{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TFDRW42V4EHJ2CVWKWYZR2KVU4","short_pith_number":"pith:TFDRW42V","canonical_record":{"source":{"id":"2505.23704","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T17:39:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"05c1cc1d67b7eaa5f87641315e961b6ca6ea3c95c33a1a2a3304ff39a0b2e972","abstract_canon_sha256":"fd872e4d91ad5f85054fa42cc4344bf51d5f145b2e9b3a6792d7e09db97fbaa9"},"schema_version":"1.0"},"canonical_sha256":"99471b7355e10e9d0ab655b198e955a736fee3266a422877adc9e3e9a1cc1587","source":{"kind":"arxiv","id":"2505.23704","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23704","created_at":"2026-07-05T11:12:12Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23704v1","created_at":"2026-07-05T11:12:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23704","created_at":"2026-07-05T11:12:12Z"},{"alias_kind":"pith_short_12","alias_value":"TFDRW42V4EHJ","created_at":"2026-07-05T11:12:12Z"},{"alias_kind":"pith_short_16","alias_value":"TFDRW42V4EHJ2CVW","created_at":"2026-07-05T11:12:12Z"},{"alias_kind":"pith_short_8","alias_value":"TFDRW42V","created_at":"2026-07-05T11:12:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TFDRW42V4EHJ2CVWKWYZR2KVU4","target":"record","payload":{"canonical_record":{"source":{"id":"2505.23704","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T17:39:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"05c1cc1d67b7eaa5f87641315e961b6ca6ea3c95c33a1a2a3304ff39a0b2e972","abstract_canon_sha256":"fd872e4d91ad5f85054fa42cc4344bf51d5f145b2e9b3a6792d7e09db97fbaa9"},"schema_version":"1.0"},"canonical_sha256":"99471b7355e10e9d0ab655b198e955a736fee3266a422877adc9e3e9a1cc1587","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:12.953831Z","signature_b64":"QCIkB6yQoPoiKpVrXjjiTNCr4vLRTkEag990hU5zlu14ZNlF6gkB9/G1CDmAfjY2v78/QOE8/pp1E26jzMneDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99471b7355e10e9d0ab655b198e955a736fee3266a422877adc9e3e9a1cc1587","last_reissued_at":"2026-07-05T11:12:12.953383Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:12.953383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.23704","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":"2026-07-05T11:12:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a7WMkVyp2JE5oGv2EvBlQM8Q0YCMMYJjGIe8OsYHwGLy9yNYAebLwsyH3F1Izi3Gicdzq7weZGfbbT9XfaJoAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T08:05:49.568740Z"},"content_sha256":"06224eb3264a77a6c1e97cf127a605bfe9526d4860c444aa903f6f1a1d5721cf","schema_version":"1.0","event_id":"sha256:06224eb3264a77a6c1e97cf127a605bfe9526d4860c444aa903f6f1a1d5721cf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TFDRW42V4EHJ2CVWKWYZR2KVU4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CLDTracker: A Comprehensive Language Description for Visual Tracking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Iyyakutti Iyappan Ganapathi, Mohamad Alansari, Muzammal Naseer, Sajid Javed, Sara Alansari","submitted_at":"2025-05-29T17:39:30Z","abstract_excerpt":"VOT remains a fundamental yet challenging task in computer vision due to dynamic appearance changes, occlusions, and background clutter. Traditional trackers, relying primarily on visual cues, often struggle in such complex scenarios. Recent advancements in VLMs have shown promise in semantic understanding for tasks like open-vocabulary detection and image captioning, suggesting their potential for VOT. However, the direct application of VLMs to VOT is hindered by critical limitations: the absence of a rich and comprehensive textual representation that semantically captures the target object's"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23704","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/2505.23704/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":"2026-07-05T11:12:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gpqF68mGBXV1FfjIorsWXlTTwLTViKM7clvl3nlsWZ4H6dRC+Spj0r46W6DXwq8wTYgYoP9Vl48leOXmhiIQAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T08:05:49.569259Z"},"content_sha256":"5d1b41abd7aab753585b7dbaa9cb61742c5115c872a3bc8b3fa20718b742c325","schema_version":"1.0","event_id":"sha256:5d1b41abd7aab753585b7dbaa9cb61742c5115c872a3bc8b3fa20718b742c325"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TFDRW42V4EHJ2CVWKWYZR2KVU4/bundle.json","state_url":"https://pith.science/pith/TFDRW42V4EHJ2CVWKWYZR2KVU4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TFDRW42V4EHJ2CVWKWYZR2KVU4/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":"2026-08-10T08:05:49Z","links":{"resolver":"https://pith.science/pith/TFDRW42V4EHJ2CVWKWYZR2KVU4","bundle":"https://pith.science/pith/TFDRW42V4EHJ2CVWKWYZR2KVU4/bundle.json","state":"https://pith.science/pith/TFDRW42V4EHJ2CVWKWYZR2KVU4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TFDRW42V4EHJ2CVWKWYZR2KVU4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TFDRW42V4EHJ2CVWKWYZR2KVU4","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":"fd872e4d91ad5f85054fa42cc4344bf51d5f145b2e9b3a6792d7e09db97fbaa9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T17:39:30Z","title_canon_sha256":"05c1cc1d67b7eaa5f87641315e961b6ca6ea3c95c33a1a2a3304ff39a0b2e972"},"schema_version":"1.0","source":{"id":"2505.23704","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23704","created_at":"2026-07-05T11:12:12Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23704v1","created_at":"2026-07-05T11:12:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23704","created_at":"2026-07-05T11:12:12Z"},{"alias_kind":"pith_short_12","alias_value":"TFDRW42V4EHJ","created_at":"2026-07-05T11:12:12Z"},{"alias_kind":"pith_short_16","alias_value":"TFDRW42V4EHJ2CVW","created_at":"2026-07-05T11:12:12Z"},{"alias_kind":"pith_short_8","alias_value":"TFDRW42V","created_at":"2026-07-05T11:12:12Z"}],"graph_snapshots":[{"event_id":"sha256:5d1b41abd7aab753585b7dbaa9cb61742c5115c872a3bc8b3fa20718b742c325","target":"graph","created_at":"2026-07-05T11:12:12Z","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/2505.23704/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"VOT remains a fundamental yet challenging task in computer vision due to dynamic appearance changes, occlusions, and background clutter. Traditional trackers, relying primarily on visual cues, often struggle in such complex scenarios. Recent advancements in VLMs have shown promise in semantic understanding for tasks like open-vocabulary detection and image captioning, suggesting their potential for VOT. However, the direct application of VLMs to VOT is hindered by critical limitations: the absence of a rich and comprehensive textual representation that semantically captures the target object's","authors_text":"Iyyakutti Iyappan Ganapathi, Mohamad Alansari, Muzammal Naseer, Sajid Javed, Sara Alansari","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T17:39:30Z","title":"CLDTracker: A Comprehensive Language Description for Visual Tracking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23704","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":"sha256:06224eb3264a77a6c1e97cf127a605bfe9526d4860c444aa903f6f1a1d5721cf","target":"record","created_at":"2026-07-05T11:12:12Z","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":"fd872e4d91ad5f85054fa42cc4344bf51d5f145b2e9b3a6792d7e09db97fbaa9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T17:39:30Z","title_canon_sha256":"05c1cc1d67b7eaa5f87641315e961b6ca6ea3c95c33a1a2a3304ff39a0b2e972"},"schema_version":"1.0","source":{"id":"2505.23704","kind":"arxiv","version":1}},"canonical_sha256":"99471b7355e10e9d0ab655b198e955a736fee3266a422877adc9e3e9a1cc1587","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"99471b7355e10e9d0ab655b198e955a736fee3266a422877adc9e3e9a1cc1587","first_computed_at":"2026-07-05T11:12:12.953383Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:12.953383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QCIkB6yQoPoiKpVrXjjiTNCr4vLRTkEag990hU5zlu14ZNlF6gkB9/G1CDmAfjY2v78/QOE8/pp1E26jzMneDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:12.953831Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.23704","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:06224eb3264a77a6c1e97cf127a605bfe9526d4860c444aa903f6f1a1d5721cf","sha256:5d1b41abd7aab753585b7dbaa9cb61742c5115c872a3bc8b3fa20718b742c325"],"state_sha256":"f63738c4794f0b9febfe6fa05bf13d4de82b3a0358e5c34f7776e6ae74d4d009"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FEtE/nUN7TI3No21A6g8NkmKIbXaqIOesDNrSvOTHkUIlljAswQWcicySziac81hlT4zMSQbc+XceCnxUgwjAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T08:05:49.573838Z","bundle_sha256":"1384eff094e7b1f506f776ad1d5d66757d4900a58224f21aa93552023e0ca092"}}