{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:UIWAX4HH4OOFFRLHIVKYKVZFNW","short_pith_number":"pith:UIWAX4HH","canonical_record":{"source":{"id":"2305.14173","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-23T15:44:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cb13e62b918a2f44f0aebb783783311527cb08d22c489406b1b5217d8eb9ed39","abstract_canon_sha256":"447071defaab07ab885b8a0d111a14a08890c03576721fe3d3470eb92a2cdde8"},"schema_version":"1.0"},"canonical_sha256":"a22c0bf0e7e39c52c56745558557256db16a524a9bb4fda11f36ce6a6fd6fad8","source":{"kind":"arxiv","id":"2305.14173","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14173","created_at":"2026-07-05T06:13:01Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14173v1","created_at":"2026-07-05T06:13:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14173","created_at":"2026-07-05T06:13:01Z"},{"alias_kind":"pith_short_12","alias_value":"UIWAX4HH4OOF","created_at":"2026-07-05T06:13:01Z"},{"alias_kind":"pith_short_16","alias_value":"UIWAX4HH4OOFFRLH","created_at":"2026-07-05T06:13:01Z"},{"alias_kind":"pith_short_8","alias_value":"UIWAX4HH","created_at":"2026-07-05T06:13:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:UIWAX4HH4OOFFRLHIVKYKVZFNW","target":"record","payload":{"canonical_record":{"source":{"id":"2305.14173","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-23T15:44:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cb13e62b918a2f44f0aebb783783311527cb08d22c489406b1b5217d8eb9ed39","abstract_canon_sha256":"447071defaab07ab885b8a0d111a14a08890c03576721fe3d3470eb92a2cdde8"},"schema_version":"1.0"},"canonical_sha256":"a22c0bf0e7e39c52c56745558557256db16a524a9bb4fda11f36ce6a6fd6fad8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:01.763366Z","signature_b64":"wwqWaRzmzcYjCGLdcFbGFMMVUNaW+o75I2ATMBihd23hiOmWM7gSa6u5FbQXUqfErjkieHZzPmXkkw0plSC5Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a22c0bf0e7e39c52c56745558557256db16a524a9bb4fda11f36ce6a6fd6fad8","last_reissued_at":"2026-07-05T06:13:01.762838Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:01.762838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.14173","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":"2026-07-05T06:13:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5iqIuWDydqfzv4Ewxra7zgogY3fWEffkpLTFGMcWVjhQygwuO9juuB88C1bfKKorrBMP1y3KMwNztyrhwN5HBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T23:51:59.236522Z"},"content_sha256":"23d9baa7ef0694b03ba0ac1579fd9a5e0b7dff3943fd9ae4f3c04a91c6799ee9","schema_version":"1.0","event_id":"sha256:23d9baa7ef0694b03ba0ac1579fd9a5e0b7dff3943fd9ae4f3c04a91c6799ee9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:UIWAX4HH4OOFFRLHIVKYKVZFNW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TVTSv2: Learning Out-of-the-box Spatiotemporal Visual Representations at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Shu-Tao Xia, Xihui Liu, Ying Shan, Yixiao Ge, Zhan Tong, Ziyun Zeng","submitted_at":"2023-05-23T15:44:56Z","abstract_excerpt":"The ultimate goal for foundation models is realizing task-agnostic, i.e., supporting out-of-the-box usage without task-specific fine-tuning. Although breakthroughs have been made in natural language processing and image representation learning, it is still challenging for video models to reach it due to the increasing uncertainty of spatiotemporal signals. To ease training, existing works leverage image foundation models' prior knowledge and equip them with efficient temporal modules. Despite the satisfactory fine-tuning performance, we empirically find they fall short of out-of-the-box usage,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14173","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/2305.14173/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":"2026-07-05T06:13:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/vGFVlFTRSs3UID99ASh4Va2550Y6sJq98PDNK3zOYIQxZ/gJhPuFaZ0G+ez3Yum8LrsK0q0dVOQmkhy1YgwCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T23:51:59.236907Z"},"content_sha256":"999f33be75895ef42bda795b8442b8d9e328bd0473837b29e6fd58858c1ab657","schema_version":"1.0","event_id":"sha256:999f33be75895ef42bda795b8442b8d9e328bd0473837b29e6fd58858c1ab657"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UIWAX4HH4OOFFRLHIVKYKVZFNW/bundle.json","state_url":"https://pith.science/pith/UIWAX4HH4OOFFRLHIVKYKVZFNW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UIWAX4HH4OOFFRLHIVKYKVZFNW/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":"2026-07-24T23:51:59Z","links":{"resolver":"https://pith.science/pith/UIWAX4HH4OOFFRLHIVKYKVZFNW","bundle":"https://pith.science/pith/UIWAX4HH4OOFFRLHIVKYKVZFNW/bundle.json","state":"https://pith.science/pith/UIWAX4HH4OOFFRLHIVKYKVZFNW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UIWAX4HH4OOFFRLHIVKYKVZFNW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UIWAX4HH4OOFFRLHIVKYKVZFNW","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":"447071defaab07ab885b8a0d111a14a08890c03576721fe3d3470eb92a2cdde8","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-23T15:44:56Z","title_canon_sha256":"cb13e62b918a2f44f0aebb783783311527cb08d22c489406b1b5217d8eb9ed39"},"schema_version":"1.0","source":{"id":"2305.14173","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14173","created_at":"2026-07-05T06:13:01Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14173v1","created_at":"2026-07-05T06:13:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14173","created_at":"2026-07-05T06:13:01Z"},{"alias_kind":"pith_short_12","alias_value":"UIWAX4HH4OOF","created_at":"2026-07-05T06:13:01Z"},{"alias_kind":"pith_short_16","alias_value":"UIWAX4HH4OOFFRLH","created_at":"2026-07-05T06:13:01Z"},{"alias_kind":"pith_short_8","alias_value":"UIWAX4HH","created_at":"2026-07-05T06:13:01Z"}],"graph_snapshots":[{"event_id":"sha256:999f33be75895ef42bda795b8442b8d9e328bd0473837b29e6fd58858c1ab657","target":"graph","created_at":"2026-07-05T06:13:01Z","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/2305.14173/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The ultimate goal for foundation models is realizing task-agnostic, i.e., supporting out-of-the-box usage without task-specific fine-tuning. Although breakthroughs have been made in natural language processing and image representation learning, it is still challenging for video models to reach it due to the increasing uncertainty of spatiotemporal signals. To ease training, existing works leverage image foundation models' prior knowledge and equip them with efficient temporal modules. Despite the satisfactory fine-tuning performance, we empirically find they fall short of out-of-the-box usage,","authors_text":"Shu-Tao Xia, Xihui Liu, Ying Shan, Yixiao Ge, Zhan Tong, Ziyun Zeng","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-23T15:44:56Z","title":"TVTSv2: Learning Out-of-the-box Spatiotemporal Visual Representations at Scale"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14173","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":"sha256:23d9baa7ef0694b03ba0ac1579fd9a5e0b7dff3943fd9ae4f3c04a91c6799ee9","target":"record","created_at":"2026-07-05T06:13:01Z","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":"447071defaab07ab885b8a0d111a14a08890c03576721fe3d3470eb92a2cdde8","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-23T15:44:56Z","title_canon_sha256":"cb13e62b918a2f44f0aebb783783311527cb08d22c489406b1b5217d8eb9ed39"},"schema_version":"1.0","source":{"id":"2305.14173","kind":"arxiv","version":1}},"canonical_sha256":"a22c0bf0e7e39c52c56745558557256db16a524a9bb4fda11f36ce6a6fd6fad8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a22c0bf0e7e39c52c56745558557256db16a524a9bb4fda11f36ce6a6fd6fad8","first_computed_at":"2026-07-05T06:13:01.762838Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:13:01.762838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wwqWaRzmzcYjCGLdcFbGFMMVUNaW+o75I2ATMBihd23hiOmWM7gSa6u5FbQXUqfErjkieHZzPmXkkw0plSC5Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:13:01.763366Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.14173","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:23d9baa7ef0694b03ba0ac1579fd9a5e0b7dff3943fd9ae4f3c04a91c6799ee9","sha256:999f33be75895ef42bda795b8442b8d9e328bd0473837b29e6fd58858c1ab657"],"state_sha256":"f2bd31b417292fda02a697e85c406191ce36338bff0fb4b79bbc4376fa14e1aa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gB2rNT99PX1kjLpWux3mUxOyVQ3cGUnQpciEmDjKWiM6pjINAVmxmC4FQH7GgJbzNl6t916mULssCIhHa/LzCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-24T23:51:59.239089Z","bundle_sha256":"1dd9276bb872600b523091beb44a5ba407d6f8f1bbee5af1203e0330e9075017"}}