889a41d200bc438b8af4619c2e594a4e10275231907e521ac27cc27c88"},"schema_version":"1.0"},"canonical_sha256":"6c15370ea4d5163770f731c96b74d0a4731e1e46d675249b6a399f8fd8b7e46a","source":{"kind":"arxiv","id":"2512.10607","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.10607","created_at":"2026-07-16T00:21:43Z"},{"alias_kind":"arxiv_version","alias_value":"2512.10607v2","created_at":"2026-07-16T00:21:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.10607","created_at":"2026-07-16T00:21:43Z"},{"alias_kind":"pith_short_12","alias_value":"NQKTODVE2ULD","created_at":"2026-07-16T00:21:43Z"},{"alias_kind":"pith_short_16","alias_value":"NQKTODVE2ULDO4HX","created_at":"2026-07-16T00:21:43Z"},{"alias_kind":"pith_short_8","alias_value":"NQKTODVE","created_at":"2026-07-16T00:21:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NQKTODVE2ULDO4HXGHEWW5GQUR","target":"record","payload":{"canonical_record":{"source":{"id":"2512.10607","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-11T13:03:03Z","cross_cats_sorted":[],"title_canon_sha256":"3390b7db1402f8f227c358924864b8e8ef63b7af3211dab077ac5768532c9eb9","abstract_canon_sha256":"4decd5889a41d200bc438b8af4619c2e594a4e10275231907e521ac27cc27c88"},"schema_version":"1.0"},"canonical_sha256":"6c15370ea4d5163770f731c96b74d0a4731e1e46d675249b6a399f8fd8b7e46a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-16T00:21:43.989197Z","signature_b64":"euTKi1UmyPqqaa/GgE/y5/EYRTtrUjYm4tokjZOQ9NYmoEeDua7jJfmzyxUo+xITJJ1iKsb5D7kuIexTik+7DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c15370ea4d5163770f731c96b74d0a4731e1e46d675249b6a399f8fd8b7e46a","last_reissued_at":"2026-07-16T00:21:43.988352Z","signature_status":"signed_v1","first_computed_at":"2026-07-16T00:21:43.988352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2512.10607","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-16T00:21:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jo+cwiISfHMRAUyaKpP8DBek6xPAHl9Mll9CCenXeOj+iBe4VXSYfTk/8hmvjhd8DA4nNkjn6eMhIkhA4M3UAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T16:35:21.855461Z"},"content_sha256":"c511b2e1a724676e4b85f84063139db921e270d88b5eb1fbe775fa6780c45cd7","schema_version":"1.0","event_id":"sha256:c511b2e1a724676e4b85f84063139db921e270d88b5eb1fbe775fa6780c45cd7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NQKTODVE2ULDO4HXGHEWW5GQUR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Track and Caption Any Motion: Open-Vocabulary Spatiotemporal Captioning via Trajectory-Conditioned Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bishoy Galoaa, Sarah Ostadabbas","submitted_at":"2025-12-11T13:03:03Z","abstract_excerpt":"We present TCAM (Track and Caption Any Motion), a generative framework that watches a video and with no text query and no region prompt decides what is moving, describes each motion in open vocabulary, locates it in time, and points to the exact trajectories that carry it. Two mature lines of work make this possible yet leave it unsolved: dense point trackers follow pixels with sub-object precision but emit no language, while video-language models produce fluent descriptions only when handed a query and only from clip-level features that cannot resolve which pixels move. Object-level captioner"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.10607","kind":"arxiv","version":2},"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/2512.10607/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":"2026-07-16T00:21:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vYNrg/dzT46ymP2TxzyjC9dITZ6YWVciQycJpQC7gGB4BeuBw+j3P93ffGnBWP7JkFyQKGj6Ialz32j46xHJBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T16:35:21.856223Z"},"content_sha256":"e093e576715d3e3c8c8b6bea7c871575515380e3da0197b0a2b9fb559e372a8e","schema_version":"1.0","event_id":"sha256:e093e576715d3e3c8c8b6bea7c871575515380e3da0197b0a2b9fb559e372a8e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NQKTODVE2ULDO4HXGHEWW5GQUR/bundle.json","state_url":"https://pith.science/pith/NQKTODVE2ULDO4HXGHEWW5GQUR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NQKTODVE2ULDO4HXGHEWW5GQUR/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":"2026-08-06T16:35:21Z","links":{"resolver":"https://pith.science/pith/NQKTODVE2ULDO4HXGHEWW5GQUR","bundle":"https://pith.science/pith/NQKTODVE2ULDO4HXGHEWW5GQUR/bundle.json","state":"https://pith.science/pith/NQKTODVE2ULDO4HXGHEWW5GQUR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NQKTODVE2ULDO4HXGHEWW5GQUR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NQKTODVE2ULDO4HXGHEWW5GQUR","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":"4decd5889a41d200bc438b8af4619c2e594a4e10275231907e521ac27cc27c88","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-11T13:03:03Z","title_canon_sha256":"3390b7db1402f8f227c358924864b8e8ef63b7af3211dab077ac5768532c9eb9"},"schema_version":"1.0","source":{"id":"2512.10607","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.10607","created_at":"2026-07-16T00:21:43Z"},{"alias_kind":"arxiv_version","alias_value":"2512.10607v2","created_at":"2026-07-16T00:21:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.10607","created_at":"2026-07-16T00:21:43Z"},{"alias_kind":"pith_short_12","alias_value":"NQKTODVE2ULD","created_at":"2026-07-16T00:21:43Z"},{"alias_kind":"pith_short_16","alias_value":"NQKTODVE2ULDO4HX","created_at":"2026-07-16T00:21:43Z"},{"alias_kind":"pith_short_8","alias_value":"NQKTODVE","created_at":"2026-07-16T00:21:43Z"}],"graph_snapshots":[{"event_id":"sha256:e093e576715d3e3c8c8b6bea7c871575515380e3da0197b0a2b9fb559e372a8e","target":"graph","created_at":"2026-07-16T00:21:43Z","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/2512.10607/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present TCAM (Track and Caption Any Motion), a generative framework that watches a video and with no text query and no region prompt decides what is moving, describes each motion in open vocabulary, locates it in time, and points to the exact trajectories that carry it. Two mature lines of work make this possible yet leave it unsolved: dense point trackers follow pixels with sub-object precision but emit no language, while video-language models produce fluent descriptions only when handed a query and only from clip-level features that cannot resolve which pixels move. Object-level captioner","authors_text":"Bishoy Galoaa, Sarah Ostadabbas","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-11T13:03:03Z","title":"Track and Caption Any Motion: Open-Vocabulary Spatiotemporal Captioning via Trajectory-Conditioned Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.10607","kind":"arxiv","version":2},"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:c511b2e1a724676e4b85f84063139db921e270d88b5eb1fbe775fa6780c45cd7","target":"record","created_at":"2026-07-16T00:21:43Z","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":"4decd5889a41d200bc438b8af4619c2e594a4e10275231907e521ac27cc27c88","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-11T13:03:03Z","title_canon_sha256":"3390b7db1402f8f227c358924864b8e8ef63b7af3211dab077ac5768532c9eb9"},"schema_version":"1.0","source":{"id":"2512.10607","kind":"arxiv","version":2}},"canonical_sha256":"6c15370ea4d5163770f731c96b74d0a4731e1e46d675249b6a399f8fd8b7e46a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6c15370ea4d5163770f731c96b74d0a4731e1e46d675249b6a399f8fd8b7e46a","first_computed_at":"2026-07-16T00:21:43.988352Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-16T00:21:43.988352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"euTKi1UmyPqqaa/GgE/y5/EYRTtrUjYm4tokjZOQ9NYmoEeDua7jJfmzyxUo+xITJJ1iKsb5D7kuIexTik+7DQ==","signature_status":"signed_v1","signed_at":"2026-07-16T00:21:43.989197Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.10607","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c511b2e1a724676e4b85f84063139db921e270d88b5eb1fbe775fa6780c45cd7","sha256:e093e576715d3e3c8c8b6bea7c871575515380e3da0197b0a2b9fb559e372a8e"],"state_sha256":"a2a4e3ce1bdbc1a34a8782b2bcadd2029f4126152d5a217bc3333f802a2b099e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HII51zf1wmSzgdP42+bKy1G8esfJgKpvqnafSFERXpbjkp/pzjEydmEvzYiBxbTYxXUmst9sxSZt7z7sjR6MDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T16:35:21.863070Z","bundle_sha256":"dbd74c66d738413c63474cd4749e60bea0834870add9de3c4a59640e0d680fe1"}}