{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7BMIBQDDG23WMXCCZ4BH7UAGPE","short_pith_number":"pith:7BMIBQDD","canonical_record":{"source":{"id":"2404.00801","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-31T21:17:48Z","cross_cats_sorted":[],"title_canon_sha256":"d6a6ec6a178c94db5adb65db12e6a25a361dc0b363cbb51e529210a763c91afc","abstract_canon_sha256":"651d05c1649b581e0638b6a6f5eabf801e381f871340ffa70e99b17bd88d3b4d"},"schema_version":"1.0"},"canonical_sha256":"f85880c06336b7665c42cf027fd00679083c4f81da5c2108c56342498df7ecff","source":{"kind":"arxiv","id":"2404.00801","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.00801","created_at":"2026-07-05T08:46:23Z"},{"alias_kind":"arxiv_version","alias_value":"2404.00801v2","created_at":"2026-07-05T08:46:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00801","created_at":"2026-07-05T08:46:23Z"},{"alias_kind":"pith_short_12","alias_value":"7BMIBQDDG23W","created_at":"2026-07-05T08:46:23Z"},{"alias_kind":"pith_short_16","alias_value":"7BMIBQDDG23WMXCC","created_at":"2026-07-05T08:46:23Z"},{"alias_kind":"pith_short_8","alias_value":"7BMIBQDD","created_at":"2026-07-05T08:46:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7BMIBQDDG23WMXCCZ4BH7UAGPE","target":"record","payload":{"canonical_record":{"source":{"id":"2404.00801","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-31T21:17:48Z","cross_cats_sorted":[],"title_canon_sha256":"d6a6ec6a178c94db5adb65db12e6a25a361dc0b363cbb51e529210a763c91afc","abstract_canon_sha256":"651d05c1649b581e0638b6a6f5eabf801e381f871340ffa70e99b17bd88d3b4d"},"schema_version":"1.0"},"canonical_sha256":"f85880c06336b7665c42cf027fd00679083c4f81da5c2108c56342498df7ecff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:23.552674Z","signature_b64":"cAfLcm1B+SlEcEuZH1Mwpc0YRd69TaIVU75ogOn4XuXDOE7lE9x8DOGhx4SRlDlFlBHCwVHeXzJKxgCFYO3hDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f85880c06336b7665c42cf027fd00679083c4f81da5c2108c56342498df7ecff","last_reissued_at":"2026-07-05T08:46:23.552270Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:23.552270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.00801","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":"2026-07-05T08:46:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"icTpEb1Fw86PffyUMA+vRZHIfeYlp72fbEQCZjZCvc87K8vHpxA/nrf9H8PCtTV52FRwnUsjkrxyYCaE1GlYCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:43:48.921229Z"},"content_sha256":"cfb8167894dd97fcdafeed2a1544e4a85014abff31f3a5d36f7e0f45f48611ab","schema_version":"1.0","event_id":"sha256:cfb8167894dd97fcdafeed2a1544e4a85014abff31f3a5d36f7e0f45f48611ab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7BMIBQDDG23WMXCCZ4BH7UAGPE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"$R^2$-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Wen Chen, Donglai Wei, Hanspeter Pfister, Jixuan He, Junsik Kim, Wanhua Li, Ye Liu","submitted_at":"2024-03-31T21:17:48Z","abstract_excerpt":"Video temporal grounding (VTG) is a fine-grained video understanding problem that aims to ground relevant clips in untrimmed videos given natural language queries. Most existing VTG models are built upon frame-wise final-layer CLIP features, aided by additional temporal backbones (e.g., SlowFast) with sophisticated temporal reasoning mechanisms. In this work, we claim that CLIP itself already shows great potential for fine-grained spatial-temporal modeling, as each layer offers distinct yet useful information under different granularity levels. Motivated by this, we propose Reversed Recurrent "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00801","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/2404.00801/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":"2026-07-05T08:46:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nsdLVefk59TI27JBiHNBv+JIkz3lvrMSwLwjX8ypYYPFsdDRW5J9IIOxiPPi+YNIEchCIV9Hg7RaoWUKOsZSAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:43:48.921606Z"},"content_sha256":"b885eee48ee77e4a51ffdbffbc15ac829a7abde44209f813a53985cf979dd8f1","schema_version":"1.0","event_id":"sha256:b885eee48ee77e4a51ffdbffbc15ac829a7abde44209f813a53985cf979dd8f1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7BMIBQDDG23WMXCCZ4BH7UAGPE/bundle.json","state_url":"https://pith.science/pith/7BMIBQDDG23WMXCCZ4BH7UAGPE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7BMIBQDDG23WMXCCZ4BH7UAGPE/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":"2026-08-03T17:43:48Z","links":{"resolver":"https://pith.science/pith/7BMIBQDDG23WMXCCZ4BH7UAGPE","bundle":"https://pith.science/pith/7BMIBQDDG23WMXCCZ4BH7UAGPE/bundle.json","state":"https://pith.science/pith/7BMIBQDDG23WMXCCZ4BH7UAGPE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7BMIBQDDG23WMXCCZ4BH7UAGPE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7BMIBQDDG23WMXCCZ4BH7UAGPE","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":"651d05c1649b581e0638b6a6f5eabf801e381f871340ffa70e99b17bd88d3b4d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-31T21:17:48Z","title_canon_sha256":"d6a6ec6a178c94db5adb65db12e6a25a361dc0b363cbb51e529210a763c91afc"},"schema_version":"1.0","source":{"id":"2404.00801","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.00801","created_at":"2026-07-05T08:46:23Z"},{"alias_kind":"arxiv_version","alias_value":"2404.00801v2","created_at":"2026-07-05T08:46:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00801","created_at":"2026-07-05T08:46:23Z"},{"alias_kind":"pith_short_12","alias_value":"7BMIBQDDG23W","created_at":"2026-07-05T08:46:23Z"},{"alias_kind":"pith_short_16","alias_value":"7BMIBQDDG23WMXCC","created_at":"2026-07-05T08:46:23Z"},{"alias_kind":"pith_short_8","alias_value":"7BMIBQDD","created_at":"2026-07-05T08:46:23Z"}],"graph_snapshots":[{"event_id":"sha256:b885eee48ee77e4a51ffdbffbc15ac829a7abde44209f813a53985cf979dd8f1","target":"graph","created_at":"2026-07-05T08:46:23Z","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/2404.00801/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video temporal grounding (VTG) is a fine-grained video understanding problem that aims to ground relevant clips in untrimmed videos given natural language queries. Most existing VTG models are built upon frame-wise final-layer CLIP features, aided by additional temporal backbones (e.g., SlowFast) with sophisticated temporal reasoning mechanisms. In this work, we claim that CLIP itself already shows great potential for fine-grained spatial-temporal modeling, as each layer offers distinct yet useful information under different granularity levels. Motivated by this, we propose Reversed Recurrent ","authors_text":"Chang Wen Chen, Donglai Wei, Hanspeter Pfister, Jixuan He, Junsik Kim, Wanhua Li, Ye Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-31T21:17:48Z","title":"$R^2$-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00801","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:cfb8167894dd97fcdafeed2a1544e4a85014abff31f3a5d36f7e0f45f48611ab","target":"record","created_at":"2026-07-05T08:46:23Z","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":"651d05c1649b581e0638b6a6f5eabf801e381f871340ffa70e99b17bd88d3b4d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-31T21:17:48Z","title_canon_sha256":"d6a6ec6a178c94db5adb65db12e6a25a361dc0b363cbb51e529210a763c91afc"},"schema_version":"1.0","source":{"id":"2404.00801","kind":"arxiv","version":2}},"canonical_sha256":"f85880c06336b7665c42cf027fd00679083c4f81da5c2108c56342498df7ecff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f85880c06336b7665c42cf027fd00679083c4f81da5c2108c56342498df7ecff","first_computed_at":"2026-07-05T08:46:23.552270Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:46:23.552270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cAfLcm1B+SlEcEuZH1Mwpc0YRd69TaIVU75ogOn4XuXDOE7lE9x8DOGhx4SRlDlFlBHCwVHeXzJKxgCFYO3hDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:46:23.552674Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.00801","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cfb8167894dd97fcdafeed2a1544e4a85014abff31f3a5d36f7e0f45f48611ab","sha256:b885eee48ee77e4a51ffdbffbc15ac829a7abde44209f813a53985cf979dd8f1"],"state_sha256":"77f4d59d299b36f0dfcc94a94caf5e47f2dec4842c33a1c1e227be86e231a46d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z8v5qxUeaf2gNRxSll++UlCQD35t9Zbrs15D0aTxdsweQ/HvRWxB3QCY/6+TAbcL6aGZgVcoH/Sf0OiqlIdBDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T17:43:48.923925Z","bundle_sha256":"809128ee5717a8a77bdaa61c7acf1c80eca32bc70f3d60edb5cd7e56aa173817"}}