{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YQFGZWF5N6GNSKR3735H6UNYQJ","short_pith_number":"pith:YQFGZWF5","canonical_record":{"source":{"id":"2506.22562","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-27T18:21:58Z","cross_cats_sorted":[],"title_canon_sha256":"699eff17181443fea5217d6a8ef4161d4588bde4e158fbde9d8324159b127049","abstract_canon_sha256":"8035f007e9f3ac61075521801cfc4ce42b7adfb7af79f72133bbca37ca6d75b1"},"schema_version":"1.0"},"canonical_sha256":"c40a6cd8bd6f8cd92a3bfefa7f51b88278c270c42bfba56f15461f0d8b6434b2","source":{"kind":"arxiv","id":"2506.22562","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.22562","created_at":"2026-07-05T11:56:20Z"},{"alias_kind":"arxiv_version","alias_value":"2506.22562v2","created_at":"2026-07-05T11:56:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.22562","created_at":"2026-07-05T11:56:20Z"},{"alias_kind":"pith_short_12","alias_value":"YQFGZWF5N6GN","created_at":"2026-07-05T11:56:20Z"},{"alias_kind":"pith_short_16","alias_value":"YQFGZWF5N6GNSKR3","created_at":"2026-07-05T11:56:20Z"},{"alias_kind":"pith_short_8","alias_value":"YQFGZWF5","created_at":"2026-07-05T11:56:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YQFGZWF5N6GNSKR3735H6UNYQJ","target":"record","payload":{"canonical_record":{"source":{"id":"2506.22562","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-27T18:21:58Z","cross_cats_sorted":[],"title_canon_sha256":"699eff17181443fea5217d6a8ef4161d4588bde4e158fbde9d8324159b127049","abstract_canon_sha256":"8035f007e9f3ac61075521801cfc4ce42b7adfb7af79f72133bbca37ca6d75b1"},"schema_version":"1.0"},"canonical_sha256":"c40a6cd8bd6f8cd92a3bfefa7f51b88278c270c42bfba56f15461f0d8b6434b2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:20.972166Z","signature_b64":"KJ4LHCKtslIJEszkKTG1sEs46POB7+hYGLKidH055FI0bxhvIOlQGRDo/BWymsYUpS8OiVkfsKJSeGPzj/yWDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c40a6cd8bd6f8cd92a3bfefa7f51b88278c270c42bfba56f15461f0d8b6434b2","last_reissued_at":"2026-07-05T11:56:20.971698Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:20.971698Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.22562","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":"2026-07-05T11:56:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xMQfGUKcWczym4z6k1w6B8jq50BlmIZetxpoqLTMy63PH+OQqIstgo6ne/PJmwDfBix1jAKDfZ4PcqDj/OJXDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T19:01:08.766046Z"},"content_sha256":"34c71c624ebcdf0e9a8bf58a3264de770426572c0455f2e5fdb6bec56e896051","schema_version":"1.0","event_id":"sha256:34c71c624ebcdf0e9a8bf58a3264de770426572c0455f2e5fdb6bec56e896051"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YQFGZWF5N6GNSKR3735H6UNYQJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Token-based Object Detection with Video","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhineet Singh, Nilanjan Ray","submitted_at":"2025-06-27T18:21:58Z","abstract_excerpt":"This paper improves upon the Pix2Seq object detector by extending it for videos. In the process, it introduces a new way to perform end-to-end video object detection that improves upon existing video detectors in two key ways. First, by representing objects as variable-length sequences of discrete tokens, we can succinctly represent widely varying numbers of video objects, with diverse shapes and locations, without having to inject any localization cues in the training process. This eliminates the need to sample the space of all possible boxes that constrains conventional detectors and thus so"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.22562","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/2506.22562/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":"2026-07-05T11:56:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lHnfERTKcDg4XEjfR6b2gcXRx/83SAIKEwXOrZN1vEG4yTNJlrBaC3+aqey42BqNiy3SUr92bzEmw2KtOxVKAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T19:01:08.766561Z"},"content_sha256":"479ead002b8c1eadd2216bd092fdfc27ded1ec6c6c7f520fce0a19195b0eda36","schema_version":"1.0","event_id":"sha256:479ead002b8c1eadd2216bd092fdfc27ded1ec6c6c7f520fce0a19195b0eda36"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YQFGZWF5N6GNSKR3735H6UNYQJ/bundle.json","state_url":"https://pith.science/pith/YQFGZWF5N6GNSKR3735H6UNYQJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YQFGZWF5N6GNSKR3735H6UNYQJ/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":"2026-08-15T19:01:08Z","links":{"resolver":"https://pith.science/pith/YQFGZWF5N6GNSKR3735H6UNYQJ","bundle":"https://pith.science/pith/YQFGZWF5N6GNSKR3735H6UNYQJ/bundle.json","state":"https://pith.science/pith/YQFGZWF5N6GNSKR3735H6UNYQJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YQFGZWF5N6GNSKR3735H6UNYQJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YQFGZWF5N6GNSKR3735H6UNYQJ","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":"8035f007e9f3ac61075521801cfc4ce42b7adfb7af79f72133bbca37ca6d75b1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-27T18:21:58Z","title_canon_sha256":"699eff17181443fea5217d6a8ef4161d4588bde4e158fbde9d8324159b127049"},"schema_version":"1.0","source":{"id":"2506.22562","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.22562","created_at":"2026-07-05T11:56:20Z"},{"alias_kind":"arxiv_version","alias_value":"2506.22562v2","created_at":"2026-07-05T11:56:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.22562","created_at":"2026-07-05T11:56:20Z"},{"alias_kind":"pith_short_12","alias_value":"YQFGZWF5N6GN","created_at":"2026-07-05T11:56:20Z"},{"alias_kind":"pith_short_16","alias_value":"YQFGZWF5N6GNSKR3","created_at":"2026-07-05T11:56:20Z"},{"alias_kind":"pith_short_8","alias_value":"YQFGZWF5","created_at":"2026-07-05T11:56:20Z"}],"graph_snapshots":[{"event_id":"sha256:479ead002b8c1eadd2216bd092fdfc27ded1ec6c6c7f520fce0a19195b0eda36","target":"graph","created_at":"2026-07-05T11:56:20Z","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/2506.22562/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper improves upon the Pix2Seq object detector by extending it for videos. In the process, it introduces a new way to perform end-to-end video object detection that improves upon existing video detectors in two key ways. First, by representing objects as variable-length sequences of discrete tokens, we can succinctly represent widely varying numbers of video objects, with diverse shapes and locations, without having to inject any localization cues in the training process. This eliminates the need to sample the space of all possible boxes that constrains conventional detectors and thus so","authors_text":"Abhineet Singh, Nilanjan Ray","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-27T18:21:58Z","title":"Improving Token-based Object Detection with Video"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.22562","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":"sha256:34c71c624ebcdf0e9a8bf58a3264de770426572c0455f2e5fdb6bec56e896051","target":"record","created_at":"2026-07-05T11:56:20Z","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":"8035f007e9f3ac61075521801cfc4ce42b7adfb7af79f72133bbca37ca6d75b1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-27T18:21:58Z","title_canon_sha256":"699eff17181443fea5217d6a8ef4161d4588bde4e158fbde9d8324159b127049"},"schema_version":"1.0","source":{"id":"2506.22562","kind":"arxiv","version":2}},"canonical_sha256":"c40a6cd8bd6f8cd92a3bfefa7f51b88278c270c42bfba56f15461f0d8b6434b2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c40a6cd8bd6f8cd92a3bfefa7f51b88278c270c42bfba56f15461f0d8b6434b2","first_computed_at":"2026-07-05T11:56:20.971698Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:56:20.971698Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KJ4LHCKtslIJEszkKTG1sEs46POB7+hYGLKidH055FI0bxhvIOlQGRDo/BWymsYUpS8OiVkfsKJSeGPzj/yWDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:56:20.972166Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.22562","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:34c71c624ebcdf0e9a8bf58a3264de770426572c0455f2e5fdb6bec56e896051","sha256:479ead002b8c1eadd2216bd092fdfc27ded1ec6c6c7f520fce0a19195b0eda36"],"state_sha256":"e8fb27a710edfe76fac5ae2c32f9826c588791ebd20a3968bcba3f41f02af91f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GDOh8N+MTHPFFADKPqM0f7o3wlr1/r65ybp6s/IRt38XeODkhv8/3yKtRVCKEPSZJWJCU7LCseZhVrmn5QoDAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T19:01:08.770650Z","bundle_sha256":"872054ace7cf5ecef2c4ad5fb502c03cfe05373bce956cc84c835ba1befcb702"}}