{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:CC4ZNQBSF77YLKRDDV442OTMAR","short_pith_number":"pith:CC4ZNQBS","canonical_record":{"source":{"id":"2306.17778","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-30T16:31:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5bde7ace1d87d55365f359ac75795476849ef82c90a87e92b104c70f95638412","abstract_canon_sha256":"82d15205f39a9c506b2b2cd53cd9c3afbaaf198c867b087fc423dc7db4a1da0b"},"schema_version":"1.0"},"canonical_sha256":"10b996c0322fff85aa231d79cd3a6c04499370160775191b48d8a3f8bbf1c941","source":{"kind":"arxiv","id":"2306.17778","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.17778","created_at":"2026-07-05T07:36:01Z"},{"alias_kind":"arxiv_version","alias_value":"2306.17778v3","created_at":"2026-07-05T07:36:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.17778","created_at":"2026-07-05T07:36:01Z"},{"alias_kind":"pith_short_12","alias_value":"CC4ZNQBSF77Y","created_at":"2026-07-05T07:36:01Z"},{"alias_kind":"pith_short_16","alias_value":"CC4ZNQBSF77YLKRD","created_at":"2026-07-05T07:36:01Z"},{"alias_kind":"pith_short_8","alias_value":"CC4ZNQBS","created_at":"2026-07-05T07:36:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:CC4ZNQBSF77YLKRDDV442OTMAR","target":"record","payload":{"canonical_record":{"source":{"id":"2306.17778","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-30T16:31:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5bde7ace1d87d55365f359ac75795476849ef82c90a87e92b104c70f95638412","abstract_canon_sha256":"82d15205f39a9c506b2b2cd53cd9c3afbaaf198c867b087fc423dc7db4a1da0b"},"schema_version":"1.0"},"canonical_sha256":"10b996c0322fff85aa231d79cd3a6c04499370160775191b48d8a3f8bbf1c941","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:36:01.765125Z","signature_b64":"g5JxdUnpGiMyzzOjGVvYank7wKOPbJ2/fhj2zPbEJFo9P7V5+VR7HouWXZTxO1WqN/2icL4QBgKEs/lkp49VDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10b996c0322fff85aa231d79cd3a6c04499370160775191b48d8a3f8bbf1c941","last_reissued_at":"2026-07-05T07:36:01.764767Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:36:01.764767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.17778","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:36:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9R/LRzWEdYqqL6eOofZ8JXtaWajD+7a53sjH2R2kCXlBOT6nLj5UTEtQ6krIIqz0sOJLjMSgy7BcsQHhDLxzCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T13:51:33.734233Z"},"content_sha256":"b4b536074560878df9e1f8d2125b8920b42d4d1c2d7ea3c7d955c582b93304de","schema_version":"1.0","event_id":"sha256:b4b536074560878df9e1f8d2125b8920b42d4d1c2d7ea3c7d955c582b93304de"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:CC4ZNQBSF77YLKRDDV442OTMAR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Look, Remember and Reason: Grounded reasoning in videos with language models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Apratim Bhattacharyya, Mingu Lee, Pulkit Madan, Reza Pourreza, Roland Memisevic, Sunny Panchal","submitted_at":"2023-06-30T16:31:14Z","abstract_excerpt":"Multi-modal language models (LM) have recently shown promising performance in high-level reasoning tasks on videos. However, existing methods still fall short in tasks like causal or compositional spatiotemporal reasoning over actions, in which model predictions need to be grounded in fine-grained low-level details, such as object motions and object interactions. In this work, we propose training an LM end-to-end on low-level surrogate tasks, including object detection, re-identification, and tracking, to endow the model with the required low-level visual capabilities. We show that a two-strea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.17778","kind":"arxiv","version":3},"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/2306.17778/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":"2026-07-05T07:36:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4lkYNRfFto9/ukCN5DIHmtgWCI25nXVhAwjJJGW/ks58cAWLkDgBh9gDCxgFLX92K/ExKomWuiKGlIrMPGISAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T13:51:33.736491Z"},"content_sha256":"7cd71bec5807ea63b400d2039220e62a1a68bfaac60299abf3945240e1946911","schema_version":"1.0","event_id":"sha256:7cd71bec5807ea63b400d2039220e62a1a68bfaac60299abf3945240e1946911"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CC4ZNQBSF77YLKRDDV442OTMAR/bundle.json","state_url":"https://pith.science/pith/CC4ZNQBSF77YLKRDDV442OTMAR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CC4ZNQBSF77YLKRDDV442OTMAR/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":"2026-08-17T13:51:33Z","links":{"resolver":"https://pith.science/pith/CC4ZNQBSF77YLKRDDV442OTMAR","bundle":"https://pith.science/pith/CC4ZNQBSF77YLKRDDV442OTMAR/bundle.json","state":"https://pith.science/pith/CC4ZNQBSF77YLKRDDV442OTMAR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CC4ZNQBSF77YLKRDDV442OTMAR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CC4ZNQBSF77YLKRDDV442OTMAR","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":"82d15205f39a9c506b2b2cd53cd9c3afbaaf198c867b087fc423dc7db4a1da0b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-30T16:31:14Z","title_canon_sha256":"5bde7ace1d87d55365f359ac75795476849ef82c90a87e92b104c70f95638412"},"schema_version":"1.0","source":{"id":"2306.17778","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.17778","created_at":"2026-07-05T07:36:01Z"},{"alias_kind":"arxiv_version","alias_value":"2306.17778v3","created_at":"2026-07-05T07:36:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.17778","created_at":"2026-07-05T07:36:01Z"},{"alias_kind":"pith_short_12","alias_value":"CC4ZNQBSF77Y","created_at":"2026-07-05T07:36:01Z"},{"alias_kind":"pith_short_16","alias_value":"CC4ZNQBSF77YLKRD","created_at":"2026-07-05T07:36:01Z"},{"alias_kind":"pith_short_8","alias_value":"CC4ZNQBS","created_at":"2026-07-05T07:36:01Z"}],"graph_snapshots":[{"event_id":"sha256:7cd71bec5807ea63b400d2039220e62a1a68bfaac60299abf3945240e1946911","target":"graph","created_at":"2026-07-05T07:36:01Z","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/2306.17778/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-modal language models (LM) have recently shown promising performance in high-level reasoning tasks on videos. However, existing methods still fall short in tasks like causal or compositional spatiotemporal reasoning over actions, in which model predictions need to be grounded in fine-grained low-level details, such as object motions and object interactions. In this work, we propose training an LM end-to-end on low-level surrogate tasks, including object detection, re-identification, and tracking, to endow the model with the required low-level visual capabilities. We show that a two-strea","authors_text":"Apratim Bhattacharyya, Mingu Lee, Pulkit Madan, Reza Pourreza, Roland Memisevic, Sunny Panchal","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-30T16:31:14Z","title":"Look, Remember and Reason: Grounded reasoning in videos with language models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.17778","kind":"arxiv","version":3},"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:b4b536074560878df9e1f8d2125b8920b42d4d1c2d7ea3c7d955c582b93304de","target":"record","created_at":"2026-07-05T07:36:01Z","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":"82d15205f39a9c506b2b2cd53cd9c3afbaaf198c867b087fc423dc7db4a1da0b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-30T16:31:14Z","title_canon_sha256":"5bde7ace1d87d55365f359ac75795476849ef82c90a87e92b104c70f95638412"},"schema_version":"1.0","source":{"id":"2306.17778","kind":"arxiv","version":3}},"canonical_sha256":"10b996c0322fff85aa231d79cd3a6c04499370160775191b48d8a3f8bbf1c941","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"10b996c0322fff85aa231d79cd3a6c04499370160775191b48d8a3f8bbf1c941","first_computed_at":"2026-07-05T07:36:01.764767Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:36:01.764767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"g5JxdUnpGiMyzzOjGVvYank7wKOPbJ2/fhj2zPbEJFo9P7V5+VR7HouWXZTxO1WqN/2icL4QBgKEs/lkp49VDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:36:01.765125Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.17778","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b4b536074560878df9e1f8d2125b8920b42d4d1c2d7ea3c7d955c582b93304de","sha256:7cd71bec5807ea63b400d2039220e62a1a68bfaac60299abf3945240e1946911"],"state_sha256":"6efe8487f5acc5e5cae3eac8fd3b0a415649e30f2437ed61f0432d189b6a9297"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kx7QqtomRfy5dr8rSvGCKkv4Y+Gs7JT/DcL7GL6s7wwA4i3mvtbn438sBMcm1VLXBJthn5IQDF0poVLXNgQHCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T13:51:33.739396Z","bundle_sha256":"ede1c68ff0e5e20b59ce5639460d9f7bd89d95619b5d6754793fa4129409baaa"}}