{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:GXENAZTUWE4KYTX7CQX3GOKGDZ","short_pith_number":"pith:GXENAZTU","canonical_record":{"source":{"id":"2106.11297","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-21T17:55:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"be2e1ce849b29b8378b725a85ce90fcfcf0fc56b05c4a7cf28ff8a13e2c83581","abstract_canon_sha256":"c5ab1b294844bd4a0d6b20013418801fdd11e0627a969def87e993d670ebc75e"},"schema_version":"1.0"},"canonical_sha256":"35c8d06674b138ac4eff142fb339461e700d3cba34a16f7d80c3f1d2dbdcf0f0","source":{"kind":"arxiv","id":"2106.11297","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.11297","created_at":"2026-07-05T04:11:06Z"},{"alias_kind":"arxiv_version","alias_value":"2106.11297v4","created_at":"2026-07-05T04:11:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.11297","created_at":"2026-07-05T04:11:06Z"},{"alias_kind":"pith_short_12","alias_value":"GXENAZTUWE4K","created_at":"2026-07-05T04:11:06Z"},{"alias_kind":"pith_short_16","alias_value":"GXENAZTUWE4KYTX7","created_at":"2026-07-05T04:11:06Z"},{"alias_kind":"pith_short_8","alias_value":"GXENAZTU","created_at":"2026-07-05T04:11:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:GXENAZTUWE4KYTX7CQX3GOKGDZ","target":"record","payload":{"canonical_record":{"source":{"id":"2106.11297","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-21T17:55:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"be2e1ce849b29b8378b725a85ce90fcfcf0fc56b05c4a7cf28ff8a13e2c83581","abstract_canon_sha256":"c5ab1b294844bd4a0d6b20013418801fdd11e0627a969def87e993d670ebc75e"},"schema_version":"1.0"},"canonical_sha256":"35c8d06674b138ac4eff142fb339461e700d3cba34a16f7d80c3f1d2dbdcf0f0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:11:06.249229Z","signature_b64":"uaD+J2MSeDqrWdSSbAW/ozB0KpMYbKcV6L8rURK4sr7N32uP1xfUEIHOGZVgz9BL93rB28cIBjbookI7OEu4BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35c8d06674b138ac4eff142fb339461e700d3cba34a16f7d80c3f1d2dbdcf0f0","last_reissued_at":"2026-07-05T04:11:06.248800Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:11:06.248800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.11297","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:11:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8JdWM+16TgSDVBGQhNimP5nthJynjyW3l4r+iC3xx6pc+XI9jU7O4FOfNjT/lqe1c9I16DTslD0c96OFPJOJDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:38:21.988867Z"},"content_sha256":"92e60f2e858794a3cfec532b8cd61fc98b781d4136b0a1c651febbbe1dac2d3b","schema_version":"1.0","event_id":"sha256:92e60f2e858794a3cfec532b8cd61fc98b781d4136b0a1c651febbbe1dac2d3b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:GXENAZTUWE4KYTX7CQX3GOKGDZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"AJ Piergiovanni, Anelia Angelova, Anurag Arnab, Michael S. Ryoo, Mostafa Dehghani","submitted_at":"2021-06-21T17:55:59Z","abstract_excerpt":"In this paper, we introduce a novel visual representation learning which relies on a handful of adaptively learned tokens, and which is applicable to both image and video understanding tasks. Instead of relying on hand-designed splitting strategies to obtain visual tokens and processing a large number of densely sampled patches for attention, our approach learns to mine important tokens in visual data. This results in efficiently and effectively finding a few important visual tokens and enables modeling of pairwise attention between such tokens, over a longer temporal horizon for videos, or th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.11297","kind":"arxiv","version":4},"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/2106.11297/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":"2026-07-05T04:11:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XwWzE25iyEuSqBAfi2IJLz1vhrn2rStNNjcdheKpr+zBN4VnL3vzj5TNwAyec5ZGrFRWU5klSl+BdzCRW603Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:38:21.989234Z"},"content_sha256":"e54864d5a136b4017052589d7e6d5d88dd00b6fb037f80961ae270532aae566b","schema_version":"1.0","event_id":"sha256:e54864d5a136b4017052589d7e6d5d88dd00b6fb037f80961ae270532aae566b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GXENAZTUWE4KYTX7CQX3GOKGDZ/bundle.json","state_url":"https://pith.science/pith/GXENAZTUWE4KYTX7CQX3GOKGDZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GXENAZTUWE4KYTX7CQX3GOKGDZ/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":"2026-07-07T15:38:21Z","links":{"resolver":"https://pith.science/pith/GXENAZTUWE4KYTX7CQX3GOKGDZ","bundle":"https://pith.science/pith/GXENAZTUWE4KYTX7CQX3GOKGDZ/bundle.json","state":"https://pith.science/pith/GXENAZTUWE4KYTX7CQX3GOKGDZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GXENAZTUWE4KYTX7CQX3GOKGDZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:GXENAZTUWE4KYTX7CQX3GOKGDZ","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":"c5ab1b294844bd4a0d6b20013418801fdd11e0627a969def87e993d670ebc75e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-21T17:55:59Z","title_canon_sha256":"be2e1ce849b29b8378b725a85ce90fcfcf0fc56b05c4a7cf28ff8a13e2c83581"},"schema_version":"1.0","source":{"id":"2106.11297","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.11297","created_at":"2026-07-05T04:11:06Z"},{"alias_kind":"arxiv_version","alias_value":"2106.11297v4","created_at":"2026-07-05T04:11:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.11297","created_at":"2026-07-05T04:11:06Z"},{"alias_kind":"pith_short_12","alias_value":"GXENAZTUWE4K","created_at":"2026-07-05T04:11:06Z"},{"alias_kind":"pith_short_16","alias_value":"GXENAZTUWE4KYTX7","created_at":"2026-07-05T04:11:06Z"},{"alias_kind":"pith_short_8","alias_value":"GXENAZTU","created_at":"2026-07-05T04:11:06Z"}],"graph_snapshots":[{"event_id":"sha256:e54864d5a136b4017052589d7e6d5d88dd00b6fb037f80961ae270532aae566b","target":"graph","created_at":"2026-07-05T04:11:06Z","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/2106.11297/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we introduce a novel visual representation learning which relies on a handful of adaptively learned tokens, and which is applicable to both image and video understanding tasks. Instead of relying on hand-designed splitting strategies to obtain visual tokens and processing a large number of densely sampled patches for attention, our approach learns to mine important tokens in visual data. This results in efficiently and effectively finding a few important visual tokens and enables modeling of pairwise attention between such tokens, over a longer temporal horizon for videos, or th","authors_text":"AJ Piergiovanni, Anelia Angelova, Anurag Arnab, Michael S. Ryoo, Mostafa Dehghani","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-21T17:55:59Z","title":"TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.11297","kind":"arxiv","version":4},"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":"sha256:92e60f2e858794a3cfec532b8cd61fc98b781d4136b0a1c651febbbe1dac2d3b","target":"record","created_at":"2026-07-05T04:11:06Z","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":"c5ab1b294844bd4a0d6b20013418801fdd11e0627a969def87e993d670ebc75e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-21T17:55:59Z","title_canon_sha256":"be2e1ce849b29b8378b725a85ce90fcfcf0fc56b05c4a7cf28ff8a13e2c83581"},"schema_version":"1.0","source":{"id":"2106.11297","kind":"arxiv","version":4}},"canonical_sha256":"35c8d06674b138ac4eff142fb339461e700d3cba34a16f7d80c3f1d2dbdcf0f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"35c8d06674b138ac4eff142fb339461e700d3cba34a16f7d80c3f1d2dbdcf0f0","first_computed_at":"2026-07-05T04:11:06.248800Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:11:06.248800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uaD+J2MSeDqrWdSSbAW/ozB0KpMYbKcV6L8rURK4sr7N32uP1xfUEIHOGZVgz9BL93rB28cIBjbookI7OEu4BA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:11:06.249229Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.11297","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:92e60f2e858794a3cfec532b8cd61fc98b781d4136b0a1c651febbbe1dac2d3b","sha256:e54864d5a136b4017052589d7e6d5d88dd00b6fb037f80961ae270532aae566b"],"state_sha256":"d285fd7165a21e6dc4dd71f561e90f435a6ed0b0556dd84e4028155ede6b9818"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wwx/njJjo7z1T0tlDjkcZIPX7h2vPI7h4KuebM4RoSaBnE81AoLj7g6/xsFegddwPABC30PYzFSKvJ36YuySCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T15:38:21.991188Z","bundle_sha256":"fd9a892728413f0c025403c611a62c28e0894932782804d2d28d52003d75ed3d"}}